Abdollahi, M, Ni, W, Abolhasan, M & Li, S 2021, 'Software-Defined Networking-Based Adaptive Routing for Multi-Hop Multi-Frequency Wireless Mesh', IEEE Transactions on Vehicular Technology, vol. 70, no. 12, pp. 13073-13086.
View/Download from: Publisher's site
View description>>
While multi-hop multi-frequency mesh has been extensively studied in the past decades, only several deployable and relatively bulky systems have been developed to support small numbers of hops under stationary settings. This paper presents a new Software-Defined Networking (SDN)-based design of multihop multi-frequency mesh. A new lightweight hardware platform is developed to support adaptive routing and frequency selection, by modifying and integrating commercial-off-the-shelf WiFi modules. We also extend the celebrated Dijkstra’s algorithm in support of the new multi-hop multi-frequency platform, where non-overlapping frequency bands are selected together with the routing paths by maintaining N2 Dijkstra processes for N frequency bands. These processes interact to recursively select the optimal upstream node and frequency for each downstream frequency of a node. Mininet-WiFi is used to evaluate the routing of the new system under dense network settings. The results indicate that our system improves the end-to-end throughput by taking background WiFi traffic into account and adaptively selecting the routes and frequencies, as compared to the shortest-path-based routing strategy.
Alabsi, MI & Gill, AQ 2021, 'A Review of Passenger Digital Information Privacy Concerns in Smart Airports', IEEE Access, vol. 9, no. 99, pp. 33769-33781.
View/Download from: Publisher's site
Alqahtani, M & Braun, R 2021, 'Reviewing Influence of UTAUT2 Factors on Cyber Security Compliance: A Literature Review', Journal of Information Assurance & Cybersecurity, vol. 2021, pp. 1-15.
View/Download from: Publisher's site
View description>>
Evidence suggests that, regardless of the number of technical controls in place, organizations will still experience security breaches. Organizations spend millions of dollars on their cyber security infrastructure that includes technical and non-technical measures but mostly disregarded the most important asset and vulnerability the human.
Alzoubi, Y & Gill, A 2021, 'The Critical Communication Challenges Between Geographically Distributed Agile Development Teams: Empirical Findings', IEEE Transactions on Professional Communication, vol. 64, no. 4, pp. 322-337.
View/Download from: Publisher's site
View description>>
Background: Although a number of empirical studies have investigated communication challenges during recent years, we still need to discover the most critical challenges that face communication when agile development is geographically distributed. We also need to discover how successful geographically distributed agile development (GDAD) organizations deal with these challenges. Literature review: Most previous studies reported that the critical challenges facing GDAD communication can be categorized into five themes: differences in cultures, different time zones, different spoken languages, different personal skills, and the efficiency and effectiveness of communication tools used. Research questions: 1. What are the challenges of communication between GDAD teams? 2. How can the impact of GDAD communication challenges be mitigated? Methodology: Data were collected by interviewing 12 members of a three-team organization using distributed agile development. These teams are distributed over three countries; the main team located in Australia, the developers' team located in China, and the testers' team located in India. A thematic analysis technique was used to identify communication challenges and practices used to mitigate the effect of these challenges. Results: Our findings reveal that the five challenges are still critical to GDAD. Moreover, we report a new critical challenge of communication in GDAD, the insufficient documentation provided by distributed teams and members. In addition, we recommend several practices to mitigate the impact of these challenges. Conclusions: Communication among distributed agile development teams still faces several critical challenges, and the solutions to these challenges provided in recent years have not been sufficient. This fact prompts the need for more research on how the impact of these challenges can be lessened.
Amirgholipour, S, Jia, W, Liu, L, Fan, X, Wang, D & He, X 2021, 'PDANet: Pyramid density-aware attention based network for accurate crowd counting', Neurocomputing, vol. 451, pp. 215-230.
View/Download from: Publisher's site
View description>>
Crowd counting, i.e., estimating the number of people in crowded areas, has attracted much interest in the research community. Although many attempts have been reported, crowd counting remains an open real-world problem due to the vast density variations and severe occlusion within the interested crowd area. In this paper, we propose a novel Pyramid Density-Aware Attention based network, abbreviated as PDANet, which leverages the attention, pyramid scale feature, and two branch decoder modules for density-aware crowd counting. The PDANet utilizes these modules to extract features of different scales while focusing on the relevant information and suppressing the misleading information. We also address the variation of crowdedness levels among different images with a Density-Aware Decoder (DAD) modules. For this purpose, a classifier is constructed to evaluate the density level of the input features and then passes them to the corresponding high and low density DAD modules. Finally, we generate an overall density map by considering the summation of low and high crowdedness density maps. Meanwhile, we employ different losses aiming to achieve a precise density map for the input scene. Extensive evaluations conducted on the challenging benchmark datasets well demonstrate the superior performance of the proposed PDANet in terms of the accuracy of counting and generated density maps over the well-known state-of-the-art approaches.
Amiri, M, Abolhasan, M, Shariati, N & Lipman, J 2021, 'Soil moisture remote sensing using SIW cavity based metamaterial perfect absorber', Scientific Reports, vol. 11, no. 1, pp. 1-17.
View/Download from: Publisher's site
View description>>
AbstractContinuous and accurate sensing of water content in soil is an essential and useful measure in the agriculture industry. Traditional sensors developed to perform this task suffer from limited lifetime and also need to be calibrated regularly. Further, maintenance, support, and deployment of these sensors in remote environments provide additional challenges to the use of conventional soil moisture sensors. In this paper, a metamaterial perfect absorber (MPA) based soil moisture sensor is introduced. The ability of MPAs to absorb electromagnetic signals with near 100% efficiency facilitates the design of highly accurate and low-profile radio frequency passive sensors. MPA based sensor can be fabricated from highly durable materials and can therefore be made more resilient than traditional sensors. High resolution sensing is achieved through the creation of physical channels in the substrate integrated waveguide (SIW) cavity. The proposed sensor does not require connection for both electromagnetic signals or for adding a testing sample. Importantly, an external power supply is not needed, making the MPA based sensor the perfect solution for remote and passive sensing in modern agriculture. The proposed MPA based sensor has three absorption bands due to the various resonance modes of the SIW cavity. By changing the soil moisture level, the absorption peak shifts by 10 MHz, 23.3 MHz, and 60 MHz, which is correlated with the water content percentage at the first, second and third absorption bands, respectively. Finally, a $$6 \times 6$$ 6 × 6 cell array with...
Amiri, M, Tofigh, F, Shariati, N, Lipman, J & Abolhasan, M 2021, 'Review on Metamaterial Perfect Absorbers and Their Applications to IoT', IEEE Internet of Things Journal, vol. 8, no. 6, pp. 4105-4131.
View/Download from: Publisher's site
View description>>
Future Internet of Things (IoT) devices are expected to be fully ubiquitous. To achieve this vision, a new generation of IoT devices needs to be developed, which can operate autonomously. To achieve autonomy, IoT devices must be completely wireless, both in terms of transmission and power. Further, accurate sensing is another crucial parameter of autonomy. Several wireless standards have been developed for improving the efficiency of IoT applications. However, the powering of IoT devices, sensor accuracy, and efficiency of electronic devices are open research problems in literature. With the advent of metamaterial perfect absorbers (MPAs), electromagnetic waves can be used as a source of energy, to enable sensing of the phenomenon and as a carrier for exchanging data. In this article, an extensive application-based investigation has been conducted on design principles and various methods of enhancing MPA characteristics. Moreover, the current applications that benefit from MPA, such as absorption of undesired frequencies, optical switching, energy harvesting, and sensing, are investigated. Finally, some implemented examples of MPA in industrial applications are provided along with possible directions for future work and open research areas.
Ansari, M, Jones, B, Zhu, H, Shariati, N & Guo, YJ 2021, 'A Highly Efficient Spherical Luneburg Lens for Low Microwave Frequencies Realized With a Metal-Based Artificial Medium', IEEE Transactions on Antennas and Propagation, vol. 69, no. 7, pp. 3758-3770.
View/Download from: Publisher's site
View description>>
IEEE This paper describes a novel spherical lens antenna constructed of planar layers of light-weight foam with equally spaced conducting inclusions of varying sizes on an orthogonal grid. This construction largely overcomes the problems of weight and cost that have tended to make larger low frequency Luneburg lenses impractical. A penalty for this type of design is that some anisotropy exists in the lens’s dielectric. This effect is examined using both ray tracing techniques and full-wave simulation and it is found that the principal consequence is that the focal length of the lens varies in different directions. Methods for mitigating the effect are proposed. A prototype lens antenna intended for cellular use in the band 3.3 – 3.8 GHz with dual linear slant polarized feeds was designed and constructed to confirm the findings. Measured results show a peak gain of 23 dBi which is less than 1 dB lower than the maximum possible directivity from the lens’s cross section area. Scanning loss is less than 0.8 dB over the whole sphere. Simulated and measured performance show excellent agreement over the whole sphere. The overall performance of the prototype lens antenna demonstrates that this type of lens should be very suitable for use in high-gain multibeam antennas at lower microwave frequencies.
Anwar, MJ, Gill, AQ, Hussain, FK & Imran, M 2021, 'Secure big data ecosystem architecture: challenges and solutions.', EURASIP J. Wirel. Commun. Netw., vol. 2021, pp. 130-130.
View/Download from: Publisher's site
Bai, J, Liu, Y, Ren, Y, Nie, Z & Guo, YJ 2021, 'Efficient Synthesis of Linearly Polarized Shaped Patterns Using Iterative FFT via Vectorial Least-Square Active Element Pattern Expansion', IEEE Transactions on Antennas and Propagation, vol. 69, no. 9, pp. 6040-6045.
View/Download from: Publisher's site
Buchlak, QD, Esmaili, N, Leveque, J-C, Bennett, C, Farrokhi, F & Piccardi, M 2021, 'Machine learning applications to neuroimaging for glioma detection and classification: An artificial intelligence augmented systematic review', Journal of Clinical Neuroscience, vol. 89, pp. 177-198.
View/Download from: Publisher's site
View description>>
Glioma is the most common primary intraparenchymal tumor of the brain and the 5-year survival rate of high-grade glioma is poor. Magnetic resonance imaging (MRI) is essential for detecting, characterizing and monitoring brain tumors but definitive diagnosis still relies on surgical pathology. Machine learning has been applied to the analysis of MRI data in glioma research and has the potential to change clinical practice and improve patient outcomes. This systematic review synthesizes and analyzes the current state of machine learning applications to glioma MRI data and explores the use of machine learning for systematic review automation. Various datapoints were extracted from the 153 studies that met inclusion criteria and analyzed. Natural language processing (NLP) analysis involved keyword extraction, topic modeling and document classification. Machine learning has been applied to tumor grading and diagnosis, tumor segmentation, non-invasive genomic biomarker identification, detection of progression and patient survival prediction. Model performance was generally strong (AUC = 0.87 ± 0.09; sensitivity = 0.87 ± 0.10; specificity = 0.0.86 ± 0.10; precision = 0.88 ± 0.11). Convolutional neural network, support vector machine and random forest algorithms were top performers. Deep learning document classifiers yielded acceptable performance (mean 5-fold cross-validation AUC = 0.71). Machine learning tools and data resources were synthesized and summarized to facilitate future research. Machine learning has been widely applied to the processing of MRI data in glioma research and has demonstrated substantial utility. NLP and transfer learning resources enabled the successful development of a replicable method for automating the systematic review article screening process, which has potential for shortening the time from discovery to clinical application in medicine.
Chakraborty, S, Milner, LE, Zhu, X, Sevimli, O, Parker, AE & Heimlich, MC 2021, 'An Edge-Coupled Marchand Balun With Partial Ground for Excellent Balance in 0.13 μm SiGe Technology', IEEE Transactions on Circuits and Systems II: Express Briefs, vol. 68, no. 1, pp. 226-230.
View/Download from: Publisher's site
View description>>
An edge-coupled meandered three-coupled-line Marchand balun with a partial ground plane implemented in 0.13 μ {m} SiGe Bi-CMOS technology is presented in this brief. The balance performance of the designed balun is significantly improved by creating a 'no ground plane' beneath the coupled-line structure, which is demonstrated by simulating two baluns: one with a partial ground and the other with a solid ground underneath. The measured amplitude and phase imbalances are less than 0.4 dB and 2.5°, across the 3-dB bandwidth from 21.5 to 95 GHz, surpassing previously reported results of edge-coupled Marchand baluns. The balun occupies 230 μ \text{m}\,\,×370\,\,μ {m}.
Chen, D, Liu, Y, Chen, S-L, Qin, P-Y & Guo, YJ 2021, 'A Wideband High-Gain Multilinear Polarization Reconfigurable Antenna', IEEE Transactions on Antennas and Propagation, vol. 69, no. 7, pp. 4136-4141.
View/Download from: Publisher's site
View description>>
IEEE In this Communication, a wideband low-profile antenna with switchable multi-linear polarizations (MLPs) is proposed. An odd number of dipoles with trapezoidal-shaped arms printed on both sides of a substrate are adopted as reconfigurable radiators, which provides a much smaller polarization interval than using an adjacent even number of dipoles. PIN diodes with simple DC biasing lines are loaded to reconfigure the polarization states. A circular-contoured artificial magnetic conductor (AMC) reflector using hexagon-patch cells is employed to reduce the antenna profile. The whole multiple dipole structure is rotationally invariant which provides almost rotationally invariant antenna performance for different LPs. In addition, the antenna can be easily re-designed when adjusting the number of dipoles for different LPs. A seven-LP reconfigurable antenna working in 2:85 GHz to 3:40 GHz is used as an example to give the detailed parameters study and performance analysis. Three antennas with 5, 7 and 9 reconfigurable LPs are designed and measured. With 0:035λ height, they achieve the measured overlapped bandwidths of 20:6%, 17:6% and 15:9% for 5, 7 and 9 LPs, respectively, and their measured peak gains are ranging from 8:3 to 8:5 dBi.
Chen, L, Chen, L, Ge, Z, Sun, Y, Hamilton, TJ & Zhu, X 2021, 'A 90-GHz Asymmetrical Single-Pole Double-Throw Switch With >19.5-dBm 1-dB Compression Point in Transmission Mode Using 55-nm Bulk CMOS Technology', IEEE Transactions on Circuits and Systems I: Regular Papers, vol. 68, no. 11, pp. 4616-4625.
View/Download from: Publisher's site
View description>>
The millimeter-wave (mm-wave) single-pole double-throw (SPDT) switch designed in bulk CMOS technology has limited power-handling capability in terms of 1-dB compression point (P1dB) inherently. This is mainly due to the low threshold voltage of the switching transistors used for shunt-connected configuration. To solve this issue, an innovative approach is presented in this work, which utilizes a unique passive ring structure. It allows a relatively strong RF signal passing through the TX branch, while the switching transistors are turned on. Thus, the fundamental limitation for P1dB due to reduced threshold voltage is overcome. To prove the presented approach is feasible in practice, a 90-GHz asymmetrical SPDT switch is designed in a standard 55-nm bulk CMOS technology. The design has achieved an insertion loss of 3.2 dB and 3.6 dB in TX and RX mode, respectively. Moreover, more than 20 dB isolation is obtained in both modes. Because of using the proposed passive ring structure, a remarkable P1dB is achieved. No gain compression is observed at all, while a 19.5 dBm input power is injected into the TX branch of the designed SPDT switch. The die area of this design is only 0.26 mm2.
Chen, L, Liu, H, Hora, J, Zhang, JA, Yeo, KS & Zhu, X 2021, 'A Monolithically Integrated Single-Input Load-Modulated Balanced Amplifier With Enhanced Efficiency at Power Back-Off', IEEE Journal of Solid-State Circuits, vol. 56, no. 5, pp. 1553-1564.
View/Download from: Publisher's site
View description>>
In this article, the design of a power amplifier (PA) using a simple but effective architecture, namely, load-modulated balanced amplifier (LMBA), is presented. Using this architecture for PA design, it can achieve not only a relatively high saturated output power but also an excellent efficiency enhancement at the power back-off (PBO) region. To prove that the presented approach is feasible in practice, a PA is designed in a 1-μm gallium arsenide (GaAs) HBT process. Operating under a 5-V power supply, the PA can deliver more than 31-dBm saturated output power with 36% collector efficiency (CE) at 5 GHz. Moreover, it also achieves 1.2 and 1.23 times CE enhancement over an idealistic Class-B PA at 6- and 9-dB PBO levels, respectively. Finally, the designed PA supports 64-quadrature amplitude modulation (QAM) with 80 Msys/s at 22-dBm average output power while still maintaining an error vector magnitude (EVM) and adjacent channel power ratio (ACPR) better than -29.5 dB and -29.4 dBc, respectively.
Chen, L, Liu, Y, Yang, S & Guo, YJ 2021, 'Efficient Synthesis of Filter-and-Sum Array With Scanned Wideband Frequency-Invariant Beam Pattern and Space-Frequency Notching', IEEE Signal Processing Letters, vol. 28, pp. 384-388.
View/Download from: Publisher's site
View description>>
IEEE This work generalizes the Fourier transform (FT)-based frequency-invariant beamforming (FIB) method to the synthesis of scanned frequency-invariant (FI) beam pattern with space-frequency notching for an array with non-isotropic elements. Wideband FI pattern characteristics are described by using multiple reference sub-band FI patterns that are obtained through an iterative single-frequency FT-based synthesis method. By applying fast Fourier transform (FFT) on the combination of these multiple reference sub-band FI patterns, a wideband excitation distribution can be generated. Based on this excitation distribution, we construct a new wideband excitation distribution that is conjugate-symmetric about zero frequency, so that real-valued finite-impulse-response (FIR) filter coefficients can be obtained by applying FFT on the constructed distribution. Two numerical examples are introduced to show the effectiveness and efficiency of the proposed method for synthesizing scanned FI beam patterns with complicated notching requirements.
Chen, R, Zhu, L, Wong, S, Lin, J, Yang, Y, Li, Y & He, Y 2021, 'Miniaturized full‐metal bandpass filter and multiplexer using circular spiral resonator', IET Microwaves, Antennas & Propagation, vol. 15, no. 6, pp. 606-619.
View/Download from: Publisher's site
View description>>
AbstractThis article proposes a new class of miniaturized full‐metal bandpass filters (BPFs) and multiplexers using circular spiral resonators (CSRs). The proposed metal CSR is supported on the metal cavity's wall, which serves as a short‐end resonator. This CSR has obvious size reduction compared to traditional cavity resonators and owns low insertion loss, high power capacity and high selectivity. Then, three BPFs using two, three and four CSRs are designed and analysed. All the proposed filters have transmission zeroes (TZs) produced by the source‐load coupling without introducing additional coupling structure. The proposed CSR is further used to design diplexer and quadruplexer. All the proposed filters have ultra‐compact size, especially, the size of quadruplexer is only 0.23λ0 × 0.081λ0 × 0.067λ0. Finally, the fourth‐order filter and quadruplexer are fabricated and measured, the good agreement between the measured results and the simulated results validates the proposed design concepts.
Chen, R-S, Wong, S-W, Lin, J-Y, Yang, Y, Li, Y, Zhang, L, He, Y & Zhu, L 2021, 'Reconfigurable Cavity Bandpass Filters Using Fluid Dielectric', IEEE Transactions on Industrial Electronics, vol. 68, no. 9, pp. 8603-8614.
View/Download from: Publisher's site
View description>>
A novel method for the development of a reconfigurable cavity bandpass filter using fluid dielectric is proposed. Dielectric material can produce an effective permittivityeff of the resonant mode when it is loaded into the cavity. Thus, a tube filled with fluid dielectric, e.g., distilled water, can achieve controlled and reversibleeff by adjusting the amount of water in the tube. The same manner of resonant frequency can be achieved as the resonant frequency is related toeff, and then frequency tuning is realized. The fluid property can realize easier and faster tuning mechanism than conventional solid dielectric. Aseff is affected by the loaded dielectric parallel to the electric field, a triple-mode resonator with resonant modes TE101, TE011, and TM110, which have orthogonal electric fields, is investigated to realize tri-band reconfiguration. Theeff, as well as the resonant frequencies, corresponding to each mode can be individually controlled by adjusting their related water posts. Then, reconfigurable single-band and tri-band bandpass filters are designed. A reconfigurable tri-band cavity filter using a triple-mode cavity resonator and fluid dielectric with individual and continuous frequency tuning is reported for the first time. Finally, the reconfigurable tri-band filter is fabricated and measured to validate the concept.
Chen, R-S, Zhu, L, Lin, J-Y, Wong, S-W, Yang, Y, Li, Y, Zhang, L & He, Y 2021, 'High-Isolation In-Band Full-Duplex Cavity-Backed Slot Antennas in a Single Resonant Cavity', IEEE Transactions on Antennas and Propagation, vol. 69, no. 11, pp. 7092-7102.
View/Download from: Publisher's site
Chu, L, Shi, J & Braun, R 2021, 'The Impacts of Material Uncertainty in Electro-Migration of SAC Solder Electronic Packaging by Monte Carlo-Based Stochastic Finite-Element Model', IEEE Transactions on Components, Packaging and Manufacturing Technology, vol. 11, no. 11, pp. 1864-1876.
View/Download from: Publisher's site
View description>>
Electro-migration (EM) induced by electric current under the conditions of multi-physical fields in integrated circuits and electronic packaging is a crucial factor that affects reliability and safety of the entire system. The uncertainty quantification and propagation in the EM process are the challenging issues that deserve more attention. In this paper, the uncertainties in the related material parameters of Sn-Ag-Cu (SAC) solder and copper conductors are taken into consideration based on the stochastic finite element model. The corners and edges of the contact surface in SAC solder are the most dynamic and active places with the maximum concentration gradient. This reaches a satisfied agreement with the experimental results and parallel numerical investigations in the literatures. The extreme values of the concentration and its gradient in each time step are computed and recorded. The accuracy and convergence of results are confirmed by the comparison of different period durations and time step scales with discrete time points. Furthermore, the probability density distribution, mean and variance of the extreme values in different time steps are recorded and compared. Based on the huge database provided by the Monte Carlo based stochastic finite element model (MC-SFEM), the correlations between the material parameters and the concentration as well as the concentration gradients are analyzed. The proposed MC-SFEM is a feasible and effective model for the comprehensive analysis of EM with the potential in uncertainty and reliability analysis.
Chu, L, Zhou, P, Shi, J & Braun, R 2021, 'Sensitivity Analysis for Geometrical Parameters of BGA in Flip-Chip Packaging Under Random Shear Stress and Thermal Temperature', IEEE Transactions on Components, Packaging and Manufacturing Technology, vol. 11, no. 5, pp. 765-777.
View/Download from: Publisher's site
View description>>
The ball grid array (BGA) is a type of popular and competitive package in electronic flip-chip packaging due to its feasibility in high density integrated circuits and convenience in the product design process. However, the effects of geometrical parameters on the product reliability and safety under complicated operating situations are not clear. In this article, an independent solder ball and four typical BGA cases are compared and analyzed based on the finite element (FE) method. The coupled random shear stress and thermal temperature are simulated in the FE models by the Latin hypercube sampling (LHS) method. According to the sensitivity analysis, the edges of the solder ball are the most dangerous places, which has the qualitative agreement with the experimental results. The complete grid array in the first BGA case with homogeneous stress and strain distribution is the most reliable and competitive design. Furthermore, the normal and Weibull distributions are not suitable to present the stochastic response of solder balls in flip-chip packaging under random coupled mechanical and thermal stress. In order to effectively improve packaging performance and reliability, the radius of the solder ball acts as the key factor, while the upper and lower height of the solder ball, as well as the pitch along the X - and Y -directions, are all feasible and potential for the geometrical optimization. However, the small scale of the solder ball causing microstress concentration points and discontinuous volumes is the essential challenge for industrial manufacturing. The work in this article provides helpful references to the industrial electronic package geometrical optimal design.
Dang, Z, Li, L, Ni, W, Liu, R, Peng, H & Yang, Y 2021, 'How does rumor spreading affect people inside and outside an institution', Information Sciences, vol. 574, pp. 377-393.
View/Download from: Publisher's site
View description>>
In this paper, we study the propagation characteristics of rumors in an institution and develop the rumor dissemination model inside the institution. Different from the traditional model, a person in the proposed model can make a judgement about the message and decide to propagate it or refute it, and most people inside the institution can refute the rumor spreaders and propagate the genuine messages to uninformed people when they have confirmed the message is a rumor. Then, we split all the people into two institutions (inside and outside). Since the rumors and genuine messages from the institution can have a non-negligible impact on people outside the institution, we put forward a new double-institution rumor propagation model, and the model considers the impact of messages on the inside and outside of the institution simultaneously. Based on the two proposed models, the basic reproduction numbers are obtained respectively, and the local and global stability of the rumor-free equilibrium points are discussed separately. We numerically simulate the propagation of rumors in small-world networks. The simulation is carried out to verify the validity of the proposed model, and our model is closer to the reality than traditional models.
Dao, N-N, Na, W, Tran, A-T, Nguyen, DN & Cho, S 2021, 'Energy-Efficient Spectrum Sensing for IoT Devices', IEEE Systems Journal, vol. 15, no. 1, pp. 1077-1085.
View/Download from: Publisher's site
Du, H, Gao, H & Jia, W 2021, 'Joint Frequency and DOA Estimation with Automatic Pairing Using the Rayleigh–Ritz Theorem', Computers, Materials & Continua, vol. 67, no. 3, pp. 3907-3919.
View/Download from: Publisher's site
View description>>
This paper presents a novel scheme for joint frequency and direction of arrival (DOA) estimation, that pairs frequencies and DOAs automatically without additional computations. First, when the property of the Kronecker product is used in the received array signal of the multiple-delay output model, the frequency-angle steering vector can be reconstructed as the product of the frequency steering vector and the angle steering vector. The frequency of the incoming signal is then obtained by searching for the minimal eigenvalue among the smallest eigenvalues that depend on the frequency parameters but are irrelevant to the DOAs. Subsequently, the DOA related to the selected frequency is acquired through some operations on the minimal eigenvector according to the Rayleigh–Ritz theorem, which realizes the natural pairing of frequencies and DOAs. Furthermore, the proposed method can not only distinguish multiple sources, but also effectively deal with other arrays. The effectiveness and superiority of the proposed algorithm are further analyzed by simulations.
Duong, HC, Tran, LTT, Vu, MT, Nguyen, D, Tran, NTV & Nghiem, LD 2021, 'A new perspective on small-scale treatment systems for arsenic affected groundwater', Environmental Technology & Innovation, vol. 23, pp. 101780-101780.
View/Download from: Publisher's site
View description>>
This work provides a new perspective on small-scale treatment systems to remove arsenic from groundwater for potable applications in low-income communities. Data corroborated from the literature highlight a significant challenge to providing potable water in a financially sustainable manner in arsenic affected areas. Analysis of the literature also reveals notable deficiency in the current practice, especially the overfocus on household-scale treatment systems for arsenic affected groundwater without adequate maintenance, monitoring, and a systematic cost–benefit analysis. Accurate and reliable analysis of arsenic in water samples at relevant health guideline values is costly and technologically demanding for low-income communities. Significant discrepancy in the performance of household-scale treatment systems can be attributed to the lack of maintenance and systematic monitoring. Moreover, data on the maintenance and compliance monitoring cost of small-scale arsenic treatment systems are very limited in the literature, and the available data show an exponential increase in maintenance cost per treatment capacity unit as the treatment size decreases. On the other hand, significant opportunities exist to increase performance reliability and reduce water treatment cost by taking advantage of the current digital transformation of the water sector. The analysis in this work suggests the need to reframe current practice towards commune-scale treatment systems as an interim step before centralised water supply is available.
Esmaili, N, Buchlak, QD, Piccardi, M, Kruger, B & Girosi, F 2021, 'Multichannel mixture models for time-series analysis and classification of engagement with multiple health services: An application to psychology and physiotherapy utilization patterns after traffic accidents', Artificial Intelligence in Medicine, vol. 111, pp. 101997-101997.
View/Download from: Publisher's site
View description>>
Background
Motor vehicle accidents (MVA) represent a significant burden on health systems globally. Tens of thousands of people are injured in Australia every year and may experience significant disability. Associated economic costs are substantial. There is little literature on the health service utilization patterns of MVA patients. To fill this gap, this study has been designed to investigate temporal patterns of psychology and physiotherapy service utilization following transport-related injuries.
Method
De-identified compensation data was provided by the Australian Transport Accident Commission. Utilization of physiotherapy and psychology services was analysed. The datasets contained 788 psychology and 3115 physiotherapy claimants and 22,522 and 118,453 episodes of service utilization, respectively. 582 claimants used both services, and their data were preprocessed to generate multidimensional time series. Time series clustering was applied using a mixture of hidden Markov models to identify the main distinct patterns of service utilization. Combinations of hidden states and clusters were evaluated and optimized using the Bayesian information criterion and interpretability. Cluster membership was further investigated using static covariates and multinomial logistic regression, and classified using high-performing classifiers (extreme gradient boosting machine, random forest and support vector machine) with 5-fold cross-validation.
Results
Four clusters of claimants were obtained from the clustering of the time series of service utilization. Service volumes and costs increased progressively from clusters 1 to 4. Membership of cluster 1 was positively associated with nerve damage and negatively associated with severe ABI and spinal injuries. Cluster 3 was positively associated with severe ABI, brain/head injury and psychiatric injury. Cluster 4 was positively associated with internal injuries. The classifiers were capable of cla...
Fan, L, Weijie, Y, Jinhong, Y, Andrew, ZJ, Zesong, F & Jianming, Z 2021, 'Radar-communication Spectrum Sharing and Integration: Overview and Prospect', Journal of Radars, vol. 10, no. 3, pp. 467-484.
View/Download from: Publisher's site
View description>>
The need of extra wireless spectrum is on the rise, given the rapid development of global wireless communication industry. To this end, Radar and Communication Spectrum Sharing (RCSS) has gained considerable attentions recently from both industry and academia. In particular, RCSS aims not only at enabling the spectral cohabitation of radar and communication systems, but also at designing a novel joint system that is capable of both functionalities. In this paper, a systematic overview of RCSS by focusing on the two main research directions are provided, i.e., Radar-Communication Coexistence (RCC) and Dual-Functional Radar-Communication (DFRC). We commence by discussing the coexistence examples of radar and communication at various frequency bands, and then elaborate on the practical application scenarios of the DFRC techniques. As a further step, the state-of-the-art approaches of both RCC and DFRC are reviewed. Finally we conclude the paper by identifying a number of open problems in the research area of RCSS.
Farasat, M, Thalakotuna, DN, Hu, Z & Yang, Y 2021, 'A Review on 5G Sub-6 GHz Base Station Antenna Design Challenges', Electronics, vol. 10, no. 16, pp. 2000-2000.
View/Download from: Publisher's site
View description>>
Modern wireless networks such as 5G require multiband MIMO-supported Base Station Antennas. As a result, antennas have multiple ports to support a range of frequency bands leading to multiple arrays within one compact antenna enclosure. The close proximity of the arrays results in significant scattering degrading pattern performance of each band while coupling between arrays leads to degradation in return loss and port-to-port isolations. Different design techniques are adopted in the literature to overcome such challenges. This paper provides a classification of challenges in BSA design and a cohesive list of design techniques adopted in the literature to overcome such challenges.
Gao, G, Yu, Y, Xie, J, Yang, J, Yang, M & Zhang, J 2021, 'Constructing multilayer locality-constrained matrix regression framework for noise robust face super-resolution', Pattern Recognition, vol. 110, pp. 107539-107539.
View/Download from: Publisher's site
Gao, X, Zhang, T, Du, J, An, J, Bu, X & Guo, J 2021, 'A dual-beam lens-free slot-array antenna coupled high-T c superconducting fundamental mixer at the W-band', Superconductor Science and Technology, vol. 34, no. 12, pp. 125006-125006.
View/Download from: Publisher's site
View description>>
Abstract This paper presents a W-band high-T c superconducting (HTS) Josephson-junction fundamental mixer which is coupled using a dual-beam lens-free slot-array antenna. The antenna features a uniplanar six-element slot array fed by an ungrounded coplanar waveguide line, of which each element is a long slot loaded by four rectangular loops. Highly directional radiation is therefore realized by utilizing the long slots and array synthesis to form a relatively large antenna aperture. The antenna also enables asymmetric dual-beam radiation in opposite directions, which not only reduces the RF coupling losses but greatly facilitates the quasi-optics design for the integration of the HTS mixer into a cryocooler. The electromagnetic simulations show that a coupling efficiency as high as −2.2 dB, a realized gain of 13 dB and a front-to-back ratio of 10 dB are achieved at the frequency of 84 GHz. Using this on-chip antenna, a W-band HTS fundamental mixer module is experimentally developed and characterized for different operating temperatures. The measured conversion gain is −10 dB at 20 K and −14.6 dB at 40 K, respectively. The mixer noise temperature is predicted to be around 780 K at 20 K and 1600 K at 40 K, respectively. It is also analyzed that the mixer performance can be further improved if the Josephson junction parameters were optimized.
Ge, Z, Chen, L, Gomez-Garcia, R & Zhu, X 2021, 'Millimeter-Wave Wide-Band Bandpass Filter in CMOS Technology Using a Two-Layered Highpass-Type Approach With Embedded Upper Stopband', IEEE Transactions on Circuits and Systems II: Express Briefs, vol. 68, no. 5, pp. 1586-1590.
View/Download from: Publisher's site
Ge, Z, Chen, L, Yang, L, Gomez-Garcia, R & Zhu, X 2021, 'On-Chip Millimeter-Wave Integrated Absorptive Bandstop Filter in (Bi)-CMOS Technology', IEEE Electron Device Letters, vol. 42, no. 1, pp. 114-117.
View/Download from: Publisher's site
Ghantous, GB & Gill, AQ 2021, 'Evaluating the DevOps Reference Architecture for Multi-cloud IoT-Applications.', SN Comput. Sci., vol. 2, pp. 123-123.
View/Download from: Publisher's site
Gill, AQ 2021, 'A Theory of Information Trilogy: Digital Ecosystem Information Exchange Architecture.', Inf., vol. 12, no. 7, pp. 283-283.
View/Download from: Publisher's site
View description>>
Information sharing is a critical component of a distributed and multi‐actor digital ecosystem (DE). DE actors, individuals and organisations, require seamless, effective, efficient, and secure architecture for exchanging information. Traditional point‐to‐point and ad hoc integrations hinder the ability of DE actors to do so. The challenge is figuring out how to enable information sharing in a complex DE. This paper addresses this important research challenge and proposes the theory of information trilogy and conceptual DE information exchange architecture, which is inspired by the study of nature and flow of matter, energy, and its states in natural ecosystems. This work is a part of the large DE information framework. The scope of this paper is limited to the emerging concept of DE information exchange. The application of the DE information exchange concept is demonstrated with the help of a geospatial information sharing case study example. The results from this paper can be used by researchers and practitioners for defining the DE information exchange as appropriate to their context. This work also complements Shannon’s mathematical theory of communication.
Gong, Y, Li, Z, Zhang, J, Liu, W, Yin, Y & Zheng, Y 2021, 'Missing Value Imputation for Multi-view Urban Statistical Data via Spatial Correlation Learning', IEEE Transactions on Knowledge and Data Engineering, pp. 1-1.
View/Download from: Publisher's site
Gong, Y, Zhang, L, Liu, R, Yu, K & Srivastava, G 2021, 'Nonlinear MIMO for Industrial Internet of Things in Cyber–Physical Systems', IEEE Transactions on Industrial Informatics, vol. 17, no. 8, pp. 5533-5541.
View/Download from: Publisher's site
Guo, YJ, Ansari, M & Fonseca, NJG 2021, 'Circuit Type Multiple Beamforming Networks for Antenna Arrays in 5G and 6G Terrestrial and Non-Terrestrial Networks', IEEE Journal of Microwaves, vol. 1, no. 3, pp. 704-722.
View/Download from: Publisher's site
Guo, YJ, Ansari, M, Ziolkowski, RW & Fonseca, NJG 2021, 'Quasi-Optical Multi-Beam Antenna Technologies for B5G and 6G mmWave and THz Networks: A Review', IEEE Open Journal of Antennas and Propagation, vol. 2, pp. 807-830.
View/Download from: Publisher's site
View description>>
Multi-beam antennas are critical components in future terrestrial and non-terrestrial wireless communications networks. The multiple beams produced by these antennas will enable dynamic interconnection of various terrestrial, airborne and space-borne network nodes. As the operating frequency increases to the high millimeter wave (mmWave) and terahertz (THz) bands for beyond 5G (B5G) and sixth-generation (6G) systems, quasi-optical techniques are expected to become dominant in the design of high gain multi-beam antennas. This paper presents a timely overview of the mainstream quasi-optical techniques employed in current and future multi-beam antennas. Their operating principles and design techniques along with those of various quasi-optical beamformers are presented. These include both conventional and advanced lens and reflector based configurations to realize high gain multiple beams at low cost and in small form factors. New research challenges and industry trends in the field, such as planar lenses based on transformation optics and metasurface-based transmitarrays, are discussed to foster further innovations in the microwave and antenna research community.
He, X, Deng, L, Yang, Y & Feng, B 2021, 'Multifunctional ultrathin reflective metasurface via polarization-decoupled phase for arbitrary circularly or elliptically polarized waves', Optics Express, vol. 29, no. 8, pp. 12736-12736.
View/Download from: Publisher's site
View description>>
Metasurface offers a promising platform in the design of multifunctional devices owing to its unique ability for EMWs manipulation. However, wave-manipulation capabilities for metasurfaces face challenges in manipulating orthogonal EMWs with arbitrary circularly or elliptically polarized EMWs in the microwave region. Herein, single-layer reflective metasurfaces are proposed for independent manipulation of an arbitrary set of orthogonal circularly or elliptically polarized EMWs via polarization-decoupled phase. Taking advantage of single-layer anisotropic meta-atoms, the proposed metasurface can act as a tandem phase modulator, which introduces polarization-decoupled phase profiles for arbitrary circularly and elliptically polarized EMWs based on the Jones matrix. In this way, the proposed metasurface can distinguish a set of orthogonal EMWs with circular or elliptical polarization states and impose arbitrary phase profiles on them independently and simultaneously. For proof-of-concept, bifunctional metasurfaces operating in the microwave region are presented for independent manipulation of three different sets of orthogonal circularly or elliptically polarized EMWs. They create dual independent channels associated with a pair of orthogonal polarization states, performing functions including polarization beam splitting and orbital angular momentum (OAM) multiplexing. Measured and simulated results show a good agreement, confirming that the proposed single-layer reflective metasurfaces are efficient devices that enable meta-devices to independently control arbitrary circular and elliptical polarized EMWs, achieving arbitrary functionalities.
He, X, Yang, Y, Deng, L, Li, S & Feng, B 2021, '3D Printed Sub-Terahertz All-Dielectric Lens for Arbitrary Manipulation of Quasi-Nondiffractive Orbital Angular Momentum Waves', ACS Applied Materials & Interfaces, vol. 13, no. 17, pp. 20770-20778.
View/Download from: Publisher's site
View description>>
Terahertz (THz) vortex waves carrying orbital angular momentum (OAM) hold great potential in dealing with the capacity crunch in wireless high-speed communication systems. Nevertheless, it is quite a challenge for the widespread applications of OAM in the THz regime due to the beam divergence and stringent alignment requirement. To address this issue, an all-dielectric lens (ADL) is proposed for the arbitrary manipulation of quasi-nondiffractive THz OAM waves (QTOWs). On the basis of the concept of the optical conical lens and the multivorticity metasurface, the beam number, the topological charge (TC), and the deflection angle as well as the nondiffractive depth of the generated THz OAM waves are controllable. For proof-of-concept, two ADLs are 3D printed to create single and dual deflected QTOWs, respectively. Remarkably, measured by a THz imaging camera, the desired QTOWs with high mode purity are observed in predesigned directions with a nondiffractive depth predefined theoretically. The proposed designs and experiments, for the first time, verified that the QTOWs could be achieved with a nondiffractive range of 55.58λg (λg = wavelength at 140 GHz) and large deflection angles of 30° and 45°.
Hesamian, MH, Jia, W, He, X, Wang, Q & Kennedy, PJ 2021, 'Synthetic CT images for semi-sequential detection and segmentation of lung nodules', Applied Intelligence, vol. 51, no. 3, pp. 1616-1628.
View/Download from: Publisher's site
View description>>
© 2020, Springer Science+Business Media, LLC, part of Springer Nature. Accurately detecting and segmenting lung nodules from CT images play a critical role in the earlier diagnosis of lung cancer and thus have attracted much interest from the research community. However, due to the irregular shapes of nodules, and the low-intensity contrast between the nodules and other lung areas, precisely segmenting nodules from lung CT images is a very challenging task. In this paper, we propose a highly effective and robust solution to this problem by innovatively utilizing the changes of nodule shapes over continuous slices (inter-slice changes) and develop a deep learning based end-to-end system. Different from the existing 2.5D or 3D methods that attempt to explore the inter-slice features, we propose to create a novel synthetic image to depict the unique changing pattern of nodules between slices in distinctive colour patterns. Based on the new synthetic images, we then adopt the deep learning based image segmentation techniques and develop a modified U-Net architecture to learn the unique color patterns formed by nodules. With our proposed approach, the detection and segmentation of nodules can be achieved simultaneously with an accuracy significantly higher than the state of the arts by 10% without introducing high computation cost. By taking advantage of inter-slice information and form the proposed synthetic image, the task of lung nodule segmentation is done more accurately and effectively.
Hieu, NQ, Hoang, DT, Niyato, D & Kim, DI 2021, 'Optimal Power Allocation for Rate Splitting Communications With Deep Reinforcement Learning', IEEE Wireless Communications Letters, vol. 10, no. 12, pp. 2820-2823.
View/Download from: Publisher's site
View description>>
This letter introduces a novel framework to optimize the power allocation for users in a Rate Splitting Multiple Access (RSMA) network. In the network, messages intended for users are split into different parts that are a single common part and respective private parts. This mechanism enables RSMA to flexibly manage interference and thus enhance energy and spectral efficiency. Although possessing outstanding advantages, optimizing power allocation in RSMA is very challenging under the uncertainty of the communication channel and the transmitter has limited knowledge of the channel information. To solve the problem, we first develop a Markov Decision Process framework to model the dynamic of the communication channel. The deep reinforcement algorithm is then proposed to find the optimal power allocation policy for the transmitter without requiring any prior information of the channel. The simulation results show that the proposed scheme can outperform baseline schemes in terms of average sum-rate under different power and QoS requirements.
Hoang, LM, Zhang, JA, Nguyen, DN, Huang, X, Kekirigoda, A & Hui, K-P 2021, 'Suppression of Multiple Spatially Correlated Jammers', IEEE Transactions on Vehicular Technology, vol. 70, no. 10, pp. 10489-10500.
View/Download from: Publisher's site
View description>>
Effective suppression of inadvertent or deliberate jamming signals is crucial to ensure reliable wireless communication. However, as demonstrated in this paper, when the transmitted jamming signals are highly correlated, and especially when the correlation coefficient varies, nullifying the jamming signals can be challenging. Unlike existing techniques that often assume uncorrelated jamming signals or non-zero but constant correlation, we analyze the impact of the non-zero and varying correlations between transmitted jamming signals on the suppression of the jamming signals. Specifically, we observe that by varying the correlation coefficients between transmitted jamming signals, jammers can 'virtually change' the jamming channels hence their nullspace, even when these channels do not physically change. This makes most jamming suppression techniques that rely on steering receiving beams towards the nullspace of jamming channels no longer applicable. To tackle the problem, we develop techniques to effectively track the jamming nullspace and correspondingly update receiving beams. Monte Carlo simulations show that our proposed techniques can suppress/nullify jamming signals for all considered scenarios with non-zero and varying correlation coefficients amongst transmitted jamming signals.
Hu, X, Wong, S, Li, Y, Lin, J, Yang, Y, Sun, G & Zhang, L 2021, 'Broadband high‐gain slot grid array antenna for millimeter wave applications', International Journal of RF and Microwave Computer-Aided Engineering, vol. 31, no. 1.
View/Download from: Publisher's site
View description>>
A broadband high-gain slot grid array antenna (SGAA) is proposed in this paper. Based on the electromagnetic complementarity principle, the metal elements in the traditional microstrip grid array antenna (GAA) are replaced by a wide slot element. Compared with the GAA, the proposed SGAA achieves broadband and high-gain performance. In order to demonstrate this concept, a prototype with 9-element SGAA is designed using wide slot radiation elements and fabricated on Rogers 5880 printed circuit board (PCB) substrates, which is fed by a 50 Ω coaxial probe. The measured and simulated results show a good agreement. The proposed SGAA achieves a measured peak gain of 14.8 dBi at 26.0 GHz, a 10-dB impedance bandwidth from 22.2 to 28.5 GHz with a fractional bandwidth of 24.9%. These results indicate that the SGAA is with high performance and it is suitable for the fifth-generation (5G) millimeter wave (mmW) wireless communication system.
Huang, H, Zhang, J, Zhang, J, Xu, J & Wu, Q 2021, 'Low-Rank Pairwise Alignment Bilinear Network For Few-Shot Fine-Grained Image Classification', IEEE Transactions on Multimedia, vol. 23, no. 99, pp. 1666-1680.
View/Download from: Publisher's site
Huang, W & Xu, RYD 2021, 'Gaussian process latent variable model factorization for context-aware recommender systems', Pattern Recognition Letters, vol. 151, pp. 281-287.
View/Download from: Publisher's site
Huang, X, Tuyen Le, A & Guo, YJ 2021, 'ALMS Loop Analyses With Higher-Order Statistics and Strategies for Joint Analog and Digital Self-Interference Cancellation', IEEE Transactions on Wireless Communications, vol. 20, no. 10, pp. 6467-6480.
View/Download from: Publisher's site
View description>>
Joint analog and digital self-interference cancellation (SIC) is essential for enabling in-band full duplex (IBFD) communications. Analog least mean square (ALMS) loop is a promising low-complexity high-performance analog SIC technique with multi-tap adaptive filtering capability, but its properties on the tap coefficient variation have not been fully understood. In this paper, analysis based on higher-order statistics of the transmitted signal is performed to solve the problem of evaluating the variance of the ALMS loop's weighting coefficient error, which reveals two additional types of irreducible residual self-interference (SI) produced by an ALMS loop if it runs freely. The residual SI channel impulse response in digital baseband is also analysed and its unique properties are investigated. By introducing a simple track and hold control to the ALMS loop's tap coefficients, a joint analog and digital SIC scheme is proposed to stop the tap coefficient variation and achieve very low residual SI close to the IBFD receiver's noise floor. In a coordinated application scenario, the noise figure of the digital SIC algorithm is proved to be only 1.76 dB at most. Simulation results are provided to verify the theoretical analyses.
Huang, X, Tuyen Le, A & Guo, YJ 2021, 'Transmit Beamforming for Communication and Self-Interference Cancellation in Full Duplex MIMO Systems: A Trade-Off Analysis', IEEE Transactions on Wireless Communications, vol. 20, no. 6, pp. 3760-3769.
View/Download from: Publisher's site
View description>>
The performance of transmit beamforming for both optimized precoding and self-interference cancellation (SIC) in full duplex multiple input multiple output (MIMO) transceivers is analysed in this paper. With sub-space dimension larger than that of the null-space of the self-interference channels, the precoding error is reduced but the interference suppression ratio (ISR) is degraded, resulting in a trade-off between multibeam communication and MIMO SIC. An analytical approach for the ISR evaluation is proposed assuming known eigenvalue distribution of the self-interference channels, and a closed-form ISR expression is derived after applying a uniform distribution approximation. The ISR and precoding error trade-off curves are also formulated. Joint SIC by transmit beamforming and beam-based analog adaptive filters over both propagation and analog domains is proposed to achieve better SIC performance and enable more flexible receive antenna selection. Simulation results verify the theoretical analyses.
Huang, Y, Wang, Q, Jia, W, Lu, Y, Li, Y & He, X 2021, 'See more than once: Kernel-sharing atrous convolution for semantic segmentation', Neurocomputing, vol. 443, pp. 26-34.
View/Download from: Publisher's site
View description>>
The state-of-the-art semantic segmentation solutions usually leverage different receptive fields via multiple parallel branches to handle objects of different sizes. However, employing separate kernels for individual branches may degrade the generalization of the network to objects with different scales, and the computational cost increases with the increase of the number of branches. To tackle this problem, we propose a novel network structure, namely Kernel-Sharing Atrous Convolution (KSAC), where branches with different receptive fields share the same kernel, i.e., let a single kernel ‘see’ the input feature maps more than once with different receptive fields. Experiments conducted on the benchmark PASCAL VOC 2012 dataset show that our proposed sharing strategy can not only boost the network's generalization and representation abilities but also reduce the computational cost significantly. Specifically, on the validation set, when compared with DeepLabv3+, about 2.7G FLOPs and 12.7G FLOPs are saved for output stride = 16 and 8 respectively. In addition, different from the widely used ASPP structure, our proposed KSAC is able to further improve the mIOU by taking benefit of wider context with larger atrous rates. Finally, our KSAC achieves mIOUs of 88.1%, 45.47% and 80.7% on the PASCAL VOC 2012 test set (Everingham et al., 2009), ADE20K dataset (Zhou et al., 2017) and Cityscapes datasets (Marius et al., 2016), respectively. Our full code will be released on Github: https://github.com/edwardyehuang/iSeg.
Huang, Y, Wu, Q, Xu, J, Zhong, Y & Zhang, Z 2021, 'Unsupervised Domain Adaptation with Background Shift Mitigating for Person Re-Identification', International Journal of Computer Vision, vol. 129, no. 7, pp. 2244-2263.
View/Download from: Publisher's site
View description>>
Unsupervised domain adaptation has been a popular approach for cross-domain person re-identification (re-ID). There are two solutions based on this approach. One solution is to build a model for data transformation across two different domains. Thus, the data in source domain can be transferred to target domain where re-ID model can be trained by rich source domain data. The other solution is to use target domain data plus corresponding virtual labels to train a re-ID model. Constrains in both solutions are very clear. The first solution heavily relies on the quality of data transformation model. Moreover, the final re-ID model is trained by source domain data but lacks knowledge of the target domain. The second solution in fact mixes target domain data with virtual labels and source domain data with true annotation information. But such a simple mixture does not well consider the raw information gap between data of two domains. This gap can be largely contributed by the background differences between domains. In this paper, a Suppression of Background Shift Generative Adversarial Network (SBSGAN) is proposed to mitigate the gaps of data between two domains. In order to tackle the constraints in the first solution mentioned above, this paper proposes a Densely Associated 2-Stream (DA-2S) network with an update strategy to best learn discriminative ID features from generated data that consider both human body information and also certain useful ID-related cues in the environment. The built re-ID model is further updated using target domain data with corresponding virtual labels. Extensive evaluations on three large benchmark datasets show the effectiveness of the proposed method.
Jafarizadeh, S, Veitch, D, Tofigh, F, Lipman, J & Abolhasan, M 2021, 'Optimal Synchronizability in Networks of Coupled Systems: Topological View', IEEE Transactions on Network Science and Engineering, vol. 8, no. 2, pp. 1517-1530.
View/Download from: Publisher's site
View description>>
Many engineered and natural systems are modeled as networks of coupled systems. Synchronization is one of their crucial and well-studied behaviors. Uniform coupling strength has been the benchmark practice in the majority of the literature. This paper considers nonuniform coupling strength, and a modified approach to the problem of synchronizability optimization, enabling a reduction to a spectral radius minimization problem, which can reach a unique optimal point on the Pareto Frontier. It is established that adding any edge to a connected graph can only improve synchronizability in this optimal measure. This result is utilized for developing a hierarchy between topologies. It is shown that several proposed structural parameters, including betweenness centrality, do not have any simple relationship to the optimal synchronizability measure.
Jiang, H, Xu, K, Zhang, Q, Yang, Y, Karmokar, DK, Chen, S, Zhao, P, Wang, G & Peng, L 2021, 'Backward-to-Forward Wide-Angle Fast Beam-Scanning Leaky-Wave Antenna With Consistent Gain', IEEE Transactions on Antennas and Propagation, vol. 69, no. 5, pp. 2987-2992.
View/Download from: Publisher's site
View description>>
A planar periodic leaky-wave antenna (PLWA) with continuous backward-to-forward beam-scanning capability and consistent gain is presented. The PLWA is made of a new type of periodically arranging meander line structures, in which the capacitive coupling between neighboring units plays the key role in achieving a high scanning rate. In detail, the beam-scanning rate of the proposed PLWA is efficiently tuned by varying the gap between two adjacent units, without considerably changing the working frequency band. To mitigate the open stopband (OSB) and to improve the impedance matching, several inductive open stubs are introduced into a single meander line unit cell to enhance the radiation. In the experiment, a prototype of the proposed PLWA was fabricated and measured. The simulated and measured beams show good agreement in terms of scanning range and radiation performance. A continuous beam scanning from -60° to +58° through broadside in the frequency band of 5.95-7.1 GHz is observed, and hence, a 102.6°/GHz scanning rate is realized in practice. Besides, the PLWA shows an average gain level of 11.96 dBi with a variation lower than 2 dB and a sidelobe below -10 dB at all the measured frequencies. The proposed PLWA may have potential applications in radar, microwave imaging, and wireless communication due to its compact structure, easy to fabricate, and dispersionless performance.
Ju, M, Ding, C, Guo, CA, Ren, W & Tao, D 2021, 'IDRLP: Image Dehazing Using Region Line Prior', IEEE Transactions on Image Processing, vol. 30, no. 99, pp. 9043-9057.
View/Download from: Publisher's site
View description>>
In this work, a novel and ultra-robust single image dehazing method called IDRLP is proposed. It is observed that when an image is divided into n regions, with each region having a similar scene depth, the brightness of both the hazy image and its haze-free correspondence are positively related with the scene depth. Based on this observation, this work determines that the hazy input and its haze-free correspondence exhibit a quasi-linear relationship after performing this region segmentation, which is named as region line prior (RLP). By combining RLP and the atmospheric scattering model (ASM), a recovery formula (RF) can be easily obtained with only two unknown parameters, i.e., the slope of the linear function and the atmospheric light. A 2D joint optimization function considering two constraints is then designed to seek the solution of RF. Unlike other comparable works, this 'joint optimization' strategy makes efficient use of the information across the entire image, leading to more accurate results with ultra-high robustness. Finally, a guided filter is introduced in RF to eliminate the adverse interference caused by the region segmentation. The proposed RLP and IDRLP are evaluated from various perspectives and compared with related state-of-the-art techniques. Extensive analysis verifies the superiority of IDRLP over state-of-the-art image dehazing techniques in terms of both the recovery quality and efficiency. A software release is available at https://sites.google.com/site/renwenqi888/.
Ju, M, Ding, C, Ren, W, Yang, Y, Zhang, D & Guo, YJ 2021, 'IDE: Image Dehazing and Exposure Using an Enhanced Atmospheric Scattering Model', IEEE Transactions on Image Processing, vol. 30, pp. 2180-2192.
View/Download from: Publisher's site
View description>>
Atmospheric scattering model (ASM) is one of the most widely used model to describe the imaging processing of hazy images. However, we found that ASM has an intrinsic limitation which leads to a dim effect in the recovered results. In this paper, by introducing a new parameter, i.e., light absorption coefficient, into ASM, an enhanced ASM (EASM) is attained, which can address the dim effect and better model outdoor hazy scenes. Relying on this EASM, a simple yet effective gray-world-assumption-based technique called IDE is then developed to enhance the visibility of hazy images. Experimental results show that IDE eliminates the dim effect and exhibits excellent dehazing performance. It is worth mentioning that IDE does not require any training process or extra information related to scene depth, which makes it very fast and robust. Moreover, the global stretch strategy used in IDE can effectively avoid some undesirable effects in recovery results, e.g., over-enhancement, over-saturation, and mist residue, etc. Comparison between the proposed IDE and other state-of-the-art techniques reveals the superiority of IDE in terms of both dehazing quality and efficiency over all the comparable techniques.
Keshavarz, R, Lipman, J, Schreurs, DMM-P & Shariati, N 2021, 'Highly Sensitive Differential Microwave Sensor for Soil Moisture Measurement', IEEE Sensors Journal, vol. 21, no. 24, pp. 27458-27464.
View/Download from: Publisher's site
View description>>
This paper presents a highly sensitive differential soil moisture sensor (DSMS) using a microstrip line loaded with triangular two-turn resonator (T2-SR) and complementary of the rectangular two-turn spiral resonator (CR2-SR), simultaneously. Volumetric Water Content (VWC) or permittivity sensing is conducted by loading the T2-SR side with dielectric samples. Two transmission notches are observed for identical loads relating to T2-SR and CR2-SR. The CR2-SR notch at 4.39 GHz is used as a reference for differential permittivity measurement method. Further, the resonance frequency of T2-SR is measured relative to the reference value. Based on this frequency difference, the permittivity of soil is calculated which is related to the soil VWC. Triangular two-turn resonator (T2-SR) resonance frequency changes from 4 to 2.38 GHz when VWC varies 0% to 30%. The sensor's operation principle is described through circuit model analysis and simulations. To validate the differential sensing concept, prototype of the designed 3-cell DSMS is fabricated and measured. The proposed sensor exhibits frequency shift of 110 MHz for 1% change at the highest soil moisture content (30%) for sandy-type soil. This work proves the differential microwave sensing concept for precision agriculture.
Khan, AA, Abolhasan, M, Ni, W, Lipman, J & Jamalipour, A 2021, 'An End-to-End (E2E) Network Slicing Framework for 5G Vehicular Ad-Hoc Networks', IEEE Transactions on Vehicular Technology, vol. 70, no. 7, pp. 7103-7112.
View/Download from: Publisher's site
View description>>
Network slicing is emerging as a promising solution for end-to-end resource management and orchestration together with Software Defined Networking (SDN) and Network Function Virtualization (NFV) technologies. In this paper, a comprehensive network slicing framework is presented to achieve end-to-end (E2E) QoS provisioning among customized services in 5G-driven VANETs. The proposed scheme manages the cooperation of both RAN and Core Network (CN), using SDN, NFV and Edge Computing technologies. Furthermore, a dynamic radio resource slice optimization scheme is formulated mathematically, that handles a mixture of mission-critical and best effort traffic, by delivering the QoS provisioning of Ultra-reliability and low latency. The proposed scheme adjusts the optimal bandwidth slicing and dynamically adapts to instantaneous network load conditions in a way that a targeted performance is guaranteed. The problem is solved using a Genetic Algorithm (GA) and results are compared with the previously proposed 5 G VANET architecture. Simulation reveal that the proposed slicing framework is able to optimize resources and deliver on the key performance metrics for mission critical communication.
Khan, HU, Niazi, M, El-Attar, M, Ikram, N, Khan, SU & Gill, AQ 2021, 'Empirical Investigation of Critical Requirements Engineering Practices for Global Software Development.', IEEE Access, vol. 9, pp. 93593-93613.
View/Download from: Publisher's site
View description>>
There is a need to identify requirements engineering (RE) practices that are important to global software development (GSD) project success. The objective of this paper is to report our recent empirical study results which aimed to identify the RE practices that are important to GSD projects. This study used an online survey questionnaire to elicit data from 56 RE experts of GSD projects. The survey included 66 RE practices identified by Sommerville et al. for non-GSD projects. The participants were asked to rank each RE practice on a four-point scale to determine the degree of importance of each practice in the context of GSD projects. This research identified a set of six key RE practices that mainly focuses on GSD project stakeholders, scope, standards and requirements traceability management. One common theme that is evident from the RE experts' feedback analysis is the standardization of requirements documents to reduce requirements inconsistencies and improve communication in diverse and distributed GSD project environments Our results show that not all 66 RE best practices are important for GSD projects. We believe that a good understanding of the identified RE practices is vital in developing and implementing the situation-specific RE processes for GSD projects.
Kieu, BT, Unanue, IJ, Pham, SB, Phan, HX & Piccardi, M 2021, 'NeuSub: A Neural Submodular Approach for Citation Recommendation', IEEE Access, vol. 9, pp. 148459-148468.
View/Download from: Publisher's site
Kumar, A, Esmaili, N & Piccardi, M 2021, 'Topic-Document Inference With the Gumbel-Softmax Distribution', IEEE Access, vol. 9, pp. 1313-1320.
View/Download from: Publisher's site
View description>>
© 2013 IEEE. Topic modeling is an important application of natural language processing (NLP) that can automatically identify the set of main topics of a given, typically large, collection of documents. In addition to identifying the main topics in the given collection, topic modeling infers which combination of topics is addressed by each individual document (the so-called topic-document inference), which can be useful for their classification and organization. However, the distributional assumptions for this inference are typically restricted to the Dirichlet family which can limit the performance of the model. For this reason, in this paper we propose modeling the topic-document inference with the Gumbel-Softmax distribution, a distribution recently introduced to expand differentiability in deep networks. To set up a performing system, the proposed approach integrates Gumbel-Softmax topic-document inference in a state-of-the-art topic model based on a deep variational autoencoder. Experimental results over two probing datasets show that the proposed approach has been able to outperform the original deep variational autoencoder and other popular topic models in terms of test-set perplexity and two topic coherence measures.
Kusakunniran, W, Charoenpanich, P, Samunyanoraset, P, Suksai, S, Karnjanapreechakorn, S, Wu, Q & Zhang, J 2021, 'Hybrid Learning of Vessel Segmentation in Retinal Images', ECTI Transactions on Computer and Information Technology (ECTI-CIT), vol. 15, no. 1, pp. 1-11.
View/Download from: Publisher's site
View description>>
This paper aims to develop a technique of vessel segmentation in retinal images. Interpreting the segmented vessels is necessary for the automatic detection of the severe stage of the diabetic retinopathy. Thus, it is important to have the technique for segmenting vessels in an automatic way with high performance, for the sake of further analysis. In this paper, the proposed method is developed based on the double layer combining supervised and non-supervised learning aspects. The first layer is to detect the initial seeds of vessels using the supervised learning. It learns based on three types of features including green intensity, line operators, and Gabor filters. Then, the support vector machine (SVM) is applied as the classification tool. In the second layer, the segmentation results from the first layer is further revised and completed using the non-supervised learning. The morphological operations with the watershed technique are applied on the results obtained from the first layer, to remain with the segmented pixels with high confidential to be vessels. Then, these pixels are used as the initial seeds of foreground in the iterative graph cut. As the result, the more completed and comprehensive foreground (i.e. vessels) can be obtained. The proposed method is evaluated using two well-known datasets including DRIVE and STARE. The experimental results show the promising performance of the proposed method when compared with other existing methods in the literature.
Le, AT, Huang, X & Guo, YJ 2021, 'Analog Self-Interference Cancellation in Dual-Polarization Full-Duplex MIMO Systems', IEEE Communications Letters, vol. 25, no. 9, pp. 3075-3079.
View/Download from: Publisher's site
View description>>
Full-duplex (FD) technology combined with dual-polarization (DP) multiple-input multiple-output (MIMO) systems is attractive to improve spectral efficiency and to enhance link capacity. Cancelling self-interference (SI) in such DPFD MIMO systems using beamforming techniques is very challenging due to a significant difference of the co-polarization and cross-polarization SI channels. In this letter, an analog adaptive filter structure is proposed to mitigate both co-polarization and cross-polarization SIs in DPFD MIMO systems. Stationary analysis is applied to evaluate the performance of the proposed structure. Simulation results show that about 45 dB to 55 dB of SI cancellation can be achieved regardless of the isolation differences between cross-polarization and co-polarization channels.
Le, AT, Tran, LC, Huang, X, Guo, YJ & Hanzo, L 2021, 'Analog Least Mean Square Adaptive Filtering for Self-Interference Cancellation in Full Duplex Radios', IEEE Wireless Communications, vol. 28, no. 1, pp. 12-18.
View/Download from: Publisher's site
Le, NP, Tran, LC, Huang, X, Choi, J, Dutkiewicz, E, Phung, SL & Bouzerdoum, A 2021, 'Performance Analysis of Uplink NOMA Systems With Hardware Impairments and Delay Constraints Over Composite Fading Channels', IEEE Transactions on Vehicular Technology, vol. 70, no. 7, pp. 6881-6897.
View/Download from: Publisher's site
View description>>
In this paper, we propose a mixture gamma distribution based analytical framework for NOMA wireless systems over composite fading channels. We analyze the outage probability (OP), delay-limited throughput (TP) and effective capacity (EC) in uplink NOMA with imperfect successive interference cancellation (SIC) due to the presence of residual hardware impairments and delay constraints. A mixture gamma distribution is used to approximate the probability density functions of fading channels. Based on this, we obtain closed-form expressions in terms of Meijer-G functions for the OP, the TP and the EC. We also perform asymptotic analysis of these metrics to characterize system behaviors at the high signal-to-noise ratio regime. Moreover, upper-bounds for the EC is derived. Efficacy of NOMA over orthogonal multiple access is analytically examined. Unlike the existing works, our analytical expressions hold for NOMA systems with an arbitrary number of users per cluster over a wide range of channel models, including lognormal-Nakagami-m, KG, η-μ, Nakagami-q (Hoyt), κ-μ, Nakagami-n (Rician), Nakagami-m, and Rayleigh fading channels. This unified analysis facilitates evaluations of impacts of the residual interference, the power allocation among users, the delay quality-of-service exponent as well as the shadowing and small-scale fading parameters on the performance metrics. Simulation results are provided to validate theoretical analysis.
Le, NP, Tran, LC, Huang, X, Dutkiewicz, E, Ritz, C, Phung, SL, Bouzerdoum, A, Franklin, DR & Hanzo, L 2021, 'Energy-Harvesting Aided Unmanned Aerial Vehicles for Reliable Ground User Localization and Communications Under Lognormal-Nakagami-$m$ Fading Channels.', IEEE Trans. Veh. Technol., vol. 70, no. 2, pp. 1632-1647.
View/Download from: Publisher's site
Lei, H, Chen, S, Wang, M, He, X, Jia, W & Li, S 2021, 'A New Algorithm for Sketch‐Based Fashion Image Retrieval Based on Cross‐Domain Transformation', Wireless Communications and Mobile Computing, vol. 2021, no. 1, pp. 1-14.
View/Download from: Publisher's site
View description>>
Due to the rise of e‐commerce platforms, online shopping has become a trend. However, the current mainstream retrieval methods are still limited to using text or exemplar images as input. For huge commodity databases, it remains a long‐standing unsolved problem for users to find the interested products quickly. Different from the traditional text‐based and exemplar‐based image retrieval techniques, sketch‐based image retrieval (SBIR) provides a more intuitive and natural way for users to specify their search need. Due to the large cross‐domain discrepancy between the free‐hand sketch and fashion images, retrieving fashion images by sketches is a significantly challenging task. In this work, we propose a new algorithm for sketch‐based fashion image retrieval based on cross‐domain transformation. In our approach, the sketch and photo are first transformed into the same domain. Then, the sketch domain similarity and the photo domain similarity are calculated, respectively, and fused to improve the retrieval accuracy of fashion images. Moreover, the existing fashion image datasets mostly contain photos only and rarely contain the sketch‐photo pairs. Thus, we contribute a fine‐grained sketch‐based fashion image retrieval dataset, which includes 36,074 sketch‐photo pairs. Specifically, when retrieving on our Fashion Image dataset, the accuracy of our model ranks the correct match at the top‐1 which is 96.6%, 92.1%, 91.0%, and 90.5% for clothes, pants, skirts, and shoes, respectively. Extensive experiments conducted on our dataset and two fine‐grained instance‐level datasets, i.e., QMUL‐shoes and QMUL‐chairs, show that our model has achieved a better performance than other existing methods.
Li, C, Xie, H-B, Fan, X, Xu, RYD, Van Huffel, S & Mengersen, K 2021, 'Kernelized Sparse Bayesian Matrix Factorization', IEEE Transactions on Neural Networks and Learning Systems, vol. 32, no. 1, pp. 391-404.
View/Download from: Publisher's site
View description>>
Extracting low-rank and/or sparse structures using matrix factorization techniques has been extensively studied in the machine learning community. Kernelized matrix factorization (KMF) is a powerful tool to incorporate side information into the low-rank approximation model, which has been applied to solve the problems of data mining, recommender systems, image restoration, and machine vision. However, most existing KMF models rely on specifying the rows and columns of the data matrix through a Gaussian process prior and have to tune manually the rank. There are also computational issues of existing models based on regularization or the Markov chain Monte Carlo. In this article, we develop a hierarchical kernelized sparse Bayesian matrix factorization (KSBMF) model to integrate side information. The KSBMF automatically infers the parameters and latent variables including the reduced rank using the variational Bayesian inference. In addition, the model simultaneously achieves low-rankness through sparse Bayesian learning and columnwise sparsity through an enforced constraint on latent factor matrices. We further connect the KSBMF with the nonlocal image processing framework to develop two algorithms for image denoising and inpainting. Experimental results demonstrate that KSBMF outperforms the state-of-the-art approaches for these image-restoration tasks under various levels of corruption.
Li, F, Zheng, J, Zhang, Y-F, Liu, N & Jia, W 2021, 'AMDFNet: Adaptive multi-level deformable fusion network for RGB-D saliency detection', Neurocomputing, vol. 465, pp. 141-156.
View/Download from: Publisher's site
View description>>
Effective exploration of useful contextual information in multi-modal images is an essential task in salient object detection. Nevertheless, the existing methods based on the early-fusion or the late-fusion schemes cannot address this problem as they are unable to effectively resolve the distribution gap and information loss. In this paper, we propose an adaptive multi-level deformable fusion network (AMDFNet) to exploit the cross-modality information. We use a cross-modality deformable convolution module to dynamically adjust the boundaries of salient objects by exploring the extra input from another modality. This enables incorporating the existing features and propagating more contexts so as to strengthen the model's ability to perceiving scenes. To accurately refine the predicted maps, a multi-scaled feature refinement module is proposed to enhance the intermediate features with multi-level prediction in the decoder part. Furthermore, we introduce a selective cross-modality attention module in the fusion process to exploit the attention mechanism. This module captures dense long-range cross-modality dependencies from a multi-modal hierarchical feature's perspective. This strategy enables the network to select more informative details and suppress the contamination caused by the negative depth maps. Experimental results on eight benchmark datasets demonstrate the effectiveness of the components in our proposed model, as well as the overall saliency model.
Li, M, Liu, Y & Guo, YJ 2021, 'Design of Sum and Difference Patterns by Optimizing Element Rotations and Positions for Linear Dipole Array', IEEE Transactions on Antennas and Propagation, vol. 69, no. 5, pp. 3027-3032.
View/Download from: Publisher's site
View description>>
IEEE This communication presents a novel method of synthesizing both sum and difference patterns by optimizing the element rotations and positions for linear dipole array. The common element rotations and positions are optimized by using the particle swarm optimization (PSO) method to produce sum and difference patterns with reduced sidelobe levels (SLLs) and cross-polarization levels (XPLs), and as steep slope as possible for the difference pattern at the target direction. Such method leads to a sum-and-difference array with sparsely distributed uniform amplitude elements, thus saving many antenna elements and unequal power dividers. Three examples for synthesizing sparse rotated dipole arrays with sum and difference patterns are provided. Synthesis results show that the obtained arrays with uniform amplitudes can produce satisfactory sum and difference patterns while saving about 34.69% ~ 42.27% of the antenna elements when compared with λ/2-spaced arrays occupying the same aperture.
Li, M, Yang, Y, Iacopi, F, Yamada, M & Nulman, J 2021, 'Compact Multilayer Bandpass Filter Using Low-Temperature Additively Manufacturing Solution', IEEE Transactions on Electron Devices, vol. 68, no. 7, pp. 3163-3169.
View/Download from: Publisher's site
View description>>
This article presented an additively manufactured bandpass filter (BPF) based on a second-order stub-loaded resonator consisting of multimetal layer components. The proposed BPF is fabricated by a low-temperature (140°) additively manufactured electronics (AME) solution that can fabricate conductive and dielectric materials simultaneously with multimetal-layer and flexible interlayer distance. By reducing the interlayer distance, constant inductance and capacitance can be realized in smaller sizes, which helps to achieve device minimization. Taking advantage of this inkjet printing technology, a second-order multimetal layer resonator is proposed. To understand the principle of the BPF, an equivalent circuit with odd- and even-mode analysis is demonstrated. For verification, the frequency response of the circuit's mathematical model is calculated to compare with the electromagnetic simulation results. Good agreement can be achieved among the calculated, simulated, and measured results. The proposed BPF is designed at 12.25 GHz with a bandwidth of 40.8% and a compact size of 2.7 mm \times1.425 mm \times0.585 mm or 0.186\lambda {g} \times 0.098\lambda {g}\times 0.040\lambda {g} , which is suitable for circuit-in-package applications in television programs, radar detection, and satellite communications.
Li, S, Liao, S, Yang, Y, Che, W & Xue, Q 2021, 'Low-Profile Circularly Polarized Isoflux Beam Antenna Array Based on Annular Aperture Elements for CubeSat Earth Coverage Applications', IEEE Transactions on Antennas and Propagation, vol. 69, no. 9, pp. 5489-5502.
View/Download from: Publisher's site
View description>>
This article presents an antenna array to produce a circularly polarized (CP) isoflux beam for CubeSat earth coverage applications. Distinguished from conventional arrays formed by identical elements, the proposed one is based on sequential rotation-fed concentric annular aperture elements. By adjusting the excitation phase, magnitude, and polarization of each annular aperture element, the radiation patterns of the array can be shaped to form isoflux beams. Radiation pattern modeling method is developed to obtain array radiation parameters. Besides, to effectively characterize the impedance matching of the radiators of the array with multiple excitations, an overall reflection coefficient is deduced from signal decomposition. A prototype operating at C -band (5 GHz) is designed, fabricated, and measured. It consists of a radiator and a feeding network. The radiator is formed by two annular aperture elements, of which the inner one is realized by a circular patch antenna while the outer one is formed by eight planar inverted-F antennas (PIFAs). The feeding network drives annular aperture elements in the manner of sequential rotation. In this way, a CP isoflux beam array with a low profile ( 0.078~{\lambda }_{0}) , lightweight, and ease-of-integration for CubeSat is realized. The proposed array can also be extended to realize other shaped beams.
Li, X, He, Y, Zhang, JA & Jing, X 2021, 'Supervised Domain Adaptation for Few-Shot Radar-Based Human Activity Recognition', IEEE Sensors Journal, vol. 21, no. 22, pp. 25880-25890.
View/Download from: Publisher's site
View description>>
With the application of deep learning (DL) techniques, radar-based human activity recognition (HAR) attracts increasing attention thanks to its high accuracy and good privacy. However, training a DL model requires a large volume of data, and generally the trained model cannot be adapted to a new scenario. In this paper, we propose a supervised few-shot adversarial domain adaptation (FS-ADA) method for HAR, where only limited radar training data is collected from a new application scenario. We adopt the domain adaptation method to learn a common feature space between a pre-existing radar dataset and the newly acquired training data. We also design a multi-class discriminator network, which integrates the category classifier and the binary domain discriminator, to employ the supervised label information in the limited radar data for model training. Then, a multitask generative adversarial training mechanism is proposed to optimize FS-ADA. In this way, both domain-invariant and category-discriminative features can be extracted for HAR in a new scenario. Experimental results for two few-shot radar-based HAR tasks show that the proposed FS-ADA method is effective and outperforms state-of-the-art methods.
Lian, J-W, Ban, Y-L & Guo, YJ 2021, 'Wideband Dual-Layer Huygens’ Metasurface for High-Gain Multibeam Array Antennas', IEEE Transactions on Antennas and Propagation, vol. 69, no. 11, pp. 7521-7531.
View/Download from: Publisher's site
View description>>
A wideband dual-layer Huygens’ unit cell based on offset electric dipole pair (OEDP) is proposed. Different from traditional designs with a combination of electric and magnetic polarizabilities, the proposed Huygens’ unit cell employs electric polarizabilities exclusively. By doing so, it practically avoids the unbalanced resonant frequencies between two polarizabilities, thereby achieving wideband transmission. Based on the proposed unit cell, a wideband and high-gain multibeam array antenna is developed. Firstly, a Rotman lens is designed by using a substrate integrated waveguide (SIW) technology. Then a parallel-fed slot antenna array is connected to the Rotman lens to generate multiple beams. Without using a series-fed slot antenna array, the multibeam array antenna based on Rotman lens can operate within a relatively wide bandwidth (28 GHz to 32 GHz). Secondly, a wideband dual-layer Huygens’ metasurface is developed that serves as a superstrate of the multibeam array antenna for increasing the antenna gain further. A wideband and high-gain multibeam array antenna is finally realized, which is comprised of a Rotman lens, a parallel-fed slot antenna array, and a Huygens’ metasurface. To verify the performance of this design, a prototype is fabricated and its measured results are compared to the simulated counterparts.
Lin, J-Y, Yang, Y, Wong, S-W & Li, Y 2021, 'High-Order Modes Analysis and Its Applications to Dual-Band Dual-Polarized Filtering Cavity Slot Arrays', IEEE Transactions on Microwave Theory and Techniques, vol. 69, no. 6, pp. 3084-3092.
View/Download from: Publisher's site
View description>>
In this article, a series of filtering cavity slot arrays using high-order modes are investigated. It is found that each unit of the cavity slot arrays in the proposed high-order mode resonator is in phase with the same amplitude, which helps enhance the antenna gain and reduce the sidelobe level. Meanwhile, the filtering function is integrated into the design for frequency selectivity and harmonic mode suppression. The higher order response can be achieved by cascading more high-order mode resonators with required external quality factor (Qₑ) and coupling coefficient (K). The fractional bandwidth (FBW) and out-of-band suppression of proposed designs are also discussed. For proof-of-concept, a single-band third-order 4 x 5 filtering cavity slot array using a TM₄₅₀ mode resonator and a dual-band dual-polarized third-order 4 x 3 filtering cavity slot array, using TM₄₃₀ and TM₃₄₀ mode resonators, are fabricated and tested. The good agreement between the simulated and measured results verifies that the proposed design methodology is feasible for designing high-order mode filtering cavity slot array antennas.
Lin, S, Liao, S, Yang, Y, Che, W & Xue, Q 2021, 'Gain Enhancement of Low-Profile Omnidirectional Antenna Using Annular Magnetic Dipole Directors', IEEE Antennas and Wireless Propagation Letters, vol. 20, no. 1, pp. 8-12.
View/Download from: Publisher's site
View description>>
An annular array antenna is proposed in this letter. The proposed low-profile antenna produces an enhanced gain with omnidirectional vertically polarized radiation patterns. Center-fed via-shorted circular patch antenna with omnidirectional radiation pattern can be low profile and wide bandwidth but suffers from tilted beam leading to a low gain in the azimuth plane. To improve the azimuth gain, instead of the traditional way of increasing the profile, a low-profile omnidirectional director is exploited, which is basically a passive magnetic dipole consisting of an annular side-coupling open-cavity. Several directors cooperating with the driven element form the proposed antenna, whose working principle is similar to the Yagi-Uda antenna. A prototype with a low profile of 0.11 λ0 is designed and fabricated. Measured results show that the prototype can realize -10-dB impedance bandwidth of 13% (4.72-5.42 GHz) and gain of 3.72 dBi at 5.34 GHz with good omnidirectivity. Compared with that of the driven element only, the omnidirectional azimuth gain is significantly improved within the bandwidth, with the maximum gain being enhanced from -4.2 to 3.72 dBi at 5.34 GHz. The proposed antenna is designed for a portable 5G sub-6 GHz wireless channel measurement application.
Lin, Z, Lv, T, Ni, W, Zhang, JA & Liu, RP 2021, 'Nested Hybrid Cylindrical Array Design and DoA Estimation for Massive IoT Networks', IEEE Journal on Selected Areas in Communications, vol. 39, no. 4, pp. 919-933.
View/Download from: Publisher's site
View description>>
IEEE Reducing cost and power consumption while maintaining high network access capability is a key physical-layer requirement of massive Internet of Things (mIoT) networks. Deploying a hybrid array is a cost-and energy-efficient way to meet the requirement, but would penalize system degree of freedom (DoF) and channel estimation accuracy. This is because signals from multiple antennas are combined by a radio frequency (RF) network of the hybrid array. This paper presents a novel hybrid uniform circular cylindrical array (UCyA) for mIoT networks. We design a nested hybrid beamforming structure based on sparse array techniques and propose the corresponding channel estimation method based on the second-order channel statistics. As a result, only a small number of RF chains are required to preserve the DoF of the UCyA. We also propose a new tensor-based two-dimensional (2-D) direction-of-arrival (DoA) estimation algorithm tailored for the proposed hybrid array. The algorithm suppresses the noise components in all tensor modes and operates on the signal data model directly, hence improving estimation accuracy with an affordable computational complexity. Corroborated by a Cramér-Rao lower bound (CRLB) analysis, simulation results show that the proposed hybrid UCyA array and the DoA estimation algorithm can accurately estimate the 2-D DoAs of a large number of IoT devices.
Lin, Z, Lv, T, Ni, W, Zhang, JA, Zeng, J & Liu, RP 2021, 'Joint Estimation of Multipath Angles and Delays for Millimeter-Wave Cylindrical Arrays With Hybrid Front-Ends', IEEE Transactions on Wireless Communications, vol. 20, no. 7, pp. 4631-4645.
View/Download from: Publisher's site
View description>>
Accurate channel parameter estimation is challenging for wideband millimeter-wave (mmWave) large-scale hybrid arrays, due to beam squint and much fewer radio frequency (RF) chains than antennas. This article presents a novel joint angle and delay estimation (JADE) approach for wideband mmWave fully-connected hybrid uniform cylindrical arrays. We first design a new hybrid beamformer to reduce the dimension of received signals on the horizontal plane by exploiting the convergence of the Bessel function, and to reduce the active beams in the vertical direction through preselection. The important recurrence relationship of the received signals needed for subspace-based angle and delay estimation is preserved, even with substantially fewer RF chains than antennas. Then, linear interpolation is generalized to reconstruct the received signals of the hybrid beamformer, so that the signals can be coherently combined across the whole band to suppress the beam squint. As a result, efficient subspace-based algorithm algorithms can be developed to estimate the angles and delays of multipath components. The estimated delays and angles are further matched and correctly associated with different paths in the presence of non-negligible noises, by putting forth perturbation operations. Simulations show that the proposed approach can approach the Cramér-Rao lower bound (CRLB) of the estimation with a significantly lower computational complexity than existing techniques.
Liu, D, Wu, Q, Huang, Y, Huang, X & An, P 2021, 'Learning from EPI-Volume-Stack for Light Field image angular super-resolution', Signal Processing: Image Communication, vol. 97, pp. 116353-116353.
View/Download from: Publisher's site
View description>>
Light Field (LF) image angular super-resolution aims to synthesize a high angular resolution LF image from a low angular resolution one, and is drawing increased attention because of its wide applications. In order to reconstruct a high angular resolution LF image, many learning based LF image angular super-resolution methods have been proposed. However, most existing methods are based on LF Epipolar Plane Image or Epipolar Plane Image volume representation, which underuse the LF image structure. The LF view spatial correlation and neighboring LF views angular correlations which can reflect LF image structure are not fully explored, which reduces LF angular super-resolution quality. In order to alleviate this problem, this paper introduces an Epipolar Plane Image Volume Stack (EPI-VS) representation for LF angular super-resolution. The EPI-VS is constituted by arranging all LF views in a raster order, which benefits in exploring LF view spatial correlation and neighboring LF views angular correlations. Based on such representation, we further propose an LF angular super-resolution network. 3D convolutions are applied in the whole super-resolution network to better accommodate the input EPI-VS data and allow information propagation between two spatial and one directional dimensions of EPI-VS data. Extensive experiments on synthetic and real-world LF scenes demonstrate the effectiveness of the proposed network. Moreover, we also illustrate the superiority of our network by applying it in scene depth estimation task.
Liu, H, Zhu, X, Wang, Y, Men, K & Yeo, KS 2021, 'A 60 GHz 8-Way Combined Power Amplifier in 0.18 μm SiGe BiCMOS', IEEE Transactions on Circuits and Systems II: Express Briefs, vol. 68, no. 6, pp. 1847-1851.
View/Download from: Publisher's site
View description>>
IEEE A 60 GHz fully-integrated 8-way combined power amplifier (PA) is developed in a standard 0.18 μm SiGe BiCMOS technology. The 8-way power splitter and combiner are co-optimized with transformer based baluns inside the eight differential PA cells, and hence resulting in minimum loss and high gain, linearity and efficiency. The measurement shows that the PA can achieve a gain of 22.2 dB around 60 GHz and 3-dB bandwidth from 53.5 GHz to 66.5 GHz, which covers all the channels specified in IEEE 802.11ad standard. It also attains a 1-dB power compression point (P1dB) of 21.8 dBm and saturated output power (PSAT) of 22.6 dBm, with power-added-efficiency of 10.7% and 12%, respectively.
Liu, L, Jiang, J, Jia, W, Amirgholipour, S, Wang, Y, Zeibots, M & He, X 2021, 'DENet: A Universal Network for Counting Crowd With Varying Densities and Scales', IEEE Transactions on Multimedia, vol. 23, no. 99, pp. 1060-1068.
View/Download from: Publisher's site
Liu, P, Li, Y, Cheng, W, Gao, X & Huang, X 2021, 'Intelligent Reflecting Surface Aided NOMA for Millimeter-Wave Massive MIMO With Lens Antenna Array', IEEE Transactions on Vehicular Technology, vol. 70, no. 5, pp. 4419-4434.
View/Download from: Publisher's site
Liu, Y, Bai, J, Zheng, J, Liao, H, Ren, Y & Guo, YJ 2021, 'Efficient Shaped Pattern Synthesis for Time Modulated Antenna Arrays Including Mutual Coupling by Differential Evolution Integrated With FFT via Least-Square Active Element Pattern Expansion', IEEE Transactions on Antennas and Propagation, vol. 69, no. 7, pp. 4223-4228.
View/Download from: Publisher's site
View description>>
IEEE The fast Fourier transform (FFT) via the least-square active element pattern expansion (LSAEPE) is generalized to speed up the computation of array patterns including mutual coupling and platform effect for time-modulated antenna arrays (TMAAs) at the central and sideband frequencies. By integrating the LSAEPE-FFT with differential evolution algorithm (DEA), the resulting DEA-LSAEPE-FFT method can realize efficient shaped pattern synthesis with accurate control of mainlobe shape, sidelobe level (SLL) and sideband level (SBL). Two examples of synthesizing different shaped patterns for different TMAAs mounted on a nonuniform platform or with metal scatters are conducted to validate the effectiveness and robustness of the proposed method. Synthesis results show that the proposed method has much better accuracy performance than the conventional DEA-FFT while costing much less CPU time than that of using DEA combined with direct summation.
Liu, Y, Yang, Y, Wu, P, Ma, X, Li, M, Xu, K-D & Guo, YJ 2021, 'Synthesis of Multibeam Sparse Circular-Arc Antenna Arrays Employing Refined Extended Alternating Convex Optimization', IEEE Transactions on Antennas and Propagation, vol. 69, no. 1, pp. 566-571.
View/Download from: Publisher's site
View description>>
IEEE A refined extended alternating convex optimization (REACO) method is presented to synthesize multibeam sparse circular-arc antenna arrays with minimum element spacing control by considering real antenna array structure characteristics. This method consists of initial step and a few refining steps. At the initial step, an initial array with dense elements distributed on a circular-arc is considered, and its array manifold vector is described by rotating a simulated isolated element pattern (IEP) without considering element mutual coupling. The collective excitation coefficient vector (CECV) and its energy bound are introduced for each element, and consequently the common element positions for generating desired multibeam patterns can be found by minimizing the number of active CECVs under multiple constraints. This minimization problem is further formulated as performing a sequence of alternating convex optimization (ACO) in which the CECV and an auxiliary weighting vector are alternately chosen as the optimization variables, so that the mimimum element spacing constraint can be easily dealt with. Once the initial optimization step is finished, a few refining steps are performed in which the element positions and excitations are successively updated in each step by renewing the array manifold vector through rotating the simulated nearby active element patterns (AEPs) of the antenna array obtained at the previous step. In such a way, the mutual coupling can be incorporated into the multibeam sparse array synthesis. An example of synthesizing a sparse circular-arc conformal array with 23 beams covering the space from–63.25° to 63.25° is conducted to validate the effectiveness and advantage of the proposed method.
Lotfi, I, Niyato, D, Sun, S, Dinh, HT, Li, Y & Kim, DI 2021, 'Protecting Multi-Function Wireless Systems From Jammers With Backscatter Assistance: An Intelligent Strategy', IEEE Transactions on Vehicular Technology, vol. 70, no. 11, pp. 11812-11826.
View/Download from: Publisher's site
View description>>
In this paper, we present a novel unified framework to protect multi-function wireless systems from jamming attacks. Examples of such multi-function system include joint radar and communication (JRC) systems and simultaneous wireless information and power transfer (SWIPT) systems. By abstracting the system functionalities as a joint optimization problem of multiple queues, we achieve effective resistance against jammers for the multi-functions simultaneously.We incorporate different antijamming techniques into one framework. Deception mechanism is adopted to lure the jammer to attack and make its actions more predictable, and ambient backscatter technology is used to leverage the jamming signals. Since conventional Markov decision process (MDP) has only one decision epoch at every time slot, it cannot be used to model the deception strategy which needs two decision epochs to leverage the jamming signals. We therefore formulate the problem using an advanced two-step MDP. After that, a deep reinforcement learning algorithm with a prioritized double deep Q-Learning architecture is proposed to learn optimal strategies in different system states. We show that by jointly considering the multi-functions of the system with potential jamming attacks during design phase, significant improvement can be achieved for both of the system functionalities.
Luo, H, Wang, P, Chen, H & Xu, M 2021, 'Object Detection Method Based on Shallow Feature Fusion and Semantic Information Enhancement', IEEE Sensors Journal, vol. 21, no. 19, pp. 21839-21851.
View/Download from: Publisher's site
Luong, NC, Lu, X, Hoang, DT, Niyato, D & Kim, DI 2021, 'Radio Resource Management in Joint Radar and Communication: A Comprehensive Survey', IEEE Communications Surveys & Tutorials, vol. 23, no. 2, pp. 780-814.
View/Download from: Publisher's site
View description>>
Joint radar and communication (JRC) has recently attracted substantial attention. The first reason is that JRC allows individual radar and communication systems to share spectrum bands and thus improves the spectrum utilization. The second reason is that JRC enables a single hardware platform, e.g., an autonomous vehicle or a UAV, to simultaneously perform the communication function and the radar function. As a result, JRC is able to improve the efficiency of resources, i.e., spectrum and energy, reduce the system size, and minimize the system cost. However, there are several challenges to be solved for the JRC design. In particular, sharing the spectrum imposes the interference caused by the systems, and sharing the hardware platform and energy resource complicates the design of the JRC transmitter and compromises the performance of each function. To address the challenges, several resource management approaches have been recently proposed, and this paper presents a comprehensive literature review on resource management for JRC. First, we give fundamental concepts of JRC, important performance metrics used in JRC systems, and applications of the JRC systems. Then, we review and analyze resource management approaches, i.e., spectrum sharing, power allocation, and interference management, for JRC. In addition, we present security issues to JRC and provide a discussion of countermeasures to the security issues. Finally, we highlight important challenges in the JRC design and discuss future research directions related to JRC.
Lyu, B, Ramezani, P, Hoang, DT, Gong, S, Yang, Z & Jamalipour, A 2021, 'Optimized Energy and Information Relaying in Self-Sustainable IRS-Empowered WPCN', IEEE Transactions on Communications, vol. 69, no. 1, pp. 619-633.
View/Download from: Publisher's site
View description>>
This paper proposes a hybrid-relaying scheme empowered by a self-sustainable intelligent reflecting surface (IRS) in a wireless powered communication network (WPCN), to simultaneously improve the performance of downlink energy transfer (ET) from a hybrid access point (HAP) to multiple users and uplink information transmission (IT) from users to the HAP. We propose time-switching (TS) and power-splitting (PS) schemes for the IRS, where the IRS can harvest energy from the HAP's signals by switching between energy harvesting and signal reflection in the TS scheme or adjusting its reflection amplitude in the PS scheme. For both the TS and PS schemes, we formulate the sum-rate maximization problems by jointly optimizing the IRS's phase shifts for both ET and IT and network resource allocation. To address each problem's non-convexity, we propose a two-step algorithm to obtain the near-optimal solution with high accuracy. To show the structure of resource allocation, we also investigate the optimal solutions for the schemes with random phase shifts. Through numerical results, we show that our proposed schemes can achieve significant system sum-rate gain compared to the baseline scheme without IRS.
Lyu, X, Ren, C, Ni, W, Tian, H, Cui, Q & Liu, RP 2021, 'Online Learning of Optimal Proactive Schedule Based on Outdated Knowledge for Energy Harvesting Powered Internet-of-Things', IEEE Transactions on Wireless Communications, vol. 20, no. 2, pp. 1248-1262.
View/Download from: Publisher's site
Lyu, X, Ren, C, Ni, W, Tian, H, Liu, RP & Tao, X 2021, 'Distributed Online Learning of Cooperative Caching in Edge Cloud', IEEE Transactions on Mobile Computing, vol. 20, no. 8, pp. 2550-2562.
View/Download from: Publisher's site
Ma, Y, Wu, N, Zhang, JA, Li, B & Hanzo, L 2021, 'Parametric Bilinear Iterative Generalized Approximate Message Passing Reception of FTN Multi-Carrier Signaling', IEEE Transactions on Communications, vol. 69, no. 12, pp. 8443-8458.
View/Download from: Publisher's site
View description>>
A low-complexity parametric bilinear generalized approximate message passing (PBiGAMP)-based receiver is conceived for multi-carrier faster-than-Nyquist (MFTN) signaling over frequency-selective fading channels. To mitigate the inherent ill-conditioning problem of MFTN signaling, we construct a segment-based frequency-domain received signal model in the form of a block circulant linear transition matrix, which can be efficiently calculated by applying a two dimensional fast Fourier transform. Based on the eigenvalue decomposition of the block circulant matrices, we can diagonalize the covariance matrix of the complex-valued colored noise process imposed by the associated two dimensional non-orthogonal matched filtering. Building on this model, a PBiGAMP-based parametric joint channel estimation and equalization (JCEE) algorithm is proposed for MFTN systems. In this algorithm, we introduce a pair of additive terms for characterizing the interferences arising from adjacent segments and employ the exact discrete a priori probabilities of the transmitted symbols for improving the bit error rate (BER) performance. To further enhance the system's robustness in the presence of ill-conditioned matrices, we develop a refined PBiGAMP-based JCEE algorithm by introducing a series of scaled identity matrices. Moreover, the proposed PBiGAMP-based JCEE algorithms may be readily decomposed into GAMP-based equalization algorithms, when the channel state information is perfectly known. The overall complexity of the proposed algorithms only increases logarithmically with the total number of transmitted symbols. Our simulation results demonstrate the benefits of the proposed PBiGAMP-based iterative message passing receiver conceived for MFTN signaling.
Masouros, C, Heath, R, Zhang, JA, Feng, Z, Zheng, L & Petropulu, A 2021, 'Editorial: Introduction to the Issue on Joint Communication and Radar Sensing for Emerging Applications', IEEE Journal of Selected Topics in Signal Processing, vol. 15, no. 6, pp. 1290-1294.
View/Download from: Publisher's site
Nahar, K, Gill, AQ & Roach, T 2021, 'Developing an access control management metamodel for secure digital enterprise architecture modeling.', Secur. Priv., vol. 4, no. 4.
View/Download from: Publisher's site
View description>>
AbstractThere is an increasing interest in embedding the security in the design of digital enterprise architecture (EA) modeling platform to secure the digital assets. Access control management (ACM) is one of the key aspects of a secure digital enterprise architecture modeling platform design. Typical enterprise architecture modeling approaches mainly focus on the modeling of business, information, and technology elements. This draws our attention to this important question: how to model ACM for a secure digital EA modeling platform to ensure secure access to digital assets? This article aims to address this important research question in collaboration with our industry partner and developed an ontology‐based ACM metamodel that can be used by enterprises to model their ACM for a particular situation. This research has been conducted using the well‐known action‐design research (ADR) method to develop and evaluate the ACM metamodel for the secure digital EA modeling platform.
Nan, Y, Huang, X, Gao, X & Guo, YJ 2021, '3-D Terahertz Imaging Based on Piecewise Constant Doppler Algorithm and Step- Frequency Continuous-Wave Signaling', IEEE Transactions on Geoscience and Remote Sensing, vol. 59, no. 8, pp. 6771-6783.
View/Download from: Publisher's site
Nguyen, C, Nguyen, D, Dinh, HT, Pham, AH, Huynh, NT, Xiao, Y & Dutkiewicz, E 2021, 'BlockRoam: Blockchain-based Roaming Management System for Future Mobile Networks', IEEE Transactions on Mobile Computing, vol. PP, no. 99, pp. 1-1.
View/Download from: Publisher's site
View description>>
Mobile service providers (MSPs) are particularly vulnerable to roaming frauds, especially ones that exploit the long delay in the data exchange process of the contemporary roaming management systems, causing multi-billion dollars loss each year. In this paper, we introduce BlockRoam, a novel blockchain-based roaming management system that provides an efficient data exchange platform among MSPs and mobile subscribers. Utilizing the Proof-of-Stake (PoS) consensus mechanism and smart contracts, BlockRoam can significantly shorten the information exchanging delay, thereby addressing the roaming fraud problems. Through intensive analysis, we show that the security and performance of such PoS-based blockchain network can be further enhanced by incentivizing more users (e.g., subscribers) to participate in the network. Moreover, users in such networks often join stake pools (e.g., formed by MSPs) to increase their profits. Therefore, we develop an economic model based on Stackelberg game to jointly maximize the profits of the network users and the stake pool, thereby encouraging user participation. We also propose an effective method to guarantee the uniqueness of this game's equilibrium. The performance evaluations show that the proposed economic model helps the MSPs to earn additional profits, attracts more investment to the blockchain network, and enhances the network's security and performance.
Nguyen, HT, Hoang, DT, Luong, NC, Niyato, D & Kim, DI 2021, 'A Hierarchical Game Model for OFDM Integrated Radar and Communication Systems', IEEE Transactions on Vehicular Technology, vol. 70, no. 5, pp. 5077-5082.
View/Download from: Publisher's site
View description>>
This paper studies the spectrum allocation problem between spectrum service providers (SSPs) and terminals equipped with orthogonal frequency division multiplexing (OFDM) integrated radar and communication (IRC) systems. In particular, IRC-equipped terminals such as autonomous vehicles need to buy spectrum for their radar functions, e.g., sensing and detecting distant vehicles, and communication functions, e.g., transmitting sensing data to road-side units. The terminals determine their spectrum demands from the SSPs subject to their IRC performance requirements, while the SSPs compete with each other on the service prices to attract terminals. Taking into account the complicated interactions, a hierarchical Stackelberg game is proposed to reconcile the spectrum demand and service price, where the SSPs are the leaders and the terminals are the followers. Due to the spectrum constraints of the SSPs, we model the lower-layer subgame among the terminals as a generalized Nash equilibrium problem. An iterative searching algorithm is then developed that guarantees the convergence to the Stackelberg equilibrium. Numerical results demonstrate the effectiveness of our proposed scheme in terms of social welfare compared to baseline schemes.
Nguyen, N-T, Nguyen, DN, Hoang, DT, Van Huynh, N, Dutkiewicz, E, Nguyen, N-H & Nguyen, Q-T 2021, 'Time Scheduling and Energy Trading for Heterogeneous Wireless-Powered and Backscattering-Based IoT Networks', IEEE Transactions on Wireless Communications, vol. 20, no. 10, pp. 6835-6851.
View/Download from: Publisher's site
View description>>
This article studies the strategic interactions between an IoT service provider (IoTSP) which consists of heterogeneous IoT devices and its energy service provider (ESP). To that end, we propose an economic framework using the Stackelberg game to maximize the network throughput and energy efficiency of both the IoTSP and ESP. To obtain the Stackelberg equilibrium (SE), we apply a backward induction technique which first derives a closed-form solution for the ESP (follower). Then, to tackle the non-convex optimization problem for the IoTSP (leader), we leverage the block coordinate descent and convex-concave procedure techniques to design two partitioning schemes (i.e., partial adjustment (PA) and joint adjustment (JA)) to find the optimal energy price and service time that constitute local SEs. Numerical results reveal that by jointly optimizing the energy trading and time allocation for IoT devices, one can achieve significant improvements in terms of the IoTSP's profit compared with those of conventional transmission methods (up to 38.7 folds). Different tradeoffs between the ESP's and IoTSP's profits and complexities of the PA/JA schemes can also be numerically tuned. Simulations also show that the obtained local SEs approach the optimal social welfare when the benefit per transmitted bit exceeds a given threshold.
Ni, Z, Zhang, JA, Huang, X, Yang, K & Yuan, J 2021, 'Uplink Sensing in Perceptive Mobile Networks With Asynchronous Transceivers', IEEE Transactions on Signal Processing, vol. 69, no. 99, pp. 1287-1300.
View/Download from: Publisher's site
Nie, X, Takalkar, MA, Duan, M, Zhang, H & Xu, M 2021, 'GEME: Dual-stream multi-task GEnder-based micro-expression recognition', Neurocomputing, vol. 427, pp. 13-28.
View/Download from: Publisher's site
View description>>
© 2020 Elsevier B.V. Recognition of micro-expressions remains a topic of concern considering its brief span and low intensity. This issue is addressed through convolutional neural networks (CNNs) by developing multi-task learning (MTL) method to effectively leverage a side task: gender detection. A dual-stream multi-task framework called GEME is introduced that recognises micro-expressions by incorporating unique gender characteristics and subsequently improves the micro-expression recognition accuracy. This research aims to examine how gender differences influence the way micro-expressions are displayed. The current study proves that selecting relevant features of micro-expressions distinctive to the gender and added to the micro-expression features improves the micro-expression recognition accuracy. This network learns gender-specific features and micro-expression features and adds them together to learn the combination of shared and task-specific representations. A multi-class focal loss is used to mitigate the class imbalance issue by down-weighing the easy samples and concentrate more on misclassified samples. The Class-Balanced (CB) focal loss is also implemented for a better class balancing during Leave-One-Subject-Out (LOSO) validations where CB loss re-balances and re-weights the loss. The experimental results on three widely used databases demonstrate the improved performance of the proposed network and achieve comparable results with the state-of-the-art methods.
Pham, Q-V, Nguyen, DC, Mirjalili, S, Hoang, DT, Nguyen, DN, Pathirana, PN & Hwang, W-J 2021, 'Swarm intelligence for next-generation networks: Recent advances and applications', Journal of Network and Computer Applications, vol. 191, pp. 103141-103141.
View/Download from: Publisher's site
Phan, KT, Huynh, P, Nguyen, DN, Ngo, DT, Hong, Y & Le-Ngoc, T 2021, 'Energy-Efficient Dual-Hop Internet of Things Communications Network With Delay-Outage Constraints', IEEE Transactions on Industrial Informatics, vol. 17, no. 7, pp. 4892-4903.
View/Download from: Publisher's site
Qureshi, S & Braun, RM 2021, 'Dynamic LightPath Allocation in WDM Networks Using an SDN Controller', IEEE Access, vol. 9, pp. 148546-148557.
View/Download from: Publisher's site
View description>>
Core wavelength division multiplexed (WDM) networks are widely used to provide fixed physical connectivity and bandwidth to the logically connected upper electronic layer devices using optical signals. However, growing demands for bandwidth-intensive applications and cloud-based services push optical networks carriers' to provide scalable and flexible services dynamically. Software defined networking (SDN) has the potential to program electronic layers by dynamically controlling and managing network resources using SDN controller applications. SDN's on-demand characteristics combined with the optical circuit-switching can enable optical network service providers to customize their service provisioning dynamically to the user's requirements. They enable fast provision of new services, and minimize underutilization of resources. In this paper, a model is proposed to bring the dynamic allocation of resources which is a layer 2+ functionality, to the WDM layer using SDN. A middle-ware application based on SDN and OpenFlow for dynamic switching and provisioning of optical service is presented. The application abstracts the optical layer's connectivity, also accounting for the switching constraints. Details of the model's implementation are discussed considering classically used equipment and its performance in terms of CPU and memory utilization, topology emulation time, and latency is evaluated. Finally, the application is tested with a Cisco layer one switch. Performance results show that the latency doubles when increasing the number of fibers of an optical cross connect from 5 to 7 and keeping wavelengths equal to 8, with Clos fabric topology.
Rahman, ML, Zhang, JA, Huang, X, Guo, YJ & Lu, Z 2021, 'Gaussian-Mixture-Model Based Clutter Suppression in Perceptive Mobile Networks', IEEE Communications Letters, vol. 25, no. 1, pp. 152-156.
View/Download from: Publisher's site
Sang, L, Xu, M, Qian, S & Wu, X 2021, 'Knowledge Graph enhanced Neural Collaborative Filtering with Residual Recurrent Network', Neurocomputing, vol. 454, pp. 417-429.
View/Download from: Publisher's site
View description>>
Knowledge Graph (KG), which commonly consists of fruitful connected facts about items, presents an unprecedented opportunity to alleviate the sparsity problem in recommender system. However, existing KG based recommendation methods mainly rely on handcrafted meta-path features or simple triple-level entity embedding, which cannot automatically capture entities’ long-term relational dependencies for the recommendation. Specially, entity embedding learning is not properly designed to combine user-item interaction information with KG context information. In this paper, a two-channel neural interaction method named Knowledge Graph enhanced Neural Collaborative Filtering with Residual Recurrent Network (KGNCF-RRN) is proposed, which leverages both long-term relational dependencies KG context and user-item interaction for recommendation. (1) For the KG context interaction channel, we propose Residual Recurrent Network (RRN) to construct context-based path embedding, which incorporates residual learning into traditional recurrent neural networks (RNNs) to efficiently encode the long-term relational dependencies of KG. The self-attention network is then applied to the path embedding to capture the polysemy of various user interaction behaviours. (2) For the user-item interaction channel, the user and item embeddings are fed into a newly designed two-dimensional interaction map. (3) Finally, above the two-channel neural interaction matrix, we employ a convolutional neural network to learn complex correlations between user and item. Extensive experimental results on three benchmark datasets show that our proposed approach outperforms existing state-of-the-art approaches for knowledge graph based recommendation.
Sang, L, Xu, M, Qian, S & Wu, X 2021, 'Knowledge graph enhanced neural collaborative recommendation', Expert Systems with Applications, vol. 164, pp. 113992-113992.
View/Download from: Publisher's site
View description>>
Existing neural collaborative filtering (NCF) recommendation methods suffer from severe sparsity problem. Knowledge Graph (KG), which commonly consists of fruitful connected facts about items, presents an unprecedented opportunity to alleviate the sparsity problem. However, pure NCF models can hardly model the high-order connectivity in KG, and ignores complex pairwise correlations between user/item embedding dimensions. To address these problems, we propose a novel Knowledge graph enhanced Neural Collaborative Recommendation (K-NCR) framework, which effectively combines user–item interaction information and auxiliary knowledge information for recommendation task into three parts: (1) For items, the proposed propagating model learns the representation of item entity. It recursively aggregates information from its multi-hop neighbours in KG, and employs an attention mechanism to discriminate the importance of the relation type to mine users’ potential preferences. (2) For users, another heterogeneous attention weights are leveraged to strengthen the embedding learning of users. (3) The user and item embeddings are then fed into a newly designed two-dimensional interaction map with convolutional hidden layers to model the complex pairwise correlations between their embedding dimensions explicitly. Extensive experimental results on three benchmark datasets demonstrate the effectiveness of our K-NCR framework.
Sang, L, Xu, M, Qian, S, Martin, M, Li, P & Wu, X 2021, 'Context-Dependent Propagating-Based Video Recommendation in Multimodal Heterogeneous Information Networks', IEEE Transactions on Multimedia, vol. 23, pp. 2019-2032.
View/Download from: Publisher's site
Seifollahi, S, Piccardi, M & Jolfaei, A 2021, 'An Embedding-Based Topic Model for Document Classification', ACM Transactions on Asian and Low-Resource Language Information Processing, vol. 20, no. 3, pp. 1-13.
View/Download from: Publisher's site
View description>>
Topic modeling is an unsupervised learning task that discovers the hidden topics in a collection of documents. In turn, the discovered topics can be used for summarizing, organizing, and understanding the documents in the collection. Most of the existing techniques for topic modeling are derivatives of the Latent Dirichlet Allocation which uses a bag-of-word assumption for the documents. However, bag-of-words models completely dismiss the relationships between the words. For this reason, this article presents a two-stage algorithm for topic modelling that leverages word embeddings and word co-occurrence. In the first stage, we determine the topic-word distributions by soft-clustering a random set of embedded n -grams from the documents. In the second stage, we determine the document-topic distributions by sampling the topics of each document from the topic-word distributions. This approach leverages the distributional properties of word embeddings instead of using the bag-of-words assumption. Experimental results on various data sets from an Australian compensation organization show the remarkable comparative effectiveness of the proposed algorithm in a task of document classification.
Shen, J, Wang, Y & Zhang, J 2021, 'ASDN: A Deep Convolutional Network for Arbitrary Scale Image Super-Resolution', Mobile Networks and Applications, vol. 26, no. 1, pp. 13-26.
View/Download from: Publisher's site
Shen, Z-H, Ni, H, Ding, C, Sui, G-R, Jia, H-Z, Gao, X-M & Wang, N 2021, 'Improving the Energy-Conversion Efficiency of a PV–TE System With an Intelligent Power-Track Switching Technique and Efficient Thermal-Management Scheme', IEEE Transactions on Components, Packaging and Manufacturing Technology, vol. 11, no. 6, pp. 963-973.
View/Download from: Publisher's site
View description>>
A photovoltaic-thermoelectric (PV-TE) hybrid system can be used for efficient thermal energy utilization from the generated waste heat in PV devices. In this article, an efficient PV-TE hybrid system with intelligent power-track switching technique and thermal management based on energy conversion is proposed. To make the output power of PV-TE system stable and normalized, an incorporated stable voltage circuit is designed based on energy conversion. In addition, a control-and-monitoring strategy is launched in the system to realize the normal collecting for the output power of PV-TE system. Finally, a battery protection circuit is performed to ensure that the energy converted by the entire system is effectively stored. The experimental results show that more electrical energy about 84 034 J was obtained with our energy harvesting system than that of a single photovoltaic (PV) cell. Besides, the thermal gradient of PV cells is indirectly reduced the operation of the whole system, which is automatically monitored due to the proposed intelligent power-track switching technique.
Sheng, Z, Tuan, HD, Nasir, AA, Poor, HV & Dutkiewicz, E 2021, 'Physical Layer Security Aided Wireless Interference Networks in the Presence of Strong Eavesdropper Channels', IEEE Transactions on Information Forensics and Security, vol. 16, pp. 3228-3240.
View/Download from: Publisher's site
View description>>
Under both long (infinite) and short (finite) blocklength transmissions, this paper considers physical layer security for a wireless interference network of multiple transmitter-user pairs, which is overheard by multiple eavesdroppers (EVs). The EVs are assumed to have better channel conditions than the legitimate users (UEs), making the conventional transmission unsecured. The paper develops a novel time-fraction based transmission, under which the information is transmitted to the UEs within a fraction of the time slot and artificial noise (AN) is transmitted within the remaining fraction to counter the strong EVs' channels. Based on channel distribution information of UEs and EVs, the joint design of transmit beamforming, time fractions and AN power allocation to maximize the worst users' secrecy rate is formulated in terms of nonconvex problems. Path-following algorithms of low complexity and rapid convergence are proposed for their solution. Simulations are provided to demonstrate the viability of the proposed methodology.
Shi, Z, Xu, M & Pan, Q 2021, '4-D Flight Trajectory Prediction With Constrained LSTM Network', IEEE Transactions on Intelligent Transportation Systems, vol. 22, no. 11, pp. 7242-7255.
View/Download from: Publisher's site
View description>>
The increasing aviation activities pose a challenge to ensure a safe and orderly flight. Trajectory prediction is one of the most important forecasting tasks in Air Traffic Management. Accurate prediction is reasonable for safe and orderly flight tasks in civil aviation monitoring. Points of interests play an important role in most land traffic prediction algorithms due to their abilities in positioning and marking. Compared with land traffic, the sparse way-points and shared airways make it difficult for flight trajectory prediction. A constrained Long Short-Term Memory network for flight trajectory prediction is proposed in this paper. According to the dynamic characteristics of the aircraft, we propose three kinds of constraints to climbing, cruising, and descending/approaching phases, in particular, they are Top of climb, Way-points, and Runway direction, correspondingly. Our model is able to keep long-term dependencies with dynamic physical constraints. Density-Based Spatial Clustering of Applications with Noise and Linear Least Squares are used in data segmentation and preprocessing. Sliding windows help maintain the continuity of trajectory. Four-dimensional spatial-temporal trajectory set consisting of spatial position and timestamps is used to prove the efficiency of our approach. Multiple ADS-B ground stations contribute to our experimental dataset. The widely used Long Short-Term Memory network, Markov Model, weighted Markov Model, Support Vector Machine, and Kalman Filter are used for comparison. Quantitative analysis demonstrates that our model outperforms the above-mentioned state-of-the-art models, and lays a good foundation for decision-making in different scenarios.
Song, L-Z, Qin, P-Y & Guo, YJ 2021, 'A High-Efficiency Conformal Transmitarray Antenna Employing Dual-Layer Ultrathin Huygens Element', IEEE Transactions on Antennas and Propagation, vol. 69, no. 2, pp. 848-858.
View/Download from: Publisher's site
Song, L-Z, Qin, P-Y, Chen, S-L & Guo, YJ 2021, 'An Elliptical Cylindrical Shaped Transmitarray for Wide-Angle Multibeam Applications', IEEE Transactions on Antennas and Propagation, vol. 69, no. 10, pp. 7023-7028.
View/Download from: Publisher's site
View description>>
A transmitarray antenna with an elliptical cylindrical shape is presented for a wide-angle multibeam radiation in this paper. The transmitarray has a cylindrical radiating aperture with an elliptical cross section, namely, elliptical cylindrical shape. Multiple feeds can be placed on the middle horizontal plane to realize multiple beams. Inspired by a two-dimensional (2-D) Ruze lens, the antenna shape and the phase compensation are jointly designed according to the desired maximal beam direction. Innovative methods including a feed refocusing analysis and a virtual focal length are utilized to achieve the phase compensation across the three-dimensional (3-D) aperture for multiple beam radiations with a small scanning loss. In order to validate the proposed antenna, a prototype operating in the millimeter-wave E band has been designed, fabricated and measured. By changing the position of the feeding gain horn along the refocusing arc, the main beam of antenna can be scanned to eleven directions. The measured peak boresight realized gain is 27 dBi at 70.5 GHz and a beam coverage of ±43° with a less than 2.7-dB scanning loss is obtained.
Song, L-Z, Qin, P-Y, Maci, S & Guo, YJ 2021, 'Ultrawideband Conformal Transmitarray Employing Connected Slot-Bowtie Elements', IEEE Transactions on Antennas and Propagation, vol. 69, no. 6, pp. 3273-3283.
View/Download from: Publisher's site
View description>>
IEEE In contrast to using multi-layer frequency selective surface (FSS) elements or tightly coupled elements, a novel technique is introduced here to achieve ultrawideband planar and conformal transmitarrays, which are based on connected elements like those used in connected arrays. In particular, the elements consist of a horizontally connected slot-bowtie and vertical meander slot-lines. The elements are capable of achieving a 360° phase variation range at the highest frequency 17 GHz with the transmission loss less than 3 dB from 6 GHz to 17 GHz. The transmitarrays have been designed, fabricated and measured in both planar and conformal versions. Stable boresight radiation patterns from 6 GHz to 17 GHz have been obtained for both antennas. Compared to conformal transmitarrays using multi-layer FSS elements, the proposed solution has a much wider bandwidth of radiation patterns. Good agreement has been found between simulation and measurement.
Srinivas, S, Gill, AQ & Roach, T 2021, 'Can Business Architecture Modeling be Adaptive?', IT Prof., vol. 23, no. 2, pp. 81-88.
View/Download from: Publisher's site
View description>>
Businesses find the need to adapt to changes in the dynamic and competitive environment. However, they are confronted by static business architecture (BA) modeling and artefacts, which are less likely to adapt and, thus, quickly become obsolete. This article proposes a dynamic analytics-enabled adaptive BA modeling framework to address this concern. This research is performed using an action design research (ADR) method in collaboration with an Australian organization. The proposed approach has been implemented and evaluated using a banking organization as a case study.
Srinivasan, M, Gopi, S, Kalyani, S, Huang, X & Hanzo, L 2021, 'Airplane-Aided Integrated Next-Generation Networking', IEEE Transactions on Vehicular Technology, vol. 70, no. 9, pp. 9345-9354.
View/Download from: Publisher's site
View description>>
A high-rate yet low-cost air-to-ground (A2G) communication backbone is conceived for integrating the space and terrestrial network by harnessing the opportunistic assistance of the passenger planes or high altitude platforms (HAPs) as mobile base stations (BSs) and millimetre wave communication. The airliners act as the network-provider for the terrestrial users while relying on satellite backhaul. Three different beamforming techniques relying on a large-scale planar array are used for transmission by the airliner/HAP for achieving a high directional gain, hence minimizing the interference among the users. Furthermore, approximate spectral efficiency (SE) and area spectral efficiency (ASE) expressions are derived and quantified for diverse system parameters.
Sun, JX, Lin, F, Zhou, XY & Zhu, X 2021, 'Design of 74% Fractional Bandwidth Continuous-Mode Doherty Power Amplifier Using Compensation Susceptance', IEEE Transactions on Circuits and Systems II: Express Briefs, vol. 68, no. 6, pp. 1827-1831.
View/Download from: Publisher's site
View description>>
IEEE This paper presents a novel design method of broadband continuous-mode Doherty power amplifier (CM-DPA) using compensation susceptance. In particular, at power back-off point, the compensation susceptance is added at the current source plane of the carrier PA to make it operates in continuous mode, which thus enhances the back-off efficiency and extends the bandwidth. Meanwhile, considering the influence of the parasitic parameters of the PA in practical design, the designed compensation susceptance at the current source plane is equivalently transformed into the compensation susceptance at the package plane of the carrier PA. Additionally, at saturation point, the load impedances at the package plane of both carrier and peaking PAs can meet the impedance conditions of drain efficiency more than 60%. Based on the proposed method, a 74 fractional bandwidth CM-DPA operating from 1.1 to 2.4 GHz is designed and measured. Under the continuous-wave excitation, the measured 6-dB back-off efficiency is 46.8%-63% and the saturation efficiency is 59.1%-78.8%. The measured small-signal gain and back-off gain are 10-12 dB and 9.1-10 dB, respectively.
Sun, Z, Yao, Y, Xiao, J, Zhang, L, Zhang, J & Tang, Z 2021, 'Exploiting textual queries for dynamically visual disambiguation', Pattern Recognition, vol. 110, pp. 107620-107620.
View/Download from: Publisher's site
View description>>
© 2020 Due to the high cost of manual annotation, learning directly from the web has attracted broad attention. One issue that limits the performance of current webly supervised models is the problem of visual polysemy. In this work, we present a novel framework that resolves visual polysemy by dynamically matching candidate text queries with retrieved images. Specifically, our proposed framework includes three major steps: we first discover and then dynamically select the text queries according to the keyword-based image search results, we employ the proposed saliency-guided deep multi-instance learning (MIL) network to remove outliers and learn classification models for visual disambiguation. Compared to existing methods, our proposed approach can figure out the right visual senses, adapt to dynamic changes in the search results, remove outliers, and jointly learn the classification models. Extensive experiments and ablation studies on CMU-Poly-30 and MIT-ISD datasets demonstrate the effectiveness of our proposed approach.
Takalkar, MA, Thuseethan, S, Rajasegarar, S, Chaczko, Z, Xu, M & Yearwood, J 2021, 'LGAttNet: Automatic micro-expression detection using dual-stream local and global attentions', Knowledge-Based Systems, vol. 212, pp. 106566-106566.
View/Download from: Publisher's site
View description>>
© 2020 Elsevier B.V. Research in the field of micro-expressions has gained significance in recent years. Many researchers have concentrated on classifying micro-expressions in different discrete emotion classes, while detecting the presence of micro-expression in the video frames is considered as a pre-requisite step in the recognition process. Hence, there is a need to introduce more advanced detection models for micro-expressions. In order to address this, we propose a dual attention network based micro-expression detection architecture called LGAttNet. LGAttNet is one of the first to utilize a dual attention network grouped with 2-dimensional convolutional neural network to perform frame-wise automatic micro-expression detection. This method divides the feature extraction and enhancement task into two different convolutional neural network modules; sparse module and feature enhancement module. One of the key modules in our approach is the attention network which extracts local and global facial features, namely local attention module and global attention module. The attention mechanism adopts the human characteristic of focusing on the specific regions of micro-movements, which enables the LGAttNet to concentrate on particular facial regions along with the full facial features to identify the micro-expressions in the frames. Experiments performed on widely used publicly available databases demonstrate the robustness and superiority of our LGAttNet when compared to state-of-the-art approaches.
Tang, J, Liu, H & Yang, Y 2021, 'Balanced Dual-Band Superconducting Filter Using Stepped-Impedance Resonators With High Band-to-Band Isolation and Wide Stopband', IEEE Transactions on Circuits and Systems II: Express Briefs, vol. 68, no. 1, pp. 131-135.
View/Download from: Publisher's site
View description>>
A balanced dual-band and wide-stopband high- temperature superconducting (HTS) bandpass filter (BPF) with deep stopband rejection is designed using modified stepped impedance resonators (SIRs) in this brief. The center frequencies of the two differential-mode (DM) passbands can be controlled by adjusting two electrical length ratios of the proposed SIR, while keeping the third spurious frequency far away for wide-stopband design. An inherent common-mode (CM) suppression can also be obtained due to the discriminating CM resonant frequencies different from the DM ones. Multiple transmission zeros (TZs) are achieved to realize high passband selectivity and enhanced DM stopband by multipath coupling and shunt stubs loaded on the I/O ports. The proposed balanced dual-band filter operating at 1.78/4.0 GHz is eventually fabricated using HTS YBCO thin films on a MgO substrate, which can significantly lower the insertion losses. The circuit was measured at the temperature of 77 K, which shows maximum insertion losses of 0.42/0.37 dB and a DM stopband of 5.0 f 1d with 40-dB attenuation, respectively.
Tang, Q, Yang, J, He, X, Jia, W, Zhang, Q & Liu, H 2021, 'Nighttime image dehazing based on Retinex and dark channel prior using Taylor series expansion', Computer Vision and Image Understanding, vol. 202, pp. 103086-103086.
View/Download from: Publisher's site
View description>>
© 2020 Elsevier Inc. Haze removal from nighttime images is more difficult compared with daytime image dehazing due to the uneven illumination, low contrast and severe color distortion. In this paper, following the approaches based on Dark channel prior, we propose a simple yet effective approach using Retinex theory and Taylor series expansion for nighttime image dehazing, referred to as ‘RDT’. Existing nighttime image dehazing methods do not handle color shift and glow removal very well. In order to address these issues, we first propose to decompose the atmospheric light image from the input image based on the Retinex theory. Taylor series expansion is then introduced for the first time to accurately estimate the pointwise transmission map. Finally, during the following processes of image fusion and color transfer, the atmospheric light image and potential haze-free image are adopted to obtain the final haze-free image. The experimental results on benchmark nighttime haze images demonstrate the superior performance of our proposed RDT dehazing method over the state-of-the-art methods.
Tang, Q, Yang, J, Liu, H, Guo, Z & Jia, W 2021, 'Single image deraining using Context Aggregation Recurrent Network', Journal of Visual Communication and Image Representation, vol. 75, pp. 103039-103039.
View/Download from: Publisher's site
View description>>
Single image deraining is a challenging problem due to the presence of non-uniform rain densities and the ill-posedness of the problem. Moreover, over-/under-deraining can directly impact the performance of vision systems. To address these issues, we propose an end-to-end Context Aggregation Recurrent Network, called CARNet, to remove rain streaks from single images. In this paper, we assume that a rainy image is the linear combination of a clean background image with rain streaks and propose to take advantage of the context information and feature reuse to learn the rain streaks. In our proposed network, we first use the dilation technique to effectively aggregate context information without sacrificing the spatial resolution, and then leverage a gated subnetwork to fuse the intermediate features from different levels. To better learn and reuse rain streaks, we integrate a LSTM module to connect different recurrences for passing the information learned from the previous stages about the rain streaks to the following stage. Finally, to further refine the coarsely derained image, we introduce a refinement module to better preserve image details. As for the loss function, the L1-norm perceptual loss and SSIM loss are adopted to reduce the gridding artifacts caused by the dilated convolution. Experiments conducted on synthetic and real rainy images show that our CARNet achieves superior deraining performance both qualitatively and quantitatively over the state-of-the-art approaches.
Tang, Y, Chen, X, Zhang, J, Wang, J, Hu, W, Liu, S, Luo, Z & Xu, H 2021, 'Generation and Characterization of Monoclonal Antibodies Against Tth DNA Polymerase and its Application to Hot-Start PCR', Protein & Peptide Letters, vol. 28, no. 10, pp. 1090-1098.
View/Download from: Publisher's site
View description>>
Background:As a heat-resistant polymerase, Thermus thermophilus (Tth) DNA polymerasecan be widely used in Polymerase Chain Reaction (PCR). However, its non-specific amplificationphenomenon is serious, which greatly limits development.Objective:In this study, we prepared Tth monoclonal antibodies against Tth DNA polymerase andresearched their application in hot-start PCR.Methods:Tth was recombinantly expressed and purified, and used as an antigen to immunize BALB/c mice to obtain monoclonal antibodies. The qualified monoclonal antibody and Tth were incubatedfor a period of time at a certain temperature to obtain the hot-start Tth. We tested the polymeraseactivity and exonuclease activity blocking the performance of hot-start Tth. Finally, thehot-start Tth was applied to one-step RT-PCR.Results:Tth with a purity of >95% was obtained, and ten monoclonal antibodies were obtained byimmunization. After incubation, three monoclonal antibodies were identified that could inhibit thepolymerase activity of Tth at low temperature. Furthermore, these three antibodies successfullyeliminated non-specific amplification in practical applications.Conclusion:Three monoclonal antibodies were successfully validated. Among them, monoclonalantibody 9 had the best overall effect. They possess the function of inhibiting at low temperatureand releasing at high temperature, which can be used as Tth polymerase inhibitors in the field ofmolecular diagnostics.
Trede, F, Braun, R & Brookes, W 2021, 'Engineering students’ expectations and perceptions of studio-based learning', European Journal of Engineering Education, vol. 46, no. 3, pp. 402-415.
View/Download from: Publisher's site
View description>>
© 2020, © 2020 SEFI. Studio-based learning is gaining currency in university engineering education programmes. It is widely argued that this practice-oriented, collaborative approach to developing professional, teamwork and interpersonal skills is needed to prepare the future workforce. In this paper, students’ expectations and perceptions of a first-year studio were explored. Data collection included baseline and follow-up interviews. Both included the rich picture method and photo-elicitation. Using critical hermeneutics interpretation, we identified three key themes: teamwork, leadership and reflection. Although studio-based learning was perceived as effortful, slow and at times even frustrating, the move away from didactic lecturing by experts to collaborative learning and building products was welcomed and endorsed by all our participants. The insight gained from this study suggests that more innovative learning and teaching approaches in engineering education may help prepare students for lifelong learning in an uncertain future world of work.
Tuan, HD, Nasir, AA, Savkin, AV, Poor, HV & Dutkiewicz, E 2021, 'MPC-Based UAV Navigation for Simultaneous Solar-Energy Harvesting and Two-Way Communications', IEEE Journal on Selected Areas in Communications, vol. 39, no. 11, pp. 3459-3474.
View/Download from: Publisher's site
View description>>
The paper is the first work that considers a constrained feedback control strategy to navigate an unmanned aerial vehicle (UAV) from a given starting point to a given terminal point while harvesting solar energy and providing a wireless communication service for ground users. Wireless communication channels are stochastic and cannot be known off-line, making the problem of off-line UAV path planning for wireless communication as considered in most existing works less meaningful. We consider the problem of navigating a solar-powered UAV from a starting point to a terminal point to harvest solar energy while serving the two-way communication between multiple pairs of ground users in a complex terrain. The objective is to jointly optimize the UAV's flight time and its flight path by trading-off between the harvested energy and power consumption subject to the ground users' minimum throughput requirement. We develop a new model predictive control (MPC) technique to address this problem. Namely, based on the well-known statistics of the air-to-ground (A2G) and ground-to-air (G2A) wireless channels, a predictive control model is proposed at each time-instant, which leads to an optimization problem over a receding horizon for the control design. This problem is non-convex due to the involvement of various optimization variables, which is then solved via novel convex iterations. Simulation results show the merits of the proposed algorithm. The results obtained by the proposed algorithm match with the benchmark non-MPC and offline-MPC approaches.
Ullah Khan, H, Kamel Alomari, M, Khan, S, Nazir, S, Qumer Gill, A, Ali Al-Maadid, A, Khalid Abu-Shawish, Z & Kamal Hassan, M 2021, 'Systematic Analysis of Safety and Security Risks in Smart Homes', Computers, Materials & Continua, vol. 68, no. 1, pp. 1409-1428.
View/Download from: Publisher's site
Van Huynh, N, Hoang, DT, Nguyen, DN & Dutkiewicz, E 2021, 'DeepFake: Deep Dueling-Based Deception Strategy to Defeat Reactive Jammers', IEEE Transactions on Wireless Communications, vol. 20, no. 10, pp. 6898-6914.
View/Download from: Publisher's site
View description>>
In this paper, we introduce DeepFake, a novel deep reinforcement learning-based deception strategy to deal with reactive jamming attacks. In particular, for a smart and reactive jamming attack, the jammer is able to sense the channel and attack the channel if it detects communications from the legitimate transmitter. To deal with such attacks, we propose an intelligent deception strategy which allows the legitimate transmitter to transmit 'fake' signals to attract the jammer. Then, if the jammer attacks the channel, the transmitter can leverage the strong jamming signals to transmit data by using ambient backscatter communication technology or harvest energy from the strong jamming signals for future use. By doing so, we can not only undermine the attack ability of the jammer, but also utilize jamming signals to improve the system performance. To effectively learn from and adapt to the dynamic and uncertainty of jamming attacks, we develop a novel deep reinforcement learning algorithm using the deep dueling neural network architecture to obtain the optimal policy with thousand times faster than those of the conventional reinforcement algorithms. Extensive simulation results reveal that our proposed DeepFake framework is superior to other anti-jamming strategies in terms of throughput, packet loss, and learning rate.
Van Huynh, N, Nguyen, DN, Hoang, DT & Dutkiewicz, E 2021, 'Optimal Beam Association for High Mobility mmWave Vehicular Networks: Lightweight Parallel Reinforcement Learning Approach', IEEE Transactions on Communications, vol. 69, no. 9, pp. 5948-5961.
View/Download from: Publisher's site
View description>>
In intelligent transportation systems (ITS), vehicles are expected to feature with advanced applications and services which demand ultra-high data rates and low-latency communications. For that, the millimeter wave (mmWave) communication has been emerging as a very promising solution. However, incorporating the mmWave into ITS is particularly challenging due to the high mobility of vehicles and the inherent sensitivity of mmWave beams to dynamic blockages. This article addresses these problems by developing an optimal beam association framework for mmWave vehicular networks under high mobility. Specifically, we use the semi-Markov decision process to capture the dynamics and uncertainty of the environment. The Q-learning algorithm is then often used to find the optimal policy. However, Q-learning is notorious for its slow-convergence. Instead of adopting deep reinforcement learning structures (like most works in the literature), we leverage the fact that there are usually multiple vehicles on the road to speed up the learning process. To that end, we develop a lightweight yet very effective parallel Q-learning algorithm to quickly obtain the optimal policy by simultaneously learning from various vehicles. Extensive simulations demonstrate that our proposed solution can increase the data rate by 47% and reduce the disconnection probability by 29% compared to other solutions.
Vu, TX, Chatzinotas, S, Nguyen, V-D, Hoang, DT, Nguyen, DN, Renzo, MD & Ottersten, B 2021, 'Machine Learning-Enabled Joint Antenna Selection and Precoding Design: From Offline Complexity to Online Performance', IEEE Transactions on Wireless Communications, vol. 20, no. 6, pp. 3710-3722.
View/Download from: Publisher's site
View description>>
We investigate the performance of multi-user multiple-antenna downlink systems in which a base station (BS) serves multiple users via a shared wireless medium. In order to fully exploit the spatial diversity while minimizing the passive energy consumed by radio frequency (RF) components, the BS is equipped with M RF chains and N antennas, where M <; N. Upon receiving pilot sequences to obtain the channel state information (CSI), the BS determines the best subset of M antennas for serving the users. We propose a joint antenna selection and precoding design (JASPD) algorithm to maximize the system sum rate subject to a transmit power constraint and quality of service (QoS) requirements. The JASPD algorithm overcomes the non-convexity of the formulated problem via a doubly iterative algorithm, in which an inner loop successively optimizes the precoding vectors, followed by an outer loop that tests all valid antenna subsets. Although approaching (near) global optimality, the JASPD suffers from a combinatorial complexity, which may limit its application in real-time network operations. To overcome this limitation, we propose a learning-based antenna selection and precoding design algorithm (L-ASPA), which employs a deep neural network (DNN) to establish underlaying relations between key system parameters and the selected antennas. The proposed L-ASPD algorithm is robust against the number of users and their locations, the transmit power of the BS, as well as the small-scale channel fading. With a well-trained learning model, it is shown that the L-ASPD algorithm significantly outperforms baseline schemes based on the block diagonalization and a learning-assisted solution for broadcasting systems and achieves a better effective sum rate than that of the JASPA under limited processing time. In addition, we observed that the proposed L-ASPD algorithm can reduce the computation complexity by 95% while retaining more than 95% of the optimal performance.
Wang, L, Yang, Y, Deng, L, Hong, W, Zhang, C & Li, S 2021, 'Vanadium dioxide embedded frequency reconfigurable metasurface for multi-dimensional multiplexing of terahertz communication', Journal of Physics D: Applied Physics, vol. 54, no. 25, pp. 255003-255003.
View/Download from: Publisher's site
View description>>
Abstract Multi-dimensional multiplexing based on the broadband metasurface is a promising candidate for the next generation terahertz (THz) communication system, which has become a research focus for data transmission rate and channel capacity enhancement. This paper proposes a THz frequency-reconfigurable metasurface hybridized with vanadium dioxide (VO2) for communication multiplexing on both dimensions of orbital angular momentum and frequency. Theoretically, 4 × n channel (n can be any positive integer) orthogonal coaxial beams carrying different data flow can be simultaneously generated based on the proposed metasurface in the tunable operating frequency band. The simulation results verify that the THz incident waves can be converted into orthogonal coaxial beams with different topological charges or frequencies, propagating perpendicular to the metasurface, when eight-channel oblique incident plane waves with varying angles or at various frequencies are reflected by the metasurface. The multi-dimensional multiplexing can be achieved in the frequency range of 0.29–0.39 THz and 0.24–0.34 THz with the VO2 switching between its fully insulating and metallic state. The proposed metasurface is expected to enable multi-band and broadband applications and has significant potential in high-speed and high-capacity THz communication.
Wang, N, Zhang, J-N, Liu, Z-Y, Ding, C, Sui, G-R, Jia, H-Z & Gao, X-M 2021, 'An Enhanced Thermoelectric Collaborative Cooling System With Thermoelectric Generator Serving as a Supplementary Power Source', IEEE Transactions on Electron Devices, vol. 68, no. 4, pp. 1847-1854.
View/Download from: Publisher's site
View description>>
Thermoelectric coolers (TECs) are widely used in state-of-the-art thermal management systems. Recently, there is a big trend to power TECs using thermoelectric generators (TEGs). Mainstream research efforts focus on attaining a higher figure of merit (ZT) of thermoelectric material, which now faces a great challenge. Alternatively, this article proposes a different approach to improve the performance of TEC, that is, integration of a TEG with a TEC. The TEG converts the collected heat energy into electric current, which reduces the power consumption and enhances the cooling capacity of the TEC. Using different methods of connecting the TEC and TEG, two thermoelectric collaborative cooling systems are proposed. Accurate SPICE models of the two cooling systems are established. The experimental results demonstrate that the discrepancy between the currents flowing through the TEC in the experiments and in the SPICE models is less than 4.8% on average. Based on the verified SPICE models, the proposed TEC-TEG collaborative cooling systems are assessed in terms of power consumption, cooling capacity, coefficient of performance, and cooling efficiency. Compared with a typical Peltier cooling system, the two collaborative cooling systems achieve significant performance improvements.
Wang, S, Lv, T, Ni, W, Beaulieu, NC & Guo, YJ 2021, 'Joint Resource Management for MC-NOMA: A Deep Reinforcement Learning Approach', IEEE Transactions on Wireless Communications, vol. 20, no. 9, pp. 5672-5688.
View/Download from: Publisher's site
View description>>
This paper presents a novel and effective deep reinforcement learning (DRL)-based approach to addressing joint resource management (JRM) in a practical multi-carrier non-orthogonal multiple access (MC-NOMA) system, where hardware sensitivity and imperfect successive interference cancellation (SIC) are considered. We first formulate the JRM problem to maximize the weighted-sum system throughput. Then, the JRM problem is decoupled into two iterative subtasks: subcarrier assignment (SA, including user grouping) and power allocation (PA). Each subtask is a sequential decision process. Invoking a deep deterministic policy gradient algorithm, our proposed DRL-based JRM (DRL-JRM) approach jointly performs the two subtasks, where the optimization objective and constraints of the subtasks are addressed by a new joint reward and internal reward mechanism. A multi-agent structure and a convolutional neural network are adopted to reduce the complexity of the PA subtask. We also tailor the neural network structure for the stability and convergence of DRL-JRM. Corroborated by extensive experiments, the proposed DRL-JRM scheme is superior to existing alternatives in terms of system throughput and resistance to interference, especially in the presence of many users and strong inter-cell interference. DRL-JRM can flexibly meet individual service requirements of users.
Wang, X, Fei, Z, Huang, J, Zhang, JA & Yuan, J 2021, 'Joint resource allocation and power control for radar interference mitigation in multi-UAV networks', Science China Information Sciences, vol. 64, no. 8.
View/Download from: Publisher's site
View description>>
Navigation problems of unmanned air vehicles (UAVs) flying in a formation have been investigated recently, where collision avoidance is a significant issue to be addressed. In this paper, we study resource allocation and power control for radar sensing in a multi- unmanned aerial vehicle (multi-UAV) formation flight system where multiple UAVs simultaneously perform radar sensing. To cope with mutual radar interference among the UAVs, we formulate a joint channel allocation and UAV transmission power control problem to maximize the minimum signal-to-interference-plus-noise ratio (SINR) of the radar echo signals. We then propose a computationally practical method to solve this NP-hard problem by decomposing it into two sub-problems, i.e., channel allocation and transmission power control. An iterative channel allocation and power control algorithm (ICAPCA) is proposed to jointly solve these two sub-problems. We also propose a reduced-complexity greedy channel allocation algorithm (GCAA), which can also be used to provide an initial solution to ICAPCA. Simulation results show that the proposed ICAPCA and GCAA can improve the minimum SINR and radar sensing performance significantly.
Wang, X, Fei, Z, Zhang, JA, Huang, J & Yuan, J 2021, 'Constrained Utility Maximization in Dual-Functional Radar-Communication Multi-UAV Networks', IEEE Transactions on Communications, vol. 69, no. 4, pp. 2660-2672.
View/Download from: Publisher's site
View description>>
IEEE In this paper, we investigate the network utility maximization problem in a dual-functional radar-communication multi-unmanned aerial vehicle (multi-UAV) network where multiple UAVs serve a group of communication users and cooperatively sense the target simultaneously. To balance the communication and sensing performance, we formulate a joint UAV location, user association, and UAV transmission power control problem to maximize the total network utility under the constraint of localization accuracy. We then propose a computationally practical method to solve this NP-hard problem by decomposing it into three sub-problems, i.e., UAV location optimization, user association and transmission power control. Three mechanisms are then introduced to solve the three sub-problems based on spectral clustering, coalition game, and successive convex approximation, respectively. The spectral clustering result provides an initial solution for user association. Based on the three mechanisms, an overall algorithm is proposed to iteratively solve the whole problem. We demonstrate that the proposed algorithm improves the minimum user data rate significantly, as well as the fairness of the network. Moreover, the proposed algorithm increases the network utility with a lower power consumption and similar localization accuracy, compared to conventional techniques.
Wang, X, Ni, W, Zha, X, Yu, G, Liu, RP, Georgalas, N & Reeves, A 2021, 'Capacity analysis of public blockchain', Computer Communications, vol. 177, pp. 112-124.
View/Download from: Publisher's site
Wang, X, Qin, P-Y & Jin, R 2021, 'Low RCS Transmitarray Employing Phase Controllable Absorptive Frequency-Selective Transmission Elements', IEEE Transactions on Antennas and Propagation, vol. 69, no. 4, pp. 2398-2403.
View/Download from: Publisher's site
Wang, Z, Xu, M, Ye, N, Xiao, F, Wang, R & Huang, H 2021, 'Computer Vision-Assisted 3D Object Localization via COTS RFID Devices and a Monocular Camera', IEEE Transactions on Mobile Computing, vol. 20, no. 3, pp. 893-908.
View/Download from: Publisher's site
View description>>
IEEE In most RFID localization systems, acquiring a reader antenna's position at each sampling time is challenging, especially for those antenna-carrying robot or drone systems with unpredictable trajectories. In this paper, we present RF-MVO that fuses RFID and computer vision for stationary RFID localization in 3D space by attaching a light-weight 2D monocular camera to two reader antennas in parallel. Firstly, the existing monocular visual odometry only recovers a camera/antenna trajectory in the camera view from 2D images. By combining it with RF phase, we design a model to estimate a scale factor for real-world trajectory transformation, along with spatial directions of an RFID tag relative to a virtual antenna array due to the mobility of each antenna. Then we propose a novel RFID localization algorithm that does not require exhaustively searching all possible positions within the pre-specified region. Secondly, to speed up the searching process and improve localization accuracy, we propose a coarse-to-fine optimization algorithm. Thirdly, we introduce the concept of horizontal dilution of precision (HDOP) to measure the confidence level of localization results. Our experiments demonstrate the effectiveness of proposed algorithms and show RF-MVO can achieve 6.23 cm localization error.
Wei, Q, Feng, D & Jia, W 2021, 'UDR: An Approximate Unbiased Difference-Ratio Edge Detector for SAR Images', IEEE Transactions on Geoscience and Remote Sensing, vol. 59, no. 8, pp. 6688-6705.
View/Download from: Publisher's site
Wong, S-W, Lin, J-Y, Yang, Y, Guo, Z-C, Zhu, L & Chu, Q-X 2021, 'Waveguide Components Based on Multiple-Mode Resonators: Advances in Microwave Multiple-Mode Waveguide Components, Including Multiplexers, Three-State Diplexers, Crossovers, and Balanced/Unbalanced Elements', IEEE Microwave Magazine, vol. 22, no. 2, pp. 33-45.
View/Download from: Publisher's site
View description>>
Waveguide components have been widely explored for several decades, due to their inherent merits of low insertion losses, high quality (Q) factors, and a significant power-handling capacity. Historically, cavity-based narrowband filters and multiplexers have been explored and designed for base stations and satellite applications. Compared with using single-mode resonators (SMRs), the implementation of multiple-mode resonators (MMRs) in waveguide structures is a promising solution to dramatically reduce the circuit volume and improve the frequency selectivity. Taking advantage of MMR techniques, various innovative waveguide structures have been proposed for a wide range of application scenarios. This article presents an overview of advances in microwave multiple-mode waveguide components, including narrow-, wide-, and multiband filters; multiplexers; three-state diplexers; crossovers; and balanced/unbalanced elements. Representative examples and their results are comprehensively discussed and summarized.
Wu, K, Zhang, JA, Huang, X & Guo, YJ 2021, 'Accurate Frequency Estimation With Fewer DFT Interpolations Based on Padé Approximation', IEEE Transactions on Vehicular Technology, vol. 70, no. 7, pp. 7267-7271.
View/Download from: Publisher's site
View description>>
Frequency estimation is a fundamental problem in many areas. The well-known A&M and its variant estimators have established an estimation framework by iteratively interpolating the discrete Fourier transform (DFT) coefficients. In general, previous estimators require two DFT interpolations per iteration, have uneven initial estimation performance against frequencies, and are incompetent for small sample numbers due to low-order approximations involved. Exploiting the iterative estimation framework of A&M, we unprecedentedly introduce the Pad Approximation to frequency estimation, unveil some features about the updating function used for refining the estimation in each iteration, and develop a simple closed-form solution to solving the residual estimation error. Extensive simulation results are provided, validating the superiority of the new estimator over the state-the-art estimators in wide ranges of key parameters.
Wu, K, Zhang, JA, Huang, X, Guo, YJ & Yuan, J 2021, 'Reliable Frequency-Hopping MIMO Radar-Based Communications With Multi-Antenna Receiver', IEEE Transactions on Communications, vol. 69, no. 8, pp. 5502-5513.
View/Download from: Publisher's site
View description>>
Frequency-hopping (FH) MIMO radar is recently introduced as an underlying system for realizing dual-function radar-communication (DFRC), increasing communication symbol rates to multiples of the radar pulse repetition frequency. As a newly conceived DFRC system, many realistic issues, such as channel estimation and synchronization, are not effectively solved yet. In this paper, we develop a multi-antenna receiver-based downlink communication scheme for the FH-MIMO DFRC, addressing the above issues in multi-path channels. By exploring the unique FH-MIMO radar waveform, we suppress both inter-antenna and inter-hop interference, and introduce minimal constraints on the radar waveform to facilitate DFRC. We then develop accurate estimation methods for timing offset and channel parameters. These methods are further employed to design reliable demodulation methods. We also derive performance bounds for the proposed estimation methods and embedded communications. Simulation results validate the efficacy of our receiving scheme, showing that the performance of estimators and data communications approaches analytical bounds.
Wu, L, Xu, M, Sang, L, Yao, T & Mei, T 2021, 'Noise Augmented Double-Stream Graph Convolutional Networks for Image Captioning', IEEE Transactions on Circuits and Systems for Video Technology, vol. 31, no. 8, pp. 3118-3127.
View/Download from: Publisher's site
Wu, S, Yan, Y, Tang, H, Qian, J, Zhang, J, Dong, Y & Jing, X-Y 2021, 'Structured discriminative tensor dictionary learning for unsupervised domain adaptation', Neurocomputing, vol. 442, pp. 281-295.
View/Download from: Publisher's site
View description>>
Unsupervised domain adaptation aims at learning a classification model robust to data distribution shift between a labeled source domain and an unlabeled target domain. Most existing approaches have overlooked the multi-dimensional nature of visual data, building classification models in vector space. Meanwhile, the issue of limited training samples is rarely considered by previous methods, yet it is ubiquitous in practical visual applications. In this paper, we develop a structured discriminative tensor dictionary learning method (SDTDL), which enables domain matching in tensor space. SDTDL produces disentangled and transferable representations by explicitly separating domain-specific factor and class-specific factor in data. Classification is achieved based on sample reconstruction fidelity and distribution alignment, which is seamlessly integrated into tensor dictionary learning. We evaluate SDTDL on cross-domain object and digit recognition tasks, paying special attention to the scenarios of limited training samples and test beyond training sample set. Experimental results show that our method outperforms existing mainstream shallow approaches and representative deep learning methods by a significant margin.
Xi, Y, Jia, W, Zheng, J, Fan, X, Xie, Y, Ren, J & He, X 2021, 'DRL-GAN: Dual-Stream Representation Learning GAN for Low-Resolution Image Classification in UAV Applications', IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 14, no. 99, pp. 1705-1716.
View/Download from: Publisher's site
View description>>
CCBY Identifying tiny objects from extremely low resolution (LR) UAV-based remote sensing images is generally considered as a very challenging task, because of very limited information in the object areas. In recent years, there have been very limited attempts to approach this problem. These attempts intend to deal with LR image classification by enhancing either the poor image quality or image representations.In this paper, we argue that the performance improvement in LR image classification is affected by the inconsistency of the information loss and learning priority on Low-Frequency (LF) components and High-Frequency (HF) components.To address this LF-HF inconsistency problem, we propose a Dual-Stream Representation Learning Generative Adversarial Network (DRL-GAN).The core idea is to produce super image representations optimal for LR recognition by simultaneously recovering the missing information in LF and HF components, respectively, under the guidance of high-resolution (HR) images.We evaluate the performance of DRL-GAN on the challenging task of LR image classification.A comparison of the experimental results on the LR benchmark, namely HRSC and CIFAR-10, and our newly collected “WIDER-SHIP” dataset demonstrates the effectiveness of our DRL-GAN, which significantly improves the classification performance, with up to 10% gain on average.
Xu, J-X, Huang, M, Li, H-Y, Yang, Y & Zhang, XY 2021, 'Design of Balanced Filtering Rat-Race Coupler Based on Quad-Mode Dielectric Resonator', IEEE Transactions on Circuits and Systems II: Express Briefs, vol. 68, no. 7, pp. 2267-2271.
View/Download from: Publisher's site
View description>>
A balanced filtering rat-race coupler is proposed based on a quad-mode dielectric resonator (DR) in this brief. Due to the electromagnetic-field distributions of the DR, the desired balanced performance with high common-mode suppression is realized without additional circuits. Moreover, by setting the feeding probes at the proper locations, the quad-mode DR is also used to obtain the desired coupler topology with filtering responses. Accordingly, a balanced filtering rat-race coupler, integrating three circuit functions of the balanced circuit, rat-race coupler, and bandpass filter, can be designed into a single-cavity configuration, resulting in a very compact size. For verification, the proposed circuit is implemented, which shows good filtering responses, low amplitude imbalance, high common-mode suppression, and excellent phase characteristics.
Yan, B, Zhao, Q, Zhang, J, Zhang, JA & Yao, X 2021, 'Multiobjective bilevel evolutionary approach for off-grid direction-of-arrival estimation', Applied Soft Computing, vol. 113, pp. 107954-107954.
View/Download from: Publisher's site
View description>>
The source number identification is an essential step in direction-of-arrival (DOA) estimation. Existing methods may provide a wrong source number due to modeling errors caused by relaxing sparse penalties, especially in impulsive noise. This paper proposes a novel idea of simultaneous source number identification and DOA estimation to address this issue. We formulate a multiobjective off-grid DOA estimation model to realize this idea, by which the source number can be automatically identified together with DOA estimation. In particular, the source number is correctly exploited by the l0 norm of impinging signals without relaxations, guaranteeing accuracy. We further design a multiobjective bilevel evolutionary algorithm to solve this model. The source number identification and sparse recovery are simultaneously optimized at the on-grid (lower) level. A forward search strategy is developed to further refine the grid at the off-grid (upper) level. This strategy does not need linear approximations and can eliminate the off-grid gap with low computational complexity. Simulation results demonstrate the outperformance of our method in terms of source number and root mean square error.
Yang, B, Xiang, L, Chen, X & Jia, W 2021, 'An Online Chronic Disease Prediction System Based on Incremental Deep Neural Network', Computers, Materials & Continua, vol. 67, no. 1, pp. 951-964.
View/Download from: Publisher's site
View description>>
Many chronic disease prediction methods have been proposed to predict or evaluate diabetes through artificial neural network. However, due to the complexity of the human body, there are still many challenges to face in that process. One of them is how to make the neural network prediction model continuously adapt and learn disease data of different patients, online. This paper presents a novel chronic disease prediction system based on an incremental deep neural network. The propensity of users suffering from chronic diseases can continuously be evaluated in an incremental manner. With time, the system can predict diabetes more and more accurately by processing the feedback information. Many diabetes prediction studies are based on a common dataset, the Pima Indians diabetes dataset, which has only eight input attributes. In order to determine the correlation between the pathological characteristics of diabetic patients and their daily living resources, we have established an in-depth cooperation with a hospital. A Chinese diabetes dataset with 575 diabetics was created. Users’ data collected by different sensors were used to train the network model. We evaluated our system using a real-world diabetes dataset to confirm its effectiveness. The experimental results show that the proposed system can not only continuously monitor the users, but also give early warning of physiological data that may indicate future diabetic ailments.
Yang, D, Zou, Y, Zhang, J & Li, G 2021, 'GID-Net: Detecting human-object interaction with global and instance dependency', Neurocomputing, vol. 444, pp. 366-377.
View/Download from: Publisher's site
View description>>
© 2020 Elsevier B.V. Since detecting and recognizing individual human or object are not adequate to understand the visual world, learning how humans interact with surrounding objects becomes a core technology. However, convolution operations are weak in depicting visual interactions between the instances since they only build blocks that process one local neighborhood at a time. To address this problem, we learn from human perception in observing HOIs to introduce a two-stage trainable reasoning mechanism, referred to as GID block. GID block breaks through the local neighborhoods and captures long-range dependency of pixels both in global-level and instance-level from the scene to help detecting interactions between instances. Furthermore, we conduct a multi-stream network called GID-Net, which is a human-object interaction detection framework consisting of a human branch, an object branch and an interaction branch. Semantic information in global-level and local-level are efficiently reasoned and aggregated in each of the branches. We have compared our proposed GID-Net with existing state-of-the-art methods on two public benchmarks, including V-COCO and HICO-DET. The results have showed that GID-Net outperforms the existing best-performing methods on both the above two benchmarks, validating its efficacy in detecting human-object interactions.
Yang, SJ, Yang, Y & Zhang, XY 2021, 'Low Scattering Element-Based Aperture-Shared Array for Multiband Base Stations', IEEE Transactions on Antennas and Propagation, vol. 69, no. 12, pp. 8315-8324.
View/Download from: Publisher's site
View description>>
This article presents a dual-wideband dual-polarized aperture-shared antenna array with low blockage effect between cross-band elements, including a low-band (LB) element with a 4 × 4 high-band (HB) antenna array underneath. The radiator of the proposed LB element consists of four slim loops with loaded periodic split-ring resonators (SRRs) for achieving low scattering property in the high band. As a result, the blockage effect of the LB element on the HB antenna array is nearly indistinct. The radiation performance, as well as the S-parameters of the HB elements in the dual-band array, is almost the same as the isolated case. For demonstration, the dual-band aperture-shared antenna array, operating in the LB of 0.69-0.96 GHz (32.7%) and the HB of 3.3-4.2 GHz (24%), is fabricated and measured. Besides, the isolated LB antenna and HB array are designed for comparison. Compared with the isolated case, the measured peak gain variation of a 1 × 4 HB array in one column is lower than 0.7 dB after adding the proposed LB element. In addition, the radiation pattern variation within 3 dB beam coverage is less than 1.5 dB. Therefore, the proposed dual-band aperture-shared array is very suitable for tackling the integration of 5G and 4G/3G/2G base station antennas.
Yang, T, Ding, C, Ziolkowski, RW & Guo, YJ 2021, 'An Epsilon-Near-Zero (ENZ) Based, Ultra-Wide Bandwidth Terahertz Single-Polarization Single-Mode Photonic Crystal Fiber', Journal of Lightwave Technology, vol. 39, no. 1, pp. 223-232.
View/Download from: Publisher's site
View description>>
© 1983-2012 IEEE. A novel terahertz (THz) photonic crystal fiber (PCF) that yields single-polarization single-mode (SPSM) propagation over an ultra-wide bandwidth is designed and analyzed. The PCF is based upon a triangle-based lattice of air holes in a high resistivity silicon substrate with three selectively-filled rectangular slots introduced into the core area. Four air holes surrounding the core region are chosen to be loaded with an epsilon-near-zero (ENZ) material. The configuration, and the large loss of the ENZ material establish a large loss difference (LD) between the two fundamental propagating polarization modes, and any higher order modes. When the central slot of the three in the core is filled with a gain material, and the adjacent two slots are air-filled, the LD values between the one desired propagating mode, and all other modes are significantly enhanced. Consequently, essentially only the desired mode will exist in the PCF after a short propagation distance resulting in the SPSM behavior. The optimized design provides large LD values, greater than 9.4 dB/cm, over a SPSM spectrum of 0.64 THz (from 1.10 to 1.74 THz), which, to the best of our knowledge, is the widest SPSM bandwidth achieved to date in the THz regime. The unwanted modes are 30 dB smaller than the wanted mode after a 3.2 cm length of the PCF. This outcome is highly desired for polarization sensitive THz communications, and sensor systems that rely on waveguiding structures.
Yang, T, Ding, C, Ziolkowski, RW & Guo, YJ 2021, 'High Sensitivity Core-Shell Structure (CSS)-Based Fiber Sensor for Monitoring Analytes in Liquids and Gases', Journal of Lightwave Technology, vol. 39, no. 10, pp. 3319-3329.
View/Download from: Publisher's site
Yao, L, Kusakunniran, W, Wu, Q & Zhang, J 2021, 'Gait recognition using a few gait frames', PeerJ Computer Science, vol. 7, pp. e382-e382.
View/Download from: Publisher's site
View description>>
Gait has been deemed as an alternative biometric in video-based surveillance applications, since it can be used to recognize individuals from a far distance without their interaction and cooperation. Recently, many gait recognition methods have been proposed, aiming at reducing the influence caused by exterior factors. However, most of these methods are developed based on sufficient input gait frames, and their recognition performance will sharply decrease if the frame number drops. In the real-world scenario, it is impossible to always obtain a sufficient number of gait frames for each subject due to many reasons, e.g., occlusion and illumination. Therefore, it is necessary to improve the gait recognition performance when the available gait frames are limited. This paper starts with three different strategies, aiming at producing more input frames and eliminating the generalization error cause by insufficient input data. Meanwhile, a two-branch network is also proposed in this paper to formulate robust gait representations from the original and new generated input gait frames. According to our experiments, under the limited gait frames being used, it was verified that the proposed method can achieve a reliable performance for gait recognition.
Yao, L, Kusakunniran, W, Wu, Q, Zhang, J, Tang, Z & Yang, W 2021, 'Robust gait recognition using hybrid descriptors based on Skeleton Gait Energy Image', Pattern Recognition Letters, vol. 150, pp. 289-296.
View/Download from: Publisher's site
View description>>
© 2019 Gait features have been widely applied in human identification. The commonly-used representations for gait recognition can be roughly classified into two categories: model-free features and model-based features. However, due to the view variances and clothes changes, model-free features are sensitive to the appearance changes. For model-based features, there is great difficulty in extracting the underlying models from gait sequences. Based on the confidence maps and the part affinity fields produced by a two-branch multi-stage CNN network, a new model-based representation, Skeleton Gait Energy Image (SGEI), has been proposed in this paper. Another contribution is that a hybrid representation has been produced, which uses SGEI to remedy the deficiency of model-free features, Gait Energy Image (GEI) for instance. The experimental performances indicate that our proposed methods are more robust to the cloth changes, and contribute to increasing the robustness of gait recognition in the unconstrained environments with view variances and clothes changes.
Yao, X, Wu, Q, Zhang, P & Bao, F 2021, 'Weighted Adaptive Image Super-Resolution Scheme Based on Local Fractal Feature and Image Roughness', IEEE Transactions on Multimedia, vol. 23, pp. 1426-1441.
View/Download from: Publisher's site
View description>>
Image super-resolution aims to reconstruct a high-resolution image from the known low-resolution version. During this process, it should keep the degree of image roughness non-decreasing, which reflects various texture features and appearance. However, this point is not well addressed in the current work. This work argues that reducing roughness during image super-resolution is the key reason causing various problems such as artificial texture and/or edge blur. In this work, keeping the image roughness non-decreasing during super-resolution is being well investigated for the first time to our best knowledge. Image super-resolution is cast as an optimization problem to keep image roughness non-decreasing. In order to tackle this problem, the image super-resolution is approached based on the theory of fractal, where adaptive fractal interpolation function is proposed. In this way, the rational fractal interpolation model is adaptive to every local region. Thus, the roughness of every image region can be best maintained while super-resolution is carried out through fractal interpolation. In this work, the image roughness is reflected by the fractal dimension, which is a key element affecting the construction of fractal interpolation model. That is, the image roughness is measurable using fractal dimension. Mathematically, the overall image super-resolution process can be converted into a fractal interpolation optimization problem where the local fractal dimension is maintained. Although adaptive super-resolution on image segments may best maintain image roughness using the proposed method, it still generates unnecessary block artifacts. To tackle this problem, this work proposes a fine-grained pixel-wise fractal function. Our extensive experimental results demonstrate that the proposed method achieves encouraging performance with the state-of-the-art super-resolution algorithms.
You, X, Wang, C-X, Huang, J, Gao, X, Zhang, Z, Wang, M, Huang, Y, Zhang, C, Jiang, Y, Wang, J, Zhu, M, Sheng, B, Wang, D, Pan, Z, Zhu, P, Yang, Y, Liu, Z, Zhang, P, Tao, X, Li, S, Chen, Z, Ma, X, I, C-L, Han, S, Li, K, Pan, C, Zheng, Z, Hanzo, L, Shen, XS, Guo, YJ, Ding, Z, Haas, H, Tong, W, Zhu, P, Yang, G, Wang, J, Larsson, EG, Ngo, HQ, Hong, W, Wang, H, Hou, D, Chen, J, Chen, Z, Hao, Z, Li, GY, Tafazolli, R, Gao, Y, Poor, HV, Fettweis, GP & Liang, Y-C 2021, 'Towards 6G wireless communication networks: vision, enabling technologies, and new paradigm shifts', Science China Information Sciences, vol. 64, no. 1, p. 110301.
View/Download from: Publisher's site
View description>>
AbstractThe fifth generation (5G) wireless communication networks are being deployed worldwide from 2020 and more capabilities are in the process of being standardized, such as mass connectivity, ultra-reliability, and guaranteed low latency. However, 5G will not meet all requirements of the future in 2030 and beyond, and sixth generation (6G) wireless communication networks are expected to provide global coverage, enhanced spectral/energy/cost efficiency, better intelligence level and security, etc. To meet these requirements, 6G networks will rely on new enabling technologies, i.e., air interface and transmission technologies and novel network architecture, such as waveform design, multiple access, channel coding schemes, multi-antenna technologies, network slicing, cell-free architecture, and cloud/fog/edge computing. Our vision on 6G is that it will have four new paradigm shifts. First, to satisfy the requirement of global coverage, 6G will not be limited to terrestrial communication networks, which will need to be complemented with non-terrestrial networks such as satellite and unmanned aerial vehicle (UAV) communication networks, thus achieving a space-air-ground-sea integrated communication network. Second, all spectra will be fully explored to further increase data rates and connection density, including the sub-6 GHz, millimeter wave (mmWave), terahertz (THz), and optical frequency bands. Third, facing the big datasets generated by the use of extremely heterogeneous networks, diverse communication scenarios, large numbers of antennas, wide bandwidths, and new service requirements, 6G networks will enable a new range of smart applications with the aid of artificial intelligence (AI) and big data technologies. Fourth, network security will have to be strengthened when developing 6G networks. This article provides a comprehensive survey of recent advances and future trends in these four aspects. Clearly, 6G with ad...
Yu, G, Zhang, L, Wang, X, Yu, K, Ni, W, Zhang, JA & Liu, RP 2021, 'A novel Dual-Blockchained structure for contract-theoretic LoRa-based information systems', Information Processing & Management, vol. 58, no. 3, pp. 102492-102492.
View/Download from: Publisher's site
View description>>
© 2021 LoRa serves as one of the most deployed technologies in Internet-of-Things-based information systems (IoT-IS), and self-motivated deployment is the key to the rollout of LoRa. Proper incentive can play an important role in encouraging the private deployment of LoRa, increasing coverage and promoting effective management of IoT-IS. However, existing incentive mechanisms have the vulnerabilities of insecure centralized architecture and excessive utility loss of LoRa Controllers and Gateways, due to asymmetric information between private owners of gateways and centralized controller (or service providers). Blockchain-based LoRa networks, as a promising solution, have not been comprehensively studied to address the vulnerabilities, let alone the other issues of security, scalability, and flexibility. In this paper, we propose a novel Dual-Chained LoRa-based information system (LoRa-IS) to provide globally cross-validated security. Behaviors, including state-of-the-art contract-theoretic incentive mechanism and new flow control protocol, can be secured with the tamper-resistance of Blockchains. Being part of the proposed incentive mechanism, the new self-driven flow control allows both the Dual-Chain system and the LoRa network to scale. To the best of our knowledge, the proposed system is the first comprehensive Blockchain-based LoRa-IS combined with contract theory. We also provide analysis and simulations, showing that our system can pay fair incentives under information asymmetry. With the new flow control, the system can optimize network coverage while improving the Blockchain scalability and flexibility.
Yu, L, Gao, Y, Zhou, J & Zhang, J 2021, 'Parameter-Efficient Deep Neural Networks With Bilinear Projections', IEEE Transactions on Neural Networks and Learning Systems, vol. 32, no. 9, pp. 4075-4085.
View/Download from: Publisher's site
View description>>
Recent research on deep neural networks (DNNs) has primarily focused on improving the model accuracy. Given a proper deep learning framework, it is generally possible to increase the depth or layer width to achieve a higher level of accuracy. However, the huge number of model parameters imposes more computational and memory usage overhead and leads to the parameter redundancy. In this article, we address the parameter redundancy problem in DNNs by replacing conventional full projections with bilinear projections (BPs). For a fully connected layer with D input nodes and D output nodes, applying BP can reduce the model space complexity from O(D²) to O(2D), achieving a deep model with a sublinear layer size. However, the structured projection has a lower freedom of degree compared with the full projection, causing the underfitting problem. Therefore, we simply scale up the mapping size by increasing the number of output channels, which can keep and even boosts the model accuracy. This makes it very parameter-efficient and handy to deploy such deep models on mobile systems with memory limitations. Experiments on four benchmark data sets show that applying the proposed BP to DNNs can achieve even higher accuracies than conventional full DNNs while significantly reducing the model size.
Yu, P, Ni, W, Yu, G, Zhang, H, Liu, RP & Wen, Q 2021, 'Efficient Anonymous Data Authentication for Vehicular Ad Hoc Networks', Security and Communication Networks, vol. 2021, pp. 1-14.
View/Download from: Publisher's site
View description>>
Vehicular ad hoc network (VANET) encounters a critical challenge of efficiently and securely authenticating massive on-road data while preserving the anonymity and traceability of vehicles. This paper designs a new anonymous authentication approach by using an attribute-based signature. Each vehicle is defined by using a set of attributes, and each message is signed with multiple attributes, enabling the anonymity of vehicles. First, a batch verification algorithm is developed to accelerate the verification processes of a massive volume of messages in large-scale VANETs. Second, replicate messages captured by different vehicles and signed under different sets of attributes can be dereplicated with the traceability of all the signers preserved. Third, the malicious vehicles forging data can be traced from their signatures and revoked from attribute groups. The security aspects of the proposed approach are also analyzed by proving the anonymity of vehicles and the unforgeability of signatures. The efficiency of the proposed approach is numerically verified, as compared to the state of the art.
Yuan, C, Tao, X, Ni, W, Li, N, Jamalipour, A & Liu, RP 2021, 'Optimal Power Allocation for Superposed Secrecy Transmission in Multicarrier Systems', IEEE Transactions on Vehicular Technology, vol. 70, no. 2, pp. 1332-1346.
View/Download from: Publisher's site
Yuan, X, Feng, Z, Zhang, JA, Ni, W, Liu, RP, Wei, Z & Xu, C 2021, 'Spatio-Temporal Power Optimization for MIMO Joint Communication and Radio Sensing Systems With Training Overhead', IEEE Transactions on Vehicular Technology, vol. 70, no. 1, pp. 514-528.
View/Download from: Publisher's site
Zeng, J, Xiao, C, Li, Z, Ni, W & Liu, RP 2021, 'Dynamic Power Allocation for Uplink NOMA With Statistical Delay QoS Guarantee', IEEE Transactions on Wireless Communications, vol. 20, no. 12, pp. 8191-8203.
View/Download from: Publisher's site
Zhang, A, Rahman, ML, Huang, X, Guo, YJ, Chen, S & Heath, RW 2021, 'Perceptive Mobile Networks: Cellular Networks With Radio Vision via Joint Communication and Radar Sensing', IEEE Vehicular Technology Magazine, vol. 16, no. 2, pp. 20-30.
View/Download from: Publisher's site
Zhang, H & Xu, M 2021, 'Graph neural networks with multiple kernel ensemble attention', Knowledge-Based Systems, vol. 229, pp. 107299-107299.
View/Download from: Publisher's site
Zhang, H & Xu, M 2021, 'Weakly Supervised Emotion Intensity Prediction for Recognition of Emotions in Images', IEEE Transactions on Multimedia, vol. 23, pp. 2033-2044.
View/Download from: Publisher's site
View description>>
Recognition of emotions in images is attracting increasing research attention. Recent studies show that using local region information helps to improve the recognition performance. Intuitively, emotion intensity maps provide more detailed information than image regions. Inspired by this intuition, we propose an end-to-end deep neural network for image emotion recognition leveraging emotion intensity learning. The proposed network is composed of a first classification stream, an intensity prediction stream and a second classification stream. The intensity prediction stream is built on top of the feature pyramid network to extract multilevel features. The class activation mapping technique is used to generate pseudo intensity maps from the first classification stream to guide the proposed network for emotion intensity learning. The predicted intensity map is integrated into the second classification stream for final emotion recognition. The three streams are trained cooperatively to improve the performance. We evaluate the proposed network for both emotion recognition and sentiment classification on different benchmark datasets. The experimental results demonstrate that the proposed network achieves improved performance compared to previous state-of-the-art approaches.
Zhang, H, Gu, Y, Yao, Y, Zhang, Z, Liu, L, Zhang, J & Shao, L 2021, 'Deep Unsupervised Self-Evolutionary Hashing for Image Retrieval', IEEE Transactions on Multimedia, vol. 23, pp. 3400-3413.
View/Download from: Publisher's site
Zhang, H, Huang, X & Zhang, JA 2021, 'Adaptive Transmission With Frequency-Domain Precoding and Linear Equalization Over Fast Fading Channels', IEEE Transactions on Wireless Communications, vol. 20, no. 11, pp. 7420-7430.
View/Download from: Publisher's site
View description>>
In this paper, the emerging orthogonal time frequency space (OTFS) modulation is firstly restructured as a precoded orthogonal frequency division multiplexing (OFDM) system, so that the well-established frequency-domain approach can be applied to perform signal in fast fading channels. Then a frequency-domain minimum mean squared error (MMSE) equalizer for OTFS is introduced and its performance is analyzed based on the eigenvalue decomposition of the channel matrix. Inspired by the frequency-domain precoding structure, an adaptive transmission scheme with frequency-domain precoding matrix composed of the eigenvectors of the channel matrix is proposed to improve the system performance under MMSE equalization, and its optimized performance is derived with simple expression. Finally, considering two extreme channel conditions, the lower and upper bounds for the diversity performance of the adaptive transmission scheme are derived. Simulation results show that the proposed adaptive transmission achieves significantly better performance for short signal frames and can work well with imperfect channel state information (CSI). The derived performance bounds can serve as benchmarks for OTFS and other precoded OFDM systems.
Zhang, J, Liu, L, Wang, P & Zhang, J 2021, 'Exploring the auxiliary learning for long-tailed visual recognition', Neurocomputing, vol. 449, pp. 303-314.
View/Download from: Publisher's site
View description>>
Real-world visual data often exhibits a long-tailed distribution, where some “head” classes have a large number of samples, yet only a few samples are available for “tail” classes. The fundamental problem of learning with the imbalanced data is that insufficient training samples easily lead to the over-fitting of feature extractor and classifier for tail classes, which can be boiled down into a dilemma: on the one hand, we prefer to increase the exposure of tail class samples to avoid the excessive dominance of head classes in the classifier training. On the other hand, oversampling tail classes makes the network prone to over-fitting, since head class samples are often consequently under-represented. To resolve this dilemma, in this paper, we propose an effective auxiliary learning approach. The key idea is to split a network into a classifier part and a feature extractor part, and then employ different training strategies for each part in an auxiliary learning manner. Specifically, to promote the awareness of tail-classes, a class-balanced sampling scheme is utilised for training both the classifier and the feature extractor as the primary task. For the feature extractor, we also introduce an auxiliary training task, which is to train a classifier under the regular random sampling scheme. In this way, the feature extractor is jointly trained from both sampling strategies and thus can take advantage of all training data and avoid the over-fitting issue. Apart from this basic auxiliary task, we further explore the benefits of different types of auxiliary tasks for improving the generality of learned features, including self-supervised learning and class-wise re-weighting. Without using any bells and whistles, our model compares favourably over state-of-the-art solutions.
Zhang, JA, Liu, F, Masouros, C, Heath, RW, Feng, Z, Zheng, L & Petropulu, A 2021, 'An Overview of Signal Processing Techniques for Joint Communication and Radar Sensing', IEEE Journal of Selected Topics in Signal Processing, vol. 15, no. 6, pp. 1295-1315.
View/Download from: Publisher's site
View description>>
Joint communication and radar sensing (JCR) represents an emerging research field aiming to integrate the above two functionalities into a single system, by sharing the majority of hardware, signal processing modules and, in a typical case, the transmitted signal. The close cooperation of the communication and sensing functions can enable significant improvement of spectrum efficiency, reduction of device size, cost and power consumption, and improvement of performance of both functions. Advanced signal processing techniques are critical for making the integration efficient, from transmission signal design to receiver processing. This paper provides a comprehensive overview of the state-of-the-art on JCR systems from the signal processing perspective. A balanced coverage on both transmitter and receiver is provided for three types of JCR systems, namely, communication-centric, radar-centric, and joint design and optimization.
Zhang, P, Wu, Q, Yao, X & Xu, J 2021, 'Beyond modality alignment: Learning part-level representation for visible-infrared person re-identification', Image and Vision Computing, vol. 108, pp. 104118-104118.
View/Download from: Publisher's site
Zhang, P, Xu, J, Wu, Q, Huang, Y & Ben, X 2021, 'Learning Spatial-Temporal Representations Over Walking Tracklet for Long-Term Person Re-Identification in the Wild', IEEE Transactions on Multimedia, vol. 23, pp. 3562-3576.
View/Download from: Publisher's site
View description>>
Long-term person re-identification (re-ID) aims to build identity correspondence of the Target Subject of Interest (TSI) exposed under surveillance cameras over a long time interval. Compared to the conventional short-term re-ID studied by most existing works, it suffers an additional problem: significant dressing change observed with time lapsing. Unfortunately, this variation in long-term person re-ID case contradicts the assumption of prior short-term re-ID approaches, and thus causes significant difficulties if conventional short-term re-ID methods are applied. To address the problem, this paper proposes to learn hybrid feature representation via a two-stream network named SpTSkM, including a spatial-temporal stream and a skeleton motion stream. The former performs directly on image sequences, which tends to learn identity-related spatial-temporal patterns such as body geometric structure and body movement. The latter operates on normalized 3D skeletons by adapting graph convolutional network, which tends to learn pure motion patterns from skeleton sequences. Both streams extract fine-grained level time-gap stable information that is robust to appearance changes in long-term re-ID and meanwhile maintains sufficient discriminability to differentiate different people. The final matching metric is obtained by mixing information of the two streams in a score-level fusion strategy. In addition, we collect a Cloth-Varying vIDeo re-ID (CVID-reID) dataset particularly for long-term re-ID. It contains video tracklets of celebrities posted on the Internet. These videos are snapshots under extremely different scenarios that include highly dynamic background, diverse camera views and abundant cloth variations on each TSI. These factors cause CVID-reID more complicated and closer to practice. Our experiments demonstrate the difficulty of long-term person re-ID and also validate the effectiveness of the proposed SpTSkM, showing the best performance.
Zhang, Q, Ge, L, Zhang, R, Metternicht, GI, Du, Z, Kuang, J & Xu, M 2021, 'Deep-learning-based burned area mapping using the synergy of Sentinel-1&2 data', Remote Sensing of Environment, vol. 264, pp. 112575-112575.
View/Download from: Publisher's site
Zhang, T, Du, J & Guo, YJ 2021, 'An 8–10-GHz Low-Loss Image-Reject HTS Mixer Based on Cascaded Josephson Junctions', IEEE Microwave and Wireless Components Letters, vol. 31, no. 8, pp. 945-948.
View/Download from: Publisher's site
View description>>
A 7.8 to 9.8 GHz low-loss high-Tc superconducting (HTS) image-reject Josephson junction mixer is presented in this paper. Image rejection is achieved using low-loss image rejection filters and a pair of parallel dual-mode resonators. Three cascaded Josephson junctions are monolithically integrated with impedance matching networks and bandpass/lowpass filters on a single chip for low loss and compactness. The implementation of series junction array increased the overall junction equivalent impedance, so that a better impedance matching is achieved. Measurement results of the novel HTS mixer showed a low conversion loss at 5.5 dB, and an image-reject ratio over 30 dB within the desired frequency. The proposed cascaded junction configuration provides a new approach for impedance matching in HTS mixer designs, and the demonstrated mixer performance makes it an ideal candidate for X-band radar systems.
Zhang, T, Yuan, J, Chen, Y-C & Jia, W 2021, 'Self-learning soft computing algorithms for prediction machines of estimating crowd density', Applied Soft Computing, vol. 105, pp. 107240-107240.
View/Download from: Publisher's site
View description>>
Human needs motivate the improvement of computing paradigms, the emergence of soft computing is more effective in dealing with daily problems, while reducing costs, it also solves the problem of robustness and becomes easier to handle. Examples of this include collecting data on video data from smart sensors and can use that information to predict and monitor the behavior of crowd. Nowadays, with the development of cyber–physical systems and artificial intelligence, the traditional data collection and analysis system faces the risks of low transparency and high data security, making it difficult to obtain an accurate prediction result. Therefore, in this paper a novel prediction machine via self-learning generative adversarial network for soft computing application is proposed, which collects data through a series of high-precision IoT sensor devices and makes preliminary preprocessing, and further solves the crowd prediction problem based on deep learning algorithms and obtains a reliable and accurate prediction result by continuously optimizing internal parameters. The focus of this work is on the accuracy and preprocessing of data collection and crowd prediction algorithms. The prediction algorithm can be used to estimate and monitor the crowd flow in public places, and can prevent crowding, trampling and other traffic jams, such as stations, airports, large exhibitions, tourist attractions and other places. Therefore, the new prediction machine includes video capture, upload and display, data analysis and early warning operations in embedded devices, and automatically predicts crowd density. In terms of constructing the network, first, in order to obtain a clearer generated density map, the feature self-learning module is merged in the generator feature extraction stage. Secondly, in order to avoid the blur of the generated image, an adversarial loss is constructed between the generator and the discriminator, and finally to deal with multiple scales...
Zhang, T, Zhang, Z, Jia, W, He, X & Yang, J 2021, 'Generating Cartoon Images from Face Photos with Cycle-Consistent Adversarial Networks', Computers, Materials & Continua, vol. 69, no. 2, pp. 2733-2747.
View/Download from: Publisher's site
View description>>
The generative adversarial network (GAN) is first proposed in 2014, and this kind of network model is machine learning systems that can learn to measure a given distribution of data, one of the most important applications is style transfer. Style transfer is a class of vision and graphics problems where the goal is to learn the mapping between an input image and an output image. CYCLE-GAN is a classic GAN model, which has a wide range of scenarios in style transfer. Considering its unsupervised learning characteristics, the mapping is easy to be learned between an input image and an output image. However, it is difficult forCYCLE-GANto converge and generate high-quality images. In order to solve this problem, spectral normalization is introduced into each convolutional kernel of the discriminator. Every convolutional kernel reaches Lipschitz stability constraint with adding spectral normalization and the value of the convolutional kernel is limited to [0, 1], which promotes the training process of the proposed model. Besides, we use pretrained model (VGG16) to control the loss of image content in the position of l1 regularization. To avoid overfitting, l1 regularization term and l2 regularization term are both used in the object loss function. In terms of Frechet Inception Distance (FID) score evaluation, our proposed model achieves outstanding performance and preserves more discriminative features. Experimental results show that the proposed model converges faster and achieves better FID scores than the state of the art.
Zhang, T, Zhao, Y, Jia, W & Chen, M-Y 2021, 'Collaborative algorithms that combine AI with IoT towards monitoring and control system', Future Generation Computer Systems, vol. 125, pp. 677-686.
View/Download from: Publisher's site
View description>>
Recently, a new IoT structure known as the Artificial Intelligence of Things (AIoT) comes into play. Crowd counting is a promising field in data analysis of AIoT, however, due to poor transparency and high data security risks, developing a novel network architecture that can precisely elevate the counting of heavy crowd is extremely difficult. In addition, the fusion of IoT and AI also poses several challenges. The focus of this work is on the effective design of IoT framework and deep learning algorithm towards security of smart city. The system can be used to estimate the crowd traffic in public places, and can prevent the occurrence of congestion, stampede and other accidents, such as stations, airports, large-scale exhibitions, tourist attractions and other places. The constructed system contains video collection, upload and display as well as data analysis and early warning operation at the embedded device end, and automatically tracks densely crowd areas by controlling the video monitoring device. Moreover, the cloud platform can be controlled through the network. Our proposed algorithms are composed of two main aspects, i.e., division and focus. Firstly, we propose a novel density-adaptive Gaussian kernel to elevate the quality of density maps. Then, we propose a module based on conditional random fields for feature fusion. Finally, we propose a block segmentation module to predict our segmentation results and extract the context-aware information in segmentation stage. Experiments on our captured data, the Shanghai Tech, UCF_CC_50 and UCF_QNRF datasets demonstrate that our solution has obtained better performance and lower count errors over the state of the art.
Zhang, Y-F, Zheng, J, Li, L, Liu, N, Jia, W, Fan, X, Xu, C & He, X 2021, 'Rethinking feature aggregation for deep RGB-D salient object detection', Neurocomputing, vol. 423, pp. 463-473.
View/Download from: Publisher's site
View description>>
© 2020 Two-stream UNet based architectures are widely used in deep RGB-D salient object detection (SOD) models. However, UNet only adopts a top-down decoder network to progressively aggregate high-level features with low-level ones. In this paper, we propose to enrich feature aggregation via holistic aggregation paths and an extra bottom-up decoder network. The former aggregates multi-level features holistically to learn abundant feature interactions while the latter aggregates improved low-level features with high-level features, thus promoting their representation ability. Aiming at the two-stream architecture, we propose another early aggregation scheme to aggregate and propagate multi-modal encoder features at each level, thereby improving the encoder capability. We also propose a factorized attention module to efficiently modulate the feature aggregation action for each feature node with multiple learned attention factors. Experimental results demonstrate that all of the proposed components can gradually improve RGB-D SOD results. Consequently, our final SOD model performs favorably against other state-of-the-art methods.
Zhang, Z, Jiang, S, Huang, C, Li, Y & Xu, RYD 2021, 'RGB-IR cross-modality person ReID based on teacher-student GAN model', Pattern Recognition Letters, vol. 150, pp. 155-161.
View/Download from: Publisher's site
Zhang, Z, Wu, Q, Wang, Y & Chen, F 2021, 'Exploring region relationships implicitly: Image captioning with visual relationship attention', Image and Vision Computing, vol. 109, pp. 104146-104146.
View/Download from: Publisher's site
View description>>
Visual attention mechanism has been widely used by image captioning model in order to dynamically attend to the related visual region based on given language information. Such capability allows a trained model to carry out fine-grained level image understanding and reasoning. However, existing visual attention models only focus on the individual visual region in the image and the alignment between the language representation and related individual visual regions. It does not fully explore the relationships/interactions between visual regions. Furthermore, it does not analyze or explore alignment for related words/phrases (e.g. verb or phrasal verb), which may best describe the relationships/interactions between these visual regions. Thus, it causes the inaccurate or impropriate description to the current image captioning model. Instead of visual region attention commonly addressed by existing visual attention mechanism, this paper proposes the novel visual relationship attention via contextualized embedding for individual regions. It can dynamically explore a related visual relationship existing between multiple regions when generating interaction words. Such relationship exploring process is constrained by spatial relationships and driven by the linguistic context of language decoder. In this work, such new visual relationship attention is designed through a parallel attention mechanism under the learned spatial constraint in order to more precisely map visual relationship information to the semantic description of such relationship in language. Different from existing methods for exploring the visual relationship, it is trained implicitly through an unsupervised approach without using any explicit visual relationship annotations. By integrating the newly proposed visual relationship attention with existing visual region attention, our image captioning model can generate high-quality captions. Solid experiments on the MSCOCO dataset demonstrate the pro...
Zhang, Z, Yang, Y, Liao, S & Xue, Q 2021, 'Omnidirectional oversized annular lens antenna with high gain for 5G millimeter‐wave channel measurement', Microwave and Optical Technology Letters, vol. 63, no. 10, pp. 2621-2627.
View/Download from: Publisher's site
View description>>
AbstractA high gain oversized annular lens antenna for 28‐GHz band channel measurement system is presented. The proposed antenna is composed of an omnidirectional feeding source and an oversized annular lens. The feeding source is a compact multi‐stepped biconical antenna with a wide impedance bandwidth. By rotating a horizontally placed two‐dimensional extended hemispherical lens around the vertical axis, the oversized annular lens is realized, which effectively increases the vertical radiation aperture and maintains high aperture efficiency to enhance the omnidirectional gain. Under the same envelope, the proposed antenna features a higher gain than the biconical antenna and the ordinary annular lens antenna. A prototype is fabricated and measured. The measured results demonstrate that the ‐10‐dB impedance bandwidth is 20.7% (24‐29.6 GHz), with stable vertically polarized (VP) omnidirectional radiation patterns and gain over 10.3 dBi within the entire band of interest.
Zheng, D, Zhang, H, Zhang, JA & Su, SW 2021, 'Stability of Switched Systems with Unstable Subsystems: A Sequence-Based Average Dwell Time Approach', Circuits, Systems, and Signal Processing, vol. 40, no. 11, pp. 5328-5350.
View/Download from: Publisher's site
View description>>
This paper proposes a new sequence-based approach to resolve the stability problems found in switched systems with unstable subsystems. In existing approaches, the sequence information of switching subsystems is seldom exploited. By exploiting the sequence information, threshold values can be less restrictive and more appropriate for the situation. We study two cases in this paper: (a) all subsystems are unstable, and (b) part of the subsystems are unstable. Both continuous-time and discrete-time systems are studied, and a numerical example is given to show the advantage of our approach.
Zhou, I, Makhdoom, I, Shariati, N, Raza, MA, Keshavarz, R, Lipman, J, Abolhasan, M & Jamalipour, A 2021, 'Internet of Things 2.0: Concepts, Applications, and Future Directions', IEEE Access, vol. 9, pp. 70961-71012.
View/Download from: Publisher's site
View description>>
Applications and technologies of the Internet of Things are in high demand with the increase of network devices. With the development of technologies such as 5G, machine learning, edge computing, and Industry 4.0, the Internet of Things has evolved. This survey article discusses the evolution of the Internet of Things and presents the vision for Internet of Things 2.0. The Internet of Things 2.0 development is discussed across seven major fields. These fields are machine learning intelligence, mission critical communication, scalability, energy harvesting-based energy sustainability, interoperability, user friendly IoT, and security. Other than these major fields, the architectural development of the Internet of Things and major types of applications are also reviewed. Finally, this article ends with the vision and current limitations of the Internet of Things in future network environments.
Zhou, W, Sutton, GJ, Liu, RP, Zhang, JA & Pan, S 2021, 'Deterministic Channel Aggregation for LTE in Unlicensed Spectrum', IEEE Communications Letters, vol. 25, no. 3, pp. 807-811.
View/Download from: Publisher's site
Zhu, H & Guo, YJ 2021, 'Dual-Band and Tri-Band Balanced-to-Single Ended Power Dividers With Wideband Common-Mode Suppression', IEEE Transactions on Circuits and Systems II: Express Briefs, vol. 68, no. 7, pp. 2332-2336.
View/Download from: Publisher's site
Zhu, J, Yang, Y, Hu, N, Liao, S & Nulman, J 2021, 'Additively Manufactured Multi-Material Ultrathin Metasurfaces for Broadband Circular Polarization Decoupled Beams and Orbital Angular Momentum Generation', ACS Applied Materials & Interfaces, vol. 13, no. 49, pp. 59460-59470.
View/Download from: Publisher's site
View description>>
Controlling the wavefront and manipulating the polarization of the electromagnetic wave using an ultrathin flat device are highly desirable in many emerging fields. To shape the wavefront between two decoupled orthogonal circular polarization states, that is, the right-hand circular polarization (RCP) and the left-hand circular polarization (LCP), most state-of-the-art metasurfaces (MSs) combine the propagation phase and Pancharatnam-Berry phase into meta-atoms. This article proposes a different strategy to fully decouple the LCP and RCP and control their wavefronts independently. By taking advantage of the conductive and dielectric multi-material-integrated additive manufacturing technique, the proposed transmissive MS has an ultrathin thickness (0.11 free-space wavelength) and controls the LCP and RCP wavefronts independently under linearly polarized incidence illumination. The proposed meta-atom consists of a receiving antenna on the top, a transmitting antenna at the bottom with a strip-line connecting them. The strip-line introduces the same phase shifts for both RCP and LCP waves, while the transmitting antenna with in-plane rotation leads to the opposite phase shifts for RCP and LCP waves. Therefore, the phase delays from the strip-line and the angular rotation of the transmitting antenna provide two degrees of freedom, enabling independent beam shaping of LCP and RCP waves. Two MSs with different functionalities are printed for proof-of-concept, and the performances are experimentally verified.
Zhu, J, Yang, Y, Li, M, Mcgloin, D, Liao, S, Nulman, J, Yamada, M & Iacopi, F 2021, 'Additively Manufactured Millimeter-Wave Dual-Band Single-Polarization Shared Aperture Fresnel Zone Plate Metalens Antenna', IEEE Transactions on Antennas and Propagation, vol. 69, no. 10, pp. 6261-6272.
View/Download from: Publisher's site
View description>>
Fresnel zone plate (FZP) lens antenna, consisting of a set of alternative transparent and opaque concentric rings arranged on curvilinear or flat surfaces, have been widely used in various fields for sensing and communications. Nevertheless, the state-of-art FZP lens antennas are limited to a single band due to the frequency-dependent feature, which hinders their use in multi-band applications. In this work, a shared-aperture dual-band FZP metalens antenna is proposed by merging two single-band FZP metalens antenna operating at distinct frequency bands seamlessly into one. Instead of using conventional metallic conductors, double-screen meta-grids are devised in this work to form the concentric rings. Because the meta-grids show distinct transmission/reflection properties at different frequencies, the performance of one set of concentric rings operating at the one band will not be affected by the other operating at the different band. In addition, to compensate for the phase shift introduced by the meta-grids, an additional dielectric ring layer is added atop the FZP taking advantage of additive manufacturing. Thus, the radiation performance of the dual-band FZP lens antenna is comparable to that of each single FZP metalens antenna. For proof-of-concept, an antenna prototype operating at the dual-band, 75 GHz and 120 GHz with a frequency ratio of 1.6, is fabricated using an integrated additively manufactured electronics (AME) technique. The measured peak gains of 20.3 dBi and 21.9 dBi are achieved at 75 GHz and 120 GHz, respectively.
Zhu, J, Yang, Y, Liao, S & Xue, Q 2021, 'Aperture-Shared Millimeter-Wave/Sub-6 GHz Dual-Band Antenna Hybridizing Fabry–Pérot Cavity and Fresnel Zone Plate', IEEE Transactions on Antennas and Propagation, vol. 69, no. 12, pp. 8170-8181.
View/Download from: Publisher's site
View description>>
This article presents an aperture-shared dual-band large frequency-ratio high gain antenna for sub-6 GHz and millimeter-wave (mm-wave) bands applications. Initially, the partially reflective surface (PRS) of the Fabry-Pérot cavity (FPC) antenna operating at the sub-6 GHz band is realized by using single-layered periodic grid patches while the opaque region of the mm-wave bandwaveband Fresnel zone plate (FZP) lens antenna is implemented by using periodic double-screen dipoles. Then, the PRS and the FZP lens are hybridized together and upgraded into a kind of composite metasurface, which simultaneously functions as the PRS of the sub-6 GHz FPC antenna and the mm-wave bandwaveband FZP lens with little dual-band mutual interference. Thus, the FPC antenna and the FZP lens can share the same aperture with high aperture reuse efficiency. Because the principles are based on the FPC resonance and the collimating FZP lens, high gains are achieved at both bands without a feeding network. Meanwhile, a dual-band large frequency-ratio antenna is designed as the feed. A prototype working at 3 and 28 GHz bands is designed, fabricated, and measured to verify the idea.
Zhu, J, Yang, Y, Mcgloin, D, Liao, S & Xue, Q 2021, '3-D Printed All-Dielectric Dual-Band Broadband Reflectarray With a Large Frequency Ratio', IEEE Transactions on Antennas and Propagation, vol. 69, no. 10, pp. 7035-7040.
View/Download from: Publisher's site
View description>>
This communication proposes a new all-dielectric broadband dual-band reflectarray with a large frequency-ratio using low-cost 3-D printing. In contrast to conventional reflectarrays using metallic resonant cells or dielectric slabs as phasing elements with full metal ground, the proposed design uses air as the phasing element and a stepped dielectric mirror structure as the ground. In this way, the metal ground is removed, which makes the design an all-dielectric one. Taking advantage of the dielectric mirror that only exhibits a bandgap in the pre-designed band while allowing electromagnetic (EM) waves to pass through it at the frequency out of the bandgap region, a dual-band reflectarray is obtained. By properly selecting the bandgap frequency of the dielectric mirror, the dual-band frequency-ratio is scalable and can be very large. Furthermore, instead of using a metallic or dielectric resonator based on resonance, air layers with linear phase response are adopted as the phasing element. Thus, the reflectarray shows broadband and stable performance over the dual-band. Compared with state-of-art works using printed-circuit-boards (PCBs) or micro-fabrication, the proposed design is low-cost and lightweight, and can be rapidly prototyped. For proof-of-concept, a prototype operating at K band and V band with a frequency-ratio of 2.7 is printed and measured.
Zhu, J, Yang, Y, McGloin, D, Liao, S & Xue, Q 2021, 'Sub-Terahertz 3-D Printed All-Dielectric Low-Cost Low-Profile Lens-Integrated Polarization Beam Splitter', IEEE Transactions on Terahertz Science and Technology, vol. 11, no. 4, pp. 433-442.
View/Download from: Publisher's site
View description>>
Polarizing beam splitters (PBSs) are essential components for polarization-multiplexed communication system. However, conventional PBS, such as Rochon prism and Wollaston prism, must be sufficiently thick to generate enough walk-off distance between two orthogonal polarizations due to the low birefringence of natural material. To reduce this requirement, we propose and demonstrate a three-dimensional printed low-cost low-profile Fresnel-Rochon prism. By adjusting the dimensions of the artificially engineered gratings that comprise the prism, the refractive index tensor along the x- and y-direction can differ, enabling the independent manipulation of the deflection angles of the orthogonal polarized components. Applying the Fresnel principle to this Rochon prism, the thickness can be greatly reduced while the polarization splitting and deflection angles remain unaltered. Meanwhile, the transmission efficiency of the prism is also improved as less energy is dissipated in the lossy printing material. In addition, in contrast to conventional Rochon prisms formed by two right triangle prisms, the proposed Rochon prism enjoys the benefit of simple fabrication without any further assembly procedure. Prototypes operating at 0.14-THz frequency were printed and measured to verify the idea.
Zhu, W, Tuan, HD, Dutkiewicz, E, Fang, Y & Hanzo, L 2021, 'A New Class of Structured Beamforming for Content-Centric Fog Radio Access Networks', IEEE Transactions on Communications, vol. 69, no. 11, pp. 7269-7282.
View/Download from: Publisher's site
View description>>
A multi-user fog radio access network (F-RAN) is designed for supporting content-centric services. The requested contents are partitioned into sub-contents, which are then 'beamformed' by the remote radio heads (RRHs) for transmission to the users. Since a large number of beamformers must be designed, this poses a computational challenge. We tackle this challenge by proposing a new class of regularized zero forcing beamforming (RZFB) for directly mitigating the inter-content interferences, while the 'intra-content interference' is mitigated by successive interference cancellation at the user end. Thus each beamformer is decided by a single real variable (for proper Gaussian signaling) or by a pair of complex variables (for improper Gaussian signaling). Hence the total number of decision variables is substantially reduced to facilitate tractable computation. To address the problem of energy efficiency optimization subject to multiple constraints, such as individual user-rate requirement and the fronthauling constraint of the links between the RRHs and the centralized baseband signal processing unit, as well as the total transmit power budget, we develop low-complexity path-following algorithms. Finally, we confirm their performance by simulations.
Zhu, X & Gomez-Garcia, R 2021, 'Exploiting Parasitic Capacitances in 3-D Inductors to Design RF CMOS Quasi-Elliptic-Type Broad-Band Bandpass Filters', IEEE Transactions on Circuits and Systems II: Express Briefs, vol. 68, no. 9, pp. 3128-3132.
View/Download from: Publisher's site
View description>>
A class of RF broad-band bandpass filter (BPF) with quasi-elliptic-type response in low-cost bulk CMOS technology is reported. It is based on the in-series cascade connection of lowpass and highpass filtering stages with 3-D inductors, whose parasitic capacitances are properly exploited. Specifically, they are used to transform the basic inductor into an LC tank, thus allowing to generate an upper transmission zero (TZ) that increases filtering selectivity and out-of-band power-rejection levels in a spurious-free/extended upper stopband. The layout of a basic third-order BPF cell shaped by four 3-D inductors and its lossless equivalent lumped-element circuit are detailed. By means of this lossless equivalent lumped-element model, its scalability to higher-order BPF designs by in-series cascading various BPF-cell replicas is also demonstrated. For experimental-validation purposes, an on-chip RF CMOS BPF prototype with 11-GHz center frequency and 68.5% 3-dB fractional bandwidth is developed using a 0.13- \mu \text{m} bulk CMOS technology. According to the measured results, it shows an upper stopband with minimum attenuation of 31.7 dB from 22.5 GHz to 67 GHz, alongside with TZs at 3.5 GHz and 22.5 GHz to produce sharp-rejection filtering.
Afroz, F & Braun, R 1970, 'QX-MAC: Improving QoS and Energy Performance of IoT-based WSNs using Q-Learning', 2021 IEEE 46th Conference on Local Computer Networks (LCN), 2021 IEEE 46th Conference on Local Computer Networks (LCN), IEEE, Edmonton, AB, Canada, pp. 455-462.
View/Download from: Publisher's site
View description>>
Low-power wireless sensor networks (WSNs) play a vital role in different IoT applications. In WSNs, MAC protocols are of paramount importance to improve energy efficiency and quality of service (QoS). This paper proposes a traffic-adaptive, energy-efficient MAC protocol, which combines the Q-Learning algorithm and the more bit scheme to provide low energy consumption together with better QoS without introducing additional overhead to the network. Simulation results show that, on average, QX-MAC offers an energy savings of 23.23% and 79.91% over the X-MAC and the B-MAC protocols respectively. QX-MAC can carry up to 92.78% of traffic, whilst X-MAC and B-MAC can transfer a maximum of 88.5%, and 67.3% traffic respectively. Furthermore, QX-MAC reduces the mean end-to-end packet delivery delay, even in the presence of high traffic loads, and improves the throughput up to 41.67% and 65.05% compared to X-MAC and B-MAC, respectively.
Alsufyani, N & Gill, AQ 1970, 'A Review of Digital Maturity Models from Adaptive Enterprise Architecture Perspective: Digital by Design.', CBI (1), IEEE Conference on Business Informatics, IEEE, Bolzano, Italy, pp. 121-130.
View/Download from: Publisher's site
View description>>
There is a growing interest among organisations to assess and improve digital capabilities. Thus, a digital maturity model can assist organisations in planning and navigating their digital transformation. The challenge is that there are several maturity models to choose from. This paper aims to review the most recent digital maturity models from an enterprise architecture design perspective to understand, tailor, and adopt the appropriate model. This paper presents a systematic review of 30 selected maturity models across 36 papers. Further, the review results were synthesised and analysed using the adaptive enterprise architecture as a theoretical lens. This review reveals that digital maturity models still lack the ability to capture a holistic picture of digital maturity from an enterprise design perspective. The results of this review can be further casted into developing digital maturity principles and metamodel.
Amiri, M, Abolhasan, M, Shariati, N & Lipman, J 1970, 'Multi-band SIW Cavity Based Metamaterial Perfect Absorber', 2021 IEEE Asia-Pacific Microwave Conference (APMC), 2021 IEEE Asia-Pacific Microwave Conference (APMC), IEEE, Brisbane, Australia, pp. 347-349.
View/Download from: Publisher's site
View description>>
Absorbing ambient electromagnetic (EM) signals is required in some applications such as energy harvesting and sensing. Metamaterial perfect absorbers (MPAs) are a promising candidate to absorb the EM signal with near-unity efficiency. However, designing a structure with multi absorption bands is still challenging among researchers due to the requiring multi-layer and multi-resonators structures. Herein, a multi-band MPA based on SIW cavity structure is introduced. Taking advantage of various resonance modes of the cavity at higher order, a low-profile, highly efficient, and easy to implement MPA is achieved. In addition, the proposed structure is completely polarization angle insensitive, which is crucial to have a highly efficient EM waves absorber.
Ansari, M, Jones, B, Shariati, N & Jay Guo, Y 1970, '3D Luneburg Lens Antenna With Layered Structure for High-Gain Communication Systems', 2021 15th European Conference on Antennas and Propagation (EuCAP), 2021 15th European Conference on Antennas and Propagation (EuCAP), IEEE, pp. 1-4.
View/Download from: Publisher's site
Bah, AO, Guo, YJ, Qin, P-Y & Bird, TS 1970, 'A Wideband Low-Profile Fabry-Perot Antenna Employing a Multi-Resonant Metasurface Based Superstrate', 2021 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting (APS/URSI), 2021 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting (APS/URSI), IEEE, pp. 1705-1706.
View/Download from: Publisher's site
Bone, D, Gay, V, Brookes, W, Trede, F & Braun, R 1970, 'Roadshow Presentations for Developing Presentation and Feedback Skills in Studio Based Learning', 2021 19th International Conference on Information Technology Based Higher Education and Training (ITHET), 2021 19th International Conference on Information Technology Based Higher Education and Training (ITHET), IEEE, Sydney, pp. 01-11.
View/Download from: Publisher's site
View description>>
Abstract—Studio Based Learning (SBL) is related to the well established Problem Based Learning (PBL) approach. At theUniversity of Technology Sydney we apply SBL in the delivery of undergraduate engineering subjects. This paper updates the description of the Studio with a focus on the steps that have been taken to adapt it to online delivery in the context of the pandemic and describes the adoption of roadshow presentations in the engineering studio subjects as a method to develop students’ presentation and feedback skills. We report on the method used and feedback received from students
Cao, F, An, P, Huang, X, Yang, C & Wu, Q 1970, 'Multi-Models Fusion for Light Field Angular Super-Resolution', ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, Toronto, ON, Canada, pp. 2365-2369.
View/Download from: Publisher's site
View description>>
Light field (LF) imaging has received increasing attention due to its richer interpretation of the scene. However, an inherent spatial-angular trade-off exists in LF that prevents LF from practical applications. Consequently, how to break such a trade-off has become one of the main challenges in sparsely sampled LF reconstruction. LF super-resolution (SR) can provide an opportunity to solve this issue, but most methods exploit only one form of LF, thereby leading to much loss of information. We believe that different LF forms can compensate each other to obtain higher gains via fusion strategy. In this paper, therefore, we propose a multi-models fusion for LF SR in angular domain. Cascading models which are trained by different LF forms can fully exploit rich LF information. Experimental results demonstrate that our method is effective and achieves a comparable result against state-of-the-art techniques.
Chaczko, Z, Chiu, C, Borowik, G & Braun, R 1970, 'Assistive IoT-centric Robotics for Senior Living', 2021 19th International Conference on Information Technology Based Higher Education and Training (ITHET), 2021 19th International Conference on Information Technology Based Higher Education and Training (ITHET), IEEE, Sydney, Australia, pp. 1-6.
View/Download from: Publisher's site
View description>>
Senior citizens consider the most significant part of aging to be the changes that occur to their bodies. For this reason, they avoid doing body exercises and therefore often prone to heart diseases, muscle disorders and many other ailments. Although weakening of bones and muscles is inevitable as we grow old, we can still maintain our health by doing regular physical exercise. Encouraging elderly people to do physical exercise can be challenging, therefore the Robot-Trainer is introduced to make their exercising journey exciting accompanied by a friendly humanoid robot. The main goal of the system is to program an IoT-Assistive Robot to interact and conduct physical exercise training sessions with elderly people and maintain their physical fitness and mental health.
Chen, L, Chen, L, Ge, Z, Gomez-Garcia, R & Zhu, X 1970, 'Design of Passive-Inspired Millimetre-Wave Integrated Devices in Low-Cost Bulk CMOS Technology', 2021 IEEE Asia-Pacific Microwave Conference (APMC), 2021 IEEE Asia-Pacific Microwave Conference (APMC), IEEE, Brisbane, Australia, pp. 97-99.
View/Download from: Publisher's site
View description>>
This work presents unique circuit design techniques for on-chip passive devices implemented in low-cost bulk CMOS technology. As the full potential of active devices for silicon-based millimetre-wave circuit design has been pushed almost to the limit, it is important to find an alternative way to further improve the performance of circuits/systems operating at millimetre-wave frequency regions. This is known as passive-inspired design methodology. Two devices, namely a reflection-less bandstop filter (BSF) and a single-pole doublethrow (SPDT) switch, are used as examples to demonstrate the proposed novel design methodologies.
Chu, L, Shi, J & Braun, R 1970, 'Monte Carlo based stochastic finite element model for uncertainty quantification in flip chip BGA electronic packaging', 2021 22nd International Conference on Electronic Packaging Technology (ICEPT), 2021 22nd International Conference on Electronic Packaging Technology (ICEPT), IEEE, Xiamen, China, pp. 1-4.
View/Download from: Publisher's site
View description>>
The Ball grid array (BGA) electronic packaging method is an efficient and appropriate way for high density integrated circuits. The uncertainties in the material and geometrical parameters to product reliability and safety under the real operating situation are the crucial issues deserved more attention. In this paper, the Monte Carlo based stochastic finite element model (MC-SFEM) is proposed for uncertainty quantification in flip chip BGA electronic packaging. The Monte Carlo stochastic sampling process is combined with the finite element computation for the resonant frequencies response of the flip chip BGA electronic packaging. The uncertainties in material and geometrical parameters of flip chip BGA electronic packaging are performed and propagated by advanced Monte Carlo method (Latin Hypercube sampling method). Four different BGA configurations are compared and discussed. The proposed model and the computational results in this paper provide meaningful references to the electronic package reliability prediction.
Chu, NH, Hoang, DT, Nguyen, DN, Huynh, NV & Dutkiewicz, E 1970, 'Fast or Slow: An Autonomous Speed Control Approach for UAV-assisted IoT Data Collection Networks', 2021 IEEE Wireless Communications and Networking Conference (WCNC), 2021 IEEE Wireless Communications and Networking Conference (WCNC), IEEE, China, pp. 1-6.
View/Download from: Publisher's site
View description>>
Unmanned Aerial Vehicles (UAVs) have been emerging as an effective solution for IoT data collection networks thanks to their outstanding flexibility, mobility, and low operation costs. However, due to the limited energy and uncertainty from the data collection process, speed control is one of the most important factors while optimizing the energy usage efficiency and performance for UAV collectors. This work aims to develop a novel autonomous speed control approach to address this issue. To that end, we first formulate the dynamic speed control task of a UAV as a Markov decision process taking into account its energy status and location. In this way, the Q-learning algorithm can be adopted to obtain the optimal speed control policy for the UAV. To further improve the system performance, we develop a highly-effective deep dueling double Q-learning algorithm utilizing outstanding features of the deep neural networks as well as advanced dueling architecture to quickly stabilize the learning process and obtain the optimal policy. Through simulations, we show that our proposed solution can achieve up to 40% greater performance, i.e., an average throughput of the system, compared with other conventional methods. Importantly, the simulation results also reveal significant impacts of UAV’s energy and charging time on the system performance.
Cotton, D & Chaczko, Z 1970, 'GymD2D: A Device-to-Device Underlay Cellular Offload Evaluation Platform', 2021 IEEE Wireless Communications and Networking Conference (WCNC), 2021 IEEE Wireless Communications and Networking Conference (WCNC), IEEE, pp. 1-7.
View/Download from: Publisher's site
Deng, Y, Zou, Y, Gong, S, Lyu, B, Hoang, DT & Niyato, D 1970, 'Robust Beamforming for IRS-assisted Wireless Communications under Channel Uncertainty', 2021 IEEE Wireless Communications and Networking Conference (WCNC), 2021 IEEE Wireless Communications and Networking Conference (WCNC), IEEE, Nanjing, PEOPLES R CHINA, pp. 1-6.
View/Download from: Publisher's site
Dinh, TQ, Nguyen, DN, Hoang, DT, Vu, PT & Dutkiewicz, E 1970, 'Enabling Large-Scale Federated Learning over Wireless Edge Networks', 2021 IEEE Global Communications Conference (GLOBECOM), GLOBECOM 2021 - 2021 IEEE Global Communications Conference, IEEE, Spain, pp. 01-06.
View/Download from: Publisher's site
Gao, X, Du, J, Zhang, T, Zhang, H, Huang, X & Guo, YJ 1970, 'Terahertz Communication Demonstration by using a High-Tc Superconducting Josephson Receiver Integrated with a Miniature Cryocooler', 2021 IEEE MTT-S International Microwave Workshop Series on Advanced Materials and Processes for RF and THz Applications (IMWS-AMP), 2021 IEEE MTT-S International Microwave Workshop Series on Advanced Materials and Processes for RF and THz Applications (IMWS-AMP), IEEE, pp. 142-144.
View/Download from: Publisher's site
Gill, AQ & Maheshwari, D 1970, 'Applying DevOps for Distributed Agile Development: A Case Study', Advances in Software Engineering, Education, and e-Learning, The 18th International Conference on Software Engineering Research and Practice, Springer International Publishing, Las Vegas, Nevada, USA, pp. 719-728.
View/Download from: Publisher's site
Gong, Y, Yi, J, Chen, D-D, Zhang, J, Zhou, J & Zhou, Z 1970, 'Inferring the Importance of Product Appearance with Semi-supervised Multi-modal Enhancement', Proceedings of the 29th ACM International Conference on Multimedia, MM '21: ACM Multimedia Conference, ACM, pp. 1120-1128.
View/Download from: Publisher's site
Guo, G, Zhang, C, He, W & Zhu, X 1970, 'Design of Broadband Low-Noise Amplifier in 45-nm SOI Technology', 2021 14th UK-Europe-China Workshop on Millimetre-Waves and Terahertz Technologies (UCMMT), 2021 14th UK-Europe-China Workshop on Millimetre-Waves and Terahertz Technologies (UCMMT), IEEE, pp. 1-3.
View/Download from: Publisher's site
Guo, YJ, Chen, S-L & Liu, Y 1970, 'Reconfigurable Antenna Arrays for Integrated Space and Terrestrial Networks', 2020 International Symposium on Antennas and Propagation (ISAP), 2020 International Symposium on Antennas and Propagation (ISAP), IEEE, Osaka, Japan, pp. 597-598.
View/Download from: Publisher's site
View description>>
Integrated space and terrestrial networks are expected to be a key technology for beyond 5G communications systems. One main challenge posed for the antennas is the array performance deterioration caused by orientation changes of various elements mounted to conformal platforms. To overcome this challenge, a reconfigurable antenna element that can switch among four linear polarizations is reported and applied to a conformal array. An efficient array synthesis algorithm is utilized to attain high-gain, low-sidelobes, and low-cross-polarization characteristics. A linear conformal array is presented to verify the effectiveness of the developed algorithm.
He, X, Deng, L & Yang, Y 1970, '3D-Printed Sub-Terahertz Lens for Manipulation of Deflective Quasi-Non-Diffractive OAM Waves', 2021 IEEE Asia-Pacific Microwave Conference (APMC), 2021 IEEE Asia-Pacific Microwave Conference (APMC), IEEE, Brisbane, Australia, pp. 332-334.
View/Download from: Publisher's site
View description>>
A 3D-printed sub-terahertz lens for manipulating quasi-non-diffractive orbital angular momentum (OAM) waves is proposed in this paper. The proposed lens comprises all-dielectric elements that impose desired phase profiles on the incident waves by varying their height. Based on the concept of the Bessel beam launchers and the beam deflectors, quasi-non-diffractive OAM waves with a pre-defined deflection angle can be produced by the proposed lens. For verification, two lenses were 3D printed for producing OAM waves with a non-diffractive depth of 55.58λc (λc is the free-space wavelength at 140 GHz). Measured by a terahertz imaging camera, the desired quasi-non-diffractive OAM waves were observed behind the proposed lenses with expected non-diffractive performance and a large deflection angle of up to 47°.
Hoang, L, Zhang, JA, Nguyen, D, Kekirigoda, A & Hui, K-P 1970, 'Nullification of Multiple Correlated Jammers', 2021 IEEE 94th Vehicular Technology Conference (VTC2021-Fall), 2021 IEEE 94th Vehicular Technology Conference (VTC2021-Fall), IEEE, Virtual, pp. 1-6.
View/Download from: Publisher's site
View description>>
Effective suppression of the intentional jamming signals is crucial to ensure reliable wireless communication. However, as demonstrated in this paper, when the transmitted jamming signals are highly correlated, and especially when the correlations between transmitted jamming signals are deliberately varied over time, nullifying the jamming signals can be challenging. Unlike existing studies assuming uncorrelated jamming signals or non-zero but constant correlations, we evaluate the impact of the non-zero and varying correlations on the suppression of the jamming signals. We discover that by varying the correlations between transmitted jamming signals, jammers can 'virtually change' the jamming channels hence their nullspace, even when these channels do not physically change. That makes most jamming suppression techniques that rely on steering receiving beams towards the nullspace of jamming channels no longer applicable. To tackle the problem, we develop techniques to effectively track the jamming nullspace and update the receiving beams accordingly. It is demonstrated by Monte Carlo simulations that our proposed techniques can suppress/nullify jamming signals for all considered scenarios with non-zero and varying correlations amongst jamming signals.
Huang, H, Zhang, J, Zhang, J, Wu, Q & Xu, C 1970, 'PTN: A Poisson Transfer Network for Semi-supervised Few-shot Learning', Proceedings of the AAAI Conference on Artificial Intelligence, The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21), Association for the Advancement of Artificial Intelligence (AAAI), Online, pp. 1602-1609.
View/Download from: Publisher's site
View description>>
The predicament in semi-supervised few-shot learning (SSFSL) is to maximize the value of the extra unlabeled data to boost the few-shot learner. In this paper, we propose a Poisson Transfer Network (PTN) to mine the unlabeled information for SSFSL from two aspects. First, the Poisson Merriman–Bence–Osher (MBO) model builds a bridge for the communications between labeled and unlabeled examples. This model serves as a more stable and informative classifier than traditional graph-based SSFSL methods in the message-passing process of the labels. Second, the extra unlabeled samples are employed to transfer the knowledge from base classes to novel classes through contrastive learning. Specifically, we force the augmented positive pairs close while push the negative ones distant. Our contrastive transfer scheme implicitly learns the novel-class embeddings to alleviate the over-fitting problem on the few labeled data. Thus, we can mitigate the degeneration of embedding generality in novel classes. Extensive experiments indicate that PTN outperforms the state-of-the-art few-shot and SSFSL models on miniImageNet and tieredImageNet benchmark datasets.
Huang, W, Da Xu, RY, Jiang, S, Liang, X & Oppermann, I 1970, 'GAN-based Gaussian Mixture Model Responsibility Learning', 2020 25th International Conference on Pattern Recognition (ICPR), 2020 25th International Conference on Pattern Recognition (ICPR), IEEE, pp. 3467-3474.
View/Download from: Publisher's site
Huang, W, Du, W & Xu, RYD 1970, 'On the Neural Tangent Kernel of Deep Networks with Orthogonal Initialization', Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, Thirtieth International Joint Conference on Artificial Intelligence {IJCAI-21}, International Joint Conferences on Artificial Intelligence Organization, pp. 2577-2583.
View/Download from: Publisher's site
View description>>
The prevailing thinking is that orthogonal weights are crucial to enforcing dynamical isometry and speeding up training. The increase in learning speed that results from orthogonal initialization in linear networks has been well-proven. However, while the same is believed to also hold for nonlinear networks when the dynamical isometry condition is satisfied, the training dynamics behind this contention have not been thoroughly explored. In this work, we study the dynamics of ultra-wide networks across a range of architectures, including Fully Connected Networks (FCNs) and Convolutional Neural Networks (CNNs) with orthogonal initialization via neural tangent kernel (NTK). Through a series of propositions and lemmas, we prove that two NTKs, one corresponding to Gaussian weights and one to orthogonal weights, are equal when the network width is infinite. Further, during training, the NTK of an orthogonally-initialized infinite-width network should theoretically remain constant. This suggests that the orthogonal initialization cannot speed up training in the NTK (lazy training) regime, contrary to the prevailing thoughts. In order to explore under what circumstances can orthogonality accelerate training, we conduct a thorough empirical investigation outside the NTK regime. We find that when the hyper-parameters are set to achieve a linear regime in nonlinear activation, orthogonal initialization can improve the learning speed with a large learning rate or large depth.
Huang, Y, Wu, Q, Xu, J, Zhong, Y & Zhang, Z 1970, 'Clothing Status Awareness for Long-Term Person Re-Identification', 2021 IEEE/CVF International Conference on Computer Vision (ICCV), 2021 IEEE/CVF International Conference on Computer Vision (ICCV), IEEE, Montreal, pp. 11875-11884.
View/Download from: Publisher's site
View description>>
Long-Term person re-identification (LT-reID) exposes extreme challenges because of the longer time gaps between two recording footages where a person is likely to change clothing. There are two types of approaches for LT-reID: biometrics-based approach and data adaptation based approach. The former one is to seek clothing irrelevant biometric features. However, seeking high quality biometric feature is the main concern. The latter one adopts fine-tuning strategy by using data with significant clothing change. However, the performance is compromised when it is applied to cases without clothing change. This work argues that these approaches in fact are not aware of clothing status (i.e., change or no-change) of a pedestrian. Instead, they blindly assume all footages of a pedestrian have different clothes. To tackle this issue, a Regularization via Clothing Status Awareness Network (RCSANet) is proposed to regularize descriptions of a pedestrian by embedding the clothing status awareness. Consequently, the description can be enhanced to maintain the best ID discriminative feature while improving its robustness to real-world LT-reID where both clothing-change case and no-clothing-change case exist. Experiments show that RCSANet performs reasonably well on three LT-reID datasets.
Ismail, L, Niyato, D, Sun, S, Hoang, DT, Kim, DI & Liang, Y-C 1970, 'Jamming Mitigation in JRC Systems via Deep Reinforcement Learning and Backscatter-supported Intelligent Deception Strategy', 2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS), 2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS), IEEE, pp. 1053-1058.
View/Download from: Publisher's site
View description>>
In this paper, we develop a framework to optimize the trade-off between radar sensing and data transmission in Joint Radar-Communication (JRC) systems under smart and reactive jamming attacks. First, we propose a novel JRC design architecture that uses backscatter technology and deception strategy to leverage jamming attacks for a JRC system. The deception strategy is used to predict the jammer's action and adopt appropriate counterattack instantaneously, while backscatter technology is used to transmit data on the jamming signals. To deal with the jamming strategy uncertainty (e.g., jamming capability), we then develop a deep reinforcement learning algorithm to quickly find the optimal defense policy for the JRC system. Our in-depth investigation reveals that the proposed design not only significantly undermines the jamming attacks, but also utilises jamming signals to improve the system performances. Compared with conventional anti-jamming methods, our proposed design significantly improves data throughput while maintaining a satisfactory radar sensing performance in dynamic environments. Moreover, the proposed deep reinforcement learning based solution can converge four times faster than a conventional deep Q- Learning based solution.
Jauregi Unanue, I, Parnell, J & Piccardi, M 1970, 'BERTTune: Fine-Tuning Neural Machine Translation with BERTScore', Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), Association for Computational Linguistics, pp. 915-924.
View/Download from: Publisher's site
Jian, Z, Tengteng, X, Jianjun, Q, Xiao, Y, Zhang, H, Li, H & Li, C 1970, 'Single Image Self-Learning Super-Resolution with Robust Matrix Regression', AATCC Journal of Research, SAGE Publications, pp. 135-142.
View/Download from: Publisher's site
View description>>
The similarity measure plays the key role in the self-learning framework for single image super-resolution. This paper involves matrix regression with properties of robustness and two-dimensional structure to measure the similarity between image blocks and enhance the effect of super-resolution. Specifically, we use the minimal nuclear norm of representation error as a criterion, and the alternating direction method of multipliers (ADMM) to calculate the similarity between high- and low-resolution image blocks. Evaluation on several images with different interference and experimental results of super-resolution images clearly demonstrate the advantages of our proposed method in visual robustness and super-resolution effects.
Kieu, BT, Unanue, IJ, Pham, SB, Phan, HX & Piccardi, M 1970, 'Learning Neural Textual Representations for Citation Recommendation', 2020 25th International Conference on Pattern Recognition (ICPR), 2020 25th International Conference on Pattern Recognition (ICPR), IEEE, Online, pp. 4145-4152.
View/Download from: Publisher's site
Kionig, L, Vold, T, Ranglund, OJ, Trajkovik, V, Videnovik, M & Braun, R 1970, 'Use of IT in Higher Education and Training - Social learning through outdoor quiz game app', 2021 19th International Conference on Information Technology Based Higher Education and Training (ITHET), 2021 19th International Conference on Information Technology Based Higher Education and Training (ITHET), IEEE, Sydney, Australia, pp. 1-4.
View/Download from: Publisher's site
View description>>
Learning in higher education is no longer by listening to a professor and handing in assignments. At the Inland Norway University of Applied Sciences, the Knowledge Management (KM) study programme has been developed over several years. From introducing Flipped Classroom, the development has been to make the students develop their own assignments based on the issues of KM they are able to unveil at their own workplaces. The practice on this is done by working to develop short cases to solve in the classroom rather than giving lectures. The lectures over the textbook and curriculum are provided by streaming video and podcasts and the students are encouraged to download and watch/listen prior to the seminars. A short introduction is provided at the start of the seminars, but not as elaborated as in the videos and podcasts. The students tend to stay indoors and work. To investigate how breaking up the indoor stay and to continue the learning process during a 'break' outside, we have developed quizzes from the curriculum. They have to download an app and in groups solve the quizzes that pop up when they close in on the designated area on the map in the app. In the app, the areas are marked by icons in the shape of berries (blueberry, raspberry, cloudberry, etc.) on a map. They have to go to the area in order for the quiz to appear. The quizzes are up to now developed by the lecturers. The students have during the Covid-19 pandemic been working in solitude and thus lost the important factor of social learning. Attempts to make the students work in group have only to a certain extent been successful. As well as 'black screens', the number of students 'fading out' when trying to divide the students into 'breakoutrooms', to support the social learning processes, are too high. Encouraging the students to go outside and work in groups to solve the quizzes allow the student to also discuss other issues than just the curriculum, and to get to know each other outside...
Klempous, R, Kluwak, K, Atsushi, I, Gorski, T, Nikodem, J, Bozejko, W, Chaczko, Z, Borowik, G, Rozenblit, J & Kulbacki, M 1970, 'Neural Networks Classification for Training of Five German Longsword Mastercuts - A Novel Application of Motion Capture: Analysis of Performance of Sword Fencing in the Historical European Martial Arts (HEMA) Domain', 2021 IEEE 21st International Symposium on Computational Intelligence and Informatics (CINTI), 2021 IEEE 21st International Symposium on Computational Intelligence and Informatics (CINTI), IEEE, pp. 000137-000142.
View/Download from: Publisher's site
Kumar, A, Esmaili, N & Piccardi, M 1970, 'A REINFORCEd Variational Autoencoder Topic Model', International Conference on Neural Information Processing, International Conference on Neural Information Processing, Springer International Publishing, Bali, Indonesia, pp. 360-369.
View/Download from: Publisher's site
Li, M, Yang, Y, Iacopi, F & Nulman, J 1970, 'Additively Manufactured Multi-Layer Bandpass Filter Based on Vertically Integrated Composite Right and Left Handed Resonator', 2021 IEEE Asia-Pacific Microwave Conference (APMC), 2021 IEEE Asia-Pacific Microwave Conference (APMC), IEEE, Brisbane, Australia, pp. 175-177.
View/Download from: Publisher's site
View description>>
This paper proposed a miniaturised multi-layer composite right/left-handed (CRLH) resonator. The odd- and even-mode circuit analysis method is presented to explain the resonance properties of the three-dimension (3D) CRLH resonator. Based on the CRLH resonator, a bandpass filter (BPF) with wide bandwidth, low-loss, and compact size is proposed. A fully-integrated additive manufacturing (AM) approach is introduced to fabricate the proposed BPF. Finally, the proposed compact BPF is designed at 8.3 GHz with a bandwidth of 72.3%, a low insertion loss of 0.51 dB, and a compact size of 5.8mm × 2.1 mm × 0.89 mm (0.269λg × 0.097λg× 0.041λg), which is suitable for circuit-in-package applications.
Li, M, Yang, Y, Zhang, Y, Iacopi, F, Ram, S & Nulman, J 1970, 'A Fully Integrated Conductive and Dielectric Additive Manufacturing Technology for Microwave Circuits and Antennas', 2020 50th European Microwave Conference (EuMC), 2020 50th European Microwave Conference (EuMC), IEEE, pp. 392-395.
View/Download from: Publisher's site
View description>>
© 2021 EuMA. A fully-integrated additive manufacturing (AM) approach for microwave devices is presented in this work. The applied AM technology can print the circuit models simultaneously with conductive and dielectric materials. Taking advantage of this one-stop 3D manufacturing technology, multilayer circuit board with vias or holes can be prototyped rapidly and precisely. The electrical properties of the dielectric ink material are measured up to 40 GHz using a quasi-optical cavity test system. To further demonstrate the merit of this technology, an infilled-ground transmission line, as well as a microstrip patch antenna, are designed and fabricated. For proof-of-concept, the return loss, gain and radiation patterns of the antenna are measured, which demonstrate a good agreement with the simulated results.
Li, S & Piccardi, M 1970, 'Improving Adversarial Text Generation with n-Gram Matching', Proceedings of the 35th Pacific Asia Conference on Language Information and Computation Paclic 2021, pp. 647-655.
View description>>
In the past few years, generative adversarial networks (GANs) have become increasingly important in natural language generation. However, their performance seems to still have a significant margin for improvement. For this reason, in this paper we propose a new adversarial training method that tackles some of the limitations of GAN training in unconditioned generation tasks. In addition to the commonly used reward signal from the discriminator, our approach leverages another reward signal which is based on the occurrence of n-gram matches between the generated sentences and the training corpus. Thanks to the inherent correlation of this reward signal with the commonly used evaluation metrics such as BLEU, our approach implicitly bridges the gap between the objectives used during training and inference. To circumvent the non-differentiability issues associated with a discrete objective, our approach leverages the reinforcement learning policy gradient theorem. Our experimental results show that the model trained with mixed rewards from both n-gram matching and the discriminator has been able to outperform other GAN-based models in terms of BLEU score and quality-diversity trade-off at a parity of computational budget.
Li, X, Jing, X, Zhang, A & He, Y 1970, 'Few-shot Human Activity Recognition with Radar Micro-Doppler Spectrograms', 2021 CIE International Conference on Radar (Radar), 2021 CIE International Conference on Radar (Radar), IEEE, pp. 1471-1474.
View/Download from: Publisher's site
Li, X, Peng, Y & Xu, M 1970, 'Edge-enhanced Instance Segmentation of Wrist CT via a Semi-Automatic Annotation Database Construction Method', 2021 Digital Image Computing: Techniques and Applications (DICTA), 2021 Digital Image Computing: Techniques and Applications (DICTA), IEEE, pp. 01-08.
View/Download from: Publisher's site
Lin, J-Y & Yang, Y 1970, '3D Sub-Terahertz Dual-Mode Cavity Resonator and Its Application to Dual-Polarized Frequency Selective Surface', 2021 IEEE Asia-Pacific Microwave Conference (APMC), 2021 IEEE Asia-Pacific Microwave Conference (APMC), IEEE, Brisbane, Australia, pp. 494-496.
View/Download from: Publisher's site
View description>>
A novel 3D sub-terahertz frequency selective surface (FSS) based on a dual-mode cavity resonator is presented in this paper. In each resonator unit, a pair of degenerate modes, namely TM210 and TM120, are excited simultaneously to dominate each of the dual polarizations, respectively. High isolation and cross-polarization level can be implemented due to the modal orthogonality of the proposed degenerate modes. Both channels share the common cavity resonators from the first order to the last order with specified external quality factor (Qe) and coupling coefficient (K). To proof-of-concept, a 2nd-order FSS prototype is designed, and its performance is verified in simulation. It resonates at 120 GHz with a fractional bandwidth of 6.1%. The channel isolation is better than 50 dB.
Lin, J-Y, Wong, S-W & Yang, Y 1970, 'Filtering In-Band Full-Duplex Slot Antenna Based on TM120 and TM210 Dual-Mode Resonators', 2021 IEEE MTT-S International Microwave Filter Workshop (IMFW), 2021 IEEE MTT-S International Microwave Filter Workshop (IMFW), IEEE, Perugia, Italy, pp. 249-251.
View/Download from: Publisher's site
View description>>
A filtering in-band full-duplex (IBFD) cavity-backed slot antenna is presented in this paper. Each of channels in the full-duplex function is dominated by a pair of degenerate modes, namely TM210 and TM120, respectively. High isolation can be implemented between channels due to the modal orthogonality of degenerate modes. In the filtering function, both channels share the common cavity resonators from the first order to the last order with specified external quality factors (Qe) and coupling coefficient (K). At the last order, radiating slots for both channels are adopted to transmit/receive the dual-polarized signals, respectively. For proof-of-concept, a 2nd-order IBFD slot antenna prototype is constructed and simulated. It resonates at 10 GHz with a fractional bandwidth of 3.3% and a realized gain of 10. 3 dBi.
Lin, J-Y, Yang, Y & Wong, S-W 1970, 'Four-Way Filtering Crossover Based on Quadruple-Mode Cavity Resonator', 2021 IEEE MTT-S International Microwave Symposium (IMS), 2021 IEEE/MTT-S International Microwave Symposium - IMS 2021, IEEE, Atlanta, GA, USA, pp. 254-257.
View/Download from: Publisher's site
View description>>
A novel waveguide four-channel filter, namely four-way filtering crossover, is presented in this paper. A quadruple-mode cavity resonator, integrated with two fundamental modes TE011, TE101 and two high-order modes TM210, TM120, is adopted to dominate each channel of the proposed four-way filtering crossover, respectively. The proposed quadruple modes are excited in the first order, simultaneously, and transmitted through to the last order with specified external quality factors (Qe) and coupling coefficient (K). By this method, the circuit volume is significantly reduced. A 3rd-order four-way filtering crossover prototype is manufactured and tested. The measured results match well with the simulated ones to verify the proposed design methodology.
Liu, H, Zhu, X, Wang, Y, Men, K & Yeo, KS 1970, 'A 60 GHz Edge-Coupled 4-Way Balun Power Amplifier with 22.7 dBm Output Power and 27.7% Peak Efficiency', 2021 IEEE MTT-S International Microwave Symposium (IMS), 2021 IEEE/MTT-S International Microwave Symposium - IMS 2021, IEEE, pp. 850-853.
View/Download from: Publisher's site
Liu, Y, Wang, M, Xu, J, Gong, S, Hoang, DT & Niyato, D 1970, 'Boosting Secret Key Generation for IRS-Assisted Symbiotic Radio Communications', 2021 IEEE 93rd Vehicular Technology Conference (VTC2021-Spring), 2021 IEEE 93rd Vehicular Technology Conference (VTC2021-Spring), IEEE, ELECTR NETWORK, pp. 1-6.
View/Download from: Publisher's site
Markos, C, Yu, JJQ & Xu, RYD 1970, 'Capturing Uncertainty in Unsupervised GPS Trajectory Segmentation Using Bayesian Deep Learning', Proceedings of the AAAI Conference on Artificial Intelligence, AAAI Conference on Artificial Intelligence, Association for the Advancement of Artificial Intelligence (AAAI), Virtual, pp. 390-398.
View/Download from: Publisher's site
View description>>
Intelligent transportation management requires not only statistical information on users' mobility patterns, but also knowledge of their corresponding transportation modes. While GPS trajectories can be readily obtained from GPS sensors found in modern smartphones and vehicles, these massive geospatial data are neither automatically annotated nor segmented by transportation mode, subsequently complicating transportation mode identification. In addition, predictive uncertainty caused by the learned model parameters or variable noise in GPS sensor readings typically remains unaccounted for. To jointly address the above issues, we propose a Bayesian deep learning framework for unsupervised GPS trajectory segmentation. After unlabeled GPS trajectories are preprocessed into sequences of motion features, they are used in unsupervised training of a channel-calibrated temporal convolutional neural network for timestep-level transportation mode identification. At test time, we approximate variational inference via Monte Carlo dropout sampling, leveraging the mean and variance of the predicted distributions to classify each input timestep and estimate its predictive uncertainty, respectively. The proposed approach outperforms both its non-Bayesian variant and established GPS trajectory segmentation baselines on Microsoft's Geolife dataset without using any labels.
Nguyen, CT, Hoang, DT, Nguyen, DN, Pham, H-A, Tuong, NH & Dutkiewicz, E 1970, 'Blockchain-based Secure Platform for Coalition Loyalty Program Management', 2021 IEEE Wireless Communications and Networking Conference (WCNC), 2021 IEEE Wireless Communications and Networking Conference (WCNC), IEEE, China, pp. 1-6.
View/Download from: Publisher's site
View description>>
In this paper, we propose a novel blockchain-based platform for the coalition loyalty program management. The platform allows the customers to freely exchange loyalty points from different existing blockchain-based loyalty programs by utilizing the sidechain technology. Moreover, by adopting the Proof-of-Stake consensus mechanism, we can further increase customer engagement by allowing the customers to participate in the consensus process to earn additional tokens. However, this might lead to situations where the customers centralize all tokens to a single chain/loyalty program if the chain offers more rewards for consensus participation. Through security and performance analyses, we show that such centralization of stakes poses a threat to the security and performance of the platform. Therefore, we develop a non-cooperative game model to analyze the rational behavior of the users. We reveal that the consensus participation rewards govern the user behavior and the decentralization of the system. Numerical experiments confirm our analytical results and show that the ratios between the consensus rewards have a significant impact on the system’s security and performance.
Parnell, J, Jauregi Unanue, I & Piccardi, M 1970, 'RewardsOfSum: Exploring Reinforcement Learning Rewards for Summarisation', Proceedings of the 5th Workshop on Structured Prediction for NLP (SPNLP 2021), Proceedings of the 5th Workshop on Structured Prediction for NLP (SPNLP 2021), Association for Computational Linguistics, Online, pp. 1-11.
View/Download from: Publisher's site
Raza, A, Keshavarz, R & Shariati, N 1970, 'Miniaturized Patch Rectenna Using 3-Turn Complementary Spiral Resonator for Wireless Power Transfer', 2021 IEEE Asia-Pacific Microwave Conference (APMC), 2021 IEEE Asia-Pacific Microwave Conference (APMC), IEEE, pp. 455-457.
View/Download from: Publisher's site
Raza, MA, Abolhasan, M, Lipman, J, Shariati Moghadam, N & Ni, W 1970, 'Statistical Learning-Based Dynamic Retransmission Mechanism for Mission Critical Communication: An Edge-Computing Approach', IEEE 45th Conference on Local Computer Networks, IEEE 45th Conference on Local Computer Networks, Sydney, NSW, Australia (Held Virtually).
Saputra, YM, Nguyen, DN, Hoang, DT & Dutkiewicz, E 1970, 'Incentive Mechanism for AI-Based Mobile Applications with Coded Federated Learning', 2021 IEEE Global Communications Conference (GLOBECOM), GLOBECOM 2021 - 2021 IEEE Global Communications Conference, IEEE, Spain, pp. 1-6.
View/Download from: Publisher's site
Saputra, YM, Nguyen, DN, Hoang, DT & Dutkiewicz, E 1970, 'Selective Federated Learning for On-Road Services in Internet-of-Vehicles', 2021 IEEE Global Communications Conference (GLOBECOM), GLOBECOM 2021 - 2021 IEEE Global Communications Conference, IEEE, Spain, pp. 1-6.
View/Download from: Publisher's site
View description>>
The Internet-of-Vehicles (IoV) can make driving safer and bring more services to smart vehicle (SV) users. Specif-ically, with IoV, the road service provider (RSP) can collaborate with SVs to provide high-accurate on-road information-based services by implementing federated learning (FL). Nonetheless, SVs' activities are very diverse in IoV networks, e.g., some SVs move frequently while other SVs are occasionally disconnected from the network. Consequently, obtaining information from all SVs for the learning process is costly and impractical. Furthermore, the quality-of-information (QoI) obtained by SVs also dramatically varies. That makes the learning process from all SVs simultaneously even worse when some SVs have low QoI. In this paper, we propose a novel selective FL approach for an IoV network to address these issues. Particularly, we first develop an SV selection method to determine a set of active SVs based on their location significance. In this case, we adopt a K-means algorithm to classify significant and insignificant areas where the SVs are located according to the areas' average annual daily flow of vehicles. From the set of SVs in the significant areas, we select the best SVs for the FL execution based on the SVs' QoI at each learning round. Through simulation results using a real-world on-road dataset, we observe that our proposed approach can converge to the FL results even with only 10% of active SVs in the network. Moreover, our results reveal that the RSP can optimize on-road services with faster convergence up to 63% compared with other baseline FL methods.
Son, DH, Thi Thuy Quynh, T, Khoa, TV, Thai Hoang, D, Trung, NL, Viet Ha, N, Niyato, D, Nguyen, DN & Dutkiewicz, E 1970, 'An Effective Framework of Private Ethereum Blockchain Networks for Smart Grid', 2021 International Conference on Advanced Technologies for Communications (ATC), 2021 International Conference on Advanced Technologies for Communications (ATC), IEEE, Virtual, pp. 312-317.
View/Download from: Publisher's site
Song, L-Z, Qin, P-Y & Guo, YJ 1970, 'A Review on Conformal Transmitarrays', 2021 15th European Conference on Antennas and Propagation (EuCAP), 2021 15th European Conference on Antennas and Propagation (EuCAP), IEEE, pp. 1-3.
View/Download from: Publisher's site
Song, L-Z, Qin, P-Y & Guo, YJ 1970, 'Millimetre-Wave Multi-Beam Shaped Transmitarray with A Wide Beam Coverage', 2021 IEEE Asia-Pacific Microwave Conference (APMC), 2021 IEEE Asia-Pacific Microwave Conference (APMC), IEEE, pp. 28-30.
View/Download from: Publisher's site
Song, L-Z, Qin, P-Y & Jay Guo, Y 1970, 'E-band Wide-Angle Multi-Beam Shaped Transmitarray', 2021 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting (APS/URSI), 2021 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting (APS/URSI), IEEE, pp. 1895-1896.
View/Download from: Publisher's site
Song, Y, Zeng, J, Wu, T, Ni, W & Liu, RP 1970, 'Vision-Based Parking Space Detection: A Mask R-CNN Approach', 2021 IEEE/CIC International Conference on Communications in China (ICCC), 2021 IEEE/CIC International Conference on Communications in China (ICCC), IEEE, pp. 300-305.
View/Download from: Publisher's site
View description>>
The rapid increment of vehicles and the inefficient management of available parking spaces lead to traffic congestion and resource waste in urban areas. Thus, there is an urgent need to develop an intelligent parking system to find out suitable parking spaces quickly. To this end, we elaborate on various object detection algorithms and parking space detection methods. Then, we propose a novel vision-based parking space detection system with a Mask R-CNN approach. It can be applied in various scenarios and infer parking spaces from the positions of the parked vehicles. Experimental results have shown that the proposed system performs well in large car parks and reduces the human effort in image processing. This study provides a successful paradigm for future intelligent parking systems, and it can also effectively promote the development of smart cities.
Sun, H-H, Jones, B, Guo, YJ & Lee, YH 1970, 'Dual-Band Base Station Antenna Array with Suppressed Cross-Band Mutual Scattering', 2021 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting (APS/URSI), 2021 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting (APS/URSI), IEEE, pp. 1-2.
View/Download from: Publisher's site
Sun, H-H, Zhu, H, Ding, C, Jones, B & Guo, YJ 1970, 'Spiral Choking Method for Scattering Suppression in 4G and 5G Base Station Antenna Arrays', 2021 International Symposium on Antennas and Propagation (ISAP), 2021 International Symposium on Antennas and Propagation (ISAP), IEEE, pp. 1-2.
View/Download from: Publisher's site
Sun, Z, Yao, Y, Wei, X-S, Zhang, Y, Shen, F, Wu, J, Zhang, J & Shen, HT 1970, 'Webly Supervised Fine-Grained Recognition: Benchmark Datasets and An Approach', 2021 IEEE/CVF International Conference on Computer Vision (ICCV), 2021 IEEE/CVF International Conference on Computer Vision (ICCV), IEEE, Montreal, QC, Canada, pp. 10582-10591.
View/Download from: Publisher's site
View description>>
Learning from the web can ease the extreme dependence of deep learning on large-scale manually labeled datasets. Especially for fine-grained recognition, which targets at distinguishing subordinate categories, it will significantly reduce the labeling costs by leveraging free web data. Despite its significant practical and research value, the webly supervised fine-grained recognition problem is not extensively studied in the computer vision community, largely due to the lack of high-quality datasets. To fill this gap, in this paper we construct two new benchmark webly supervised fine-grained datasets, termed WebFG-496 and WebiNat-5089, respectively. In concretely, WebFG-496 consists of three sub-datasets containing a total of 53,339 web training images with 200 species of birds (Web-bird), 100 types of aircrafts (Web-aircraft), and 196 models of cars (Web-car). For WebiNat-5089, it contains 5089 sub-categories and more than 1.1 million web training images, which is the largest webly supervised fine-grained dataset ever. As a minor contribution, we also propose a novel webly supervised method (termed “Peer-learning”) for benchmarking these datasets. Comprehensive experimental results and analyses on two new benchmark datasets demonstrate that the proposed method achieves superior performance over the competing baseline models and states-of-the-art. Our benchmark datasets and the source codes of Peer-learning have been made available at https://github.com/NUST-Machine-Intelligence-Laboratory/weblyFG-dataset.
Tuyen Trinh, K, Yang, Y & Chandra Karmakar, N 1970, 'Design of Ka-Band Reflection-Type Phase Shifter Using Offset Broadside-Coupled Line Coupler in 0.13 µm SiGe BiCMOS Technology', 2020 IEEE Eighth International Conference on Communications and Electronics (ICCE), 2020 IEEE Eighth International Conference on Communications and Electronics (ICCE), IEEE, Phu Quoc Island, Vietnam, pp. 203-208.
View/Download from: Publisher's site
View description>>
A 36 - 38 GHz Ka-band SiGe BiCMOS reflection-type phase shifter (RTPS) for a soil moisture radiometer antenna is presented. The phase shifter comprises an offset broadside-coupled line 3 dB coupler and two identical varactor reflective loads for continuous phase shift. The offset broadside-coupled line coupler is designed to achieve smaller insertion loss (IL) compared to a normal broadside coupled line coupler. The varactors, which are essential components of the reflective loads, are biased with a variable voltage from -1 to 2 V to control phase shift continuously. The simulation results show that the phase shifter yields a phase shift from 0° to 253° with 12 ± 2 dB IL. More than 12 dB about the input and output return loss (RL) is obtained over 36 - 38 GHz. The phase shifter is designed using 0.13 μm SiGe BiCMOS technology. The chip consumes almost zero DC power. The chip is compact, with the core area of about 0.32 mm2.
Unanue, IJ & Piccardi, M 1970, 'Pretrained Language Models and Backtranslation for English-Basque Biomedical Neural Machine Translation', 5th Conference on Machine Translation, WMT 2020 - Proceedings, Fifth Conference on Machine Translation (WMT20), The Association for Computational Linguistics, Online, pp. 826-832.
View description>>
This paper describes the machine translation systems proposed by the University of Technology Sydney Natural Language Processing (UTS NLP) team for the WMT20 English-Basque biomedical translation tasks. Due to the limited parallel corpora available, we have opted to train a BERT-fused NMT model that leverages the use of pretrained language models. Furthermore, we have augmented the training corpus by backtranslating monolingual data. Our experiments show that NMT models in low-resource scenarios can benefit from combining these two training techniques, with improvements of up to 6.16 BLEU percentage points in the case of biomedical abstract translations.
Van Huynh, N, Hoang, DT, Nguyen, DN & Dutkiewicz, E 1970, 'Dynamic Optimal Coding and Scheduling for Distributed Learning over Wireless Edge Networks', 2021 IEEE Global Communications Conference (GLOBECOM), GLOBECOM 2021 - 2021 IEEE Global Communications Conference, IEEE, Spain, pp. 1-6.
View/Download from: Publisher's site
Van Huynh, N, Nguyen, DN, Hoang, DT & Dutkiewicz, E 1970, 'Defeating Reactive Jammers with Deep Dueling-based Deception Mechanism', ICC 2021 - IEEE International Conference on Communications, ICC 2021 - IEEE International Conference on Communications, IEEE, Montreal, QC, Canada, pp. 1-6.
View/Download from: Publisher's site
View description>>
Conventional anti-jamming solutions like frequency hopping and rate adaptation that are more suitable for proactive jammers are not effective in dealing with reactive jammers. These advanced jammers with recent advances in signal detection can discern the activities of legitimate radios then attack them as soon as the transmission is detected. To combat this type of jammer, we develop an intelligent deception strategy in which the transmitter generates 'fake' transmissions to attract the jammer. After that, the transmitter can either harvest energy from the jamming signals or backscatter the jamming signals to transmit data. As such, we can leverage jamming signals to improve the average throughput and reduce the packet loss. To effectively learn from and adapt to the dynamic and uncertainty of jamming attacks, we develop a Markov decision process (MDP) that can dynamically construct two decision epochs in each time slot to capture the special properties of our proposed deception mechanism. The Q-learning algorithm then can be adopted to find the optimal deception strategy for the transmitter. Nevertheless, due to very-slow convergence rates, conventional Q-learning algorithms may not be effective in dealing with smart jamming attacks. We thus develop an advanced deep reinforcement learning model based on deep dueling architecture to quickly obtain the optimal defense policy. Simulation results show that the proposed framework can improve the system throughput up to 173% and reduce the packet loss by 42% compared with other anti-jamming strategies that are not equipped with the proposed deception mechanism.
Wang, X, Jin, R, Qin, P-Y & Ding, C 1970, 'Low RCS Transmitarray Using Phase Controllabe Rasorber', 2021 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting (APS/URSI), 2021 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting (APS/URSI), IEEE, Singapore, Singapore, pp. 161-162.
View/Download from: Publisher's site
View description>>
A phase controllable rasorber, also named as phase controllable absorptive frequency-selective transmission (AFST) surface, is developed in this paper. It is composed of asymmetrical resonators with lumped resistors, achieving an absorption-transmission-absorption response. Compared with other reported rasorbers, the proposed one has an additional feature that is to realize a 1-bit phase change of its element within the transmission band by rotating the element by 90°. A low radar cross section (RCS) transmitarray is designed at 12.5 GHz with a peak realized gain of 24.4 dBi using the developed elements. The 10 dB RCS reduction bandwidths are 18% and 14% for the lower and upper absorption bands, respectively.
Wang, X, Qin, P-Y & Guo, YJ 1970, '1-Bit Reconfigurable Huygens Element for Beam-Steering Transmitarrays', 2021 International Symposium on Antennas and Propagation (ISAP), 2021 International Symposium on Antennas and Propagation (ISAP), IEEE, pp. 1-2.
View/Download from: Publisher's site
Wang, Z, Xu, M & Xiao, F 1970, 'Recognizing 3D Orientation of a Two-RFID-Tag Labeled Object in Multipath Environments Using Deep Transfer Learning', 2021 IEEE 41st International Conference on Distributed Computing Systems (ICDCS), 2021 IEEE 41st International Conference on Distributed Computing Systems (ICDCS), IEEE, DC, USA, pp. 652-662.
View/Download from: Publisher's site
View description>>
State-of-the-art battery-free RFID systems attach multiple RFID tags to an object and exploit their RF phase to estimate its three-dimensional (3D) orientation. However, the measured RF phase may be inaccurate because each tag's signal fingerprint (i.e., RSSI and RF Phase) is distorted by multipath interference and electromagnetic interaction between neighboring tags. In this paper, we propose RF-Orien3D that minimizes these interferences for accurate 3D orientation recognition only using two RFID tags. The electromagnet interference modifies the radiation pattern and modulation factor of each tag in the two-element tag array, which can be estimated to compensate for the distortion in RFID fingerprints. To deal with the multipath impact, we simulate multipath noise to generate huge amounts of RFID fingerprints and use them to pre-train a convolutional neural network (CNN). Then we only collect dozens of actual samples to fine-tune the CNN for multipath-tolerant orientation recognition. The experiments show RF-Orien3D recognizes a two-tag labeled object's 2D orientation with the angular error of about 16° and its 3D orientation (azimuth and elevation) with the errors of about 29° and 11° in low/rich multipath scenarios.
Wong, S-W, Lin, J-Y, Chen, G-W, Wang, L, Du, Z-M, Zhang, L, Yang, Y & He, Y 1970, 'Wideband Three-Way Cavity Filtering Crossover Array', 2021 International Applied Computational Electromagnetics Society (ACES-China) Symposium, 2021 International Applied Computational Electromagnetics Society (ACES-China) Symposium, IEEE, Chengdu, China, pp. 1-2.
View/Download from: Publisher's site
View description>>
In this paper, a 7th-order cavity filtering crossover with three intersecting channels is presented. Three fundamental modes in one cavity resonator, namely TE011, TE101, and TM110, are adopted to control three frequency channels, respectively. Each channel of proposed crossover resonates at 3 GHz with the fractional bandwidth of 24%. Due to the modal orthogonality of three fundamental modes, good isolation among channels can be easily achieved with the level of 50 dB. Finally, the proposed design can be extended into 3times 3times 3 crossover array.
Wong, SYK, Chan, JSK, Azizi, L & Xu, RYD 1970, 'Supervised Temporal Autoencoder for Stock Return Time-series Forecasting', 2021 IEEE 45th Annual Computers, Software, and Applications Conference (COMPSAC), 2021 IEEE 45th Annual Computers, Software, and Applications Conference (COMPSAC), IEEE, pp. 1735-1741.
View/Download from: Publisher's site
Wu, T, Fan, X, Zeng, J, Ni, W & Liu, RP 1970, 'Enabling URLLC under $\kappa-\mu$ Shadowed Fading', 2021 28th International Conference on Telecommunications (ICT), 2021 28th International Conference on Telecommunications (ICT), IEEE, pp. 1-6.
View/Download from: Publisher's site
Xiong, Y, Ding, C, Cheng, Z & Guo, YJ 1970, 'Cross-Band Interaction Mitigation in Dual-Band Antenna Arrays for 4G/5G and Beyond', 2021 15th European Conference on Antennas and Propagation (EuCAP), 2021 15th European Conference on Antennas and Propagation (EuCAP), IEEE, Dusseldorf, Germany, pp. 1-5.
View/Download from: Publisher's site
View description>>
Collocating antennas for different purposes on a single communication platform is a big trend as it can improve space efficiency. However, strong interferences happen among the antennas working at different bands due to the close proximity, leading to deteriorated antenna performance. This paper proposes a simple yet effective method to alleviate this issue by developing low-scattering array topology without increasing array size. The proposed method is used on a typical 3G/4G dual-band dual-polarized base station antenna array as an example to illustrate its effectiveness. By relocating the positions of the antennas in such array, the antenna performance can be substantially enhanced. Although this technique cannot eliminate the interferences solely, it can be used as a supplementary with other techniques to achieve optimal performance. At last, the proposed array topology is used together with a low-scattering spiral antenna designed for cross-band scattering mitigation, which leads to an outstanding array performance with a compact size.
Xu, J, Wu, Q, Zhang, J & Tait, A 1970, 'AUTOMATIC SHEEP BEHAVIOUR ANALYSIS USING MASK R-CNN', 2021 Digital Image Computing: Techniques and Applications (DICTA), 2021 Digital Image Computing: Techniques and Applications (DICTA), IEEE, Gold Coast, Australia, pp. 01-06.
View/Download from: Publisher's site
View description>>
The issue of sheep welfare during live exports has triggered a lot of public concern recently. Extensive research is being carried out to monitor and improve animal welfare. Stocking density can be a critical factor affecting sheep welfare during export and its impact can be monitored through sheep behaviour, position, group dynamics and physiology. In this paper we demonstrate the application of the instance segmentation method Mask R-CNN to support sheep behaviour recognition. As an initial step, two typical behaviours standing and lying are recognized under different group sizes in pens over time. 94%+ mAP was achieved in the validation set demonstrating the effectiveness of the method on identifying sheep behaviours. Further data analysis will provide available space requirements for additional sheep allocation and daily behaviour monitoring to detect abnormal cases which will aim to improve the health and wellbeing of sheep on ships.
Xu, S, Zhang, J, Bo, L, Li, H, Zhang, H, Zhong, Z & Yuan, D 1970, 'Retinex based underwater image enhancement using attenuation compensated color balance and gamma correction', International Symposium on Artificial Intelligence and Robotics 2021, International Symposium on Artificial Intelligence and Robotics 2021, SPIE, pp. 62-62.
View/Download from: Publisher's site
Yang, L, Gomez-Garcia, R, Munoz-Ferreras, J-M & Zhu, X 1970, 'Two-Port-Reflectionless Negative-Group-Delay Circuit on Multilayered Lossy Bandstop Filter', 2021 IEEE International Workshop on Electromagnetics: Applications and Student Innovation Competition (iWEM), 2021 IEEE International Workshop on Electromagnetics: Applications and Student Innovation Competition (iWEM), IEEE, Guangzhou, China, pp. 1-3.
View/Download from: Publisher's site
View description>>
A symmetrical reflectionless negative-group-delay (NGD) circuit based on a multilayered lossy bandstop filter (BSF) is presented. It consists of two identical back-to-back-connected lossy BSFs, each of them being shaped by a resistively-terminated lossy microstrip-to-microstrip vertical transition and a lossy microstrip section arranged in a quasi-complementary-diplexer-based structure. The NGD property is determined by the shaped microstrip lossy BSF channel, whilst the resistively-terminated lossy vertical transitions are used to absorb the non-transmitted in-band RF-input-signal energy of the BSF channel in order to attain perfect power matching at the center frequency f0 and broadband two-port-reflectionless behavior. Its theoretical operational foundations are detailed through even-/odd-mode analysis of the equivalent circuit of the proposed lossy BSF. Besides, its main properties are discussed in terms of power-attenuation levels, NGD depth at f0, and NGD bandwidth (BW). For experimental-demonstration purposes, a two-layered microstrip prototype of the engineered two-port-reflectionless lossy-BSF-based NGD circuit is designed and characterized.
Yang, S, Liu, L & Xu, M 1970, 'FREE LUNCH FOR FEW-SHOT LEARNING: DISTRIBUTION CALIBRATION', Iclr 2021 9th International Conference on Learning Representations.
View description>>
Learning from a limited number of samples is challenging since the learned model can easily become overfitted based on the biased distribution formed by only a few training examples. In this paper, we calibrate the distribution of these few-sample classes by transferring statistics from the classes with sufficient examples. Then an adequate number of examples can be sampled from the calibrated distribution to expand the inputs to the classifier. We assume every dimension in the feature representation follows a Gaussian distribution so that the mean and the variance of the distribution can borrow from that of similar classes whose statistics are better estimated with an adequate number of samples. Our method can be built on top of off-the-shelf pretrained feature extractors and classification models without extra parameters. We show that a simple logistic regression classifier trained using the features sampled from our calibrated distribution can outperform the state-of-the-art accuracy on three datasets (5% improvement on miniImageNet compared to the next best). The visualization of these generated features demonstrates that our calibrated distribution is an accurate estimation.
Yang, S, Xu, M, Xie, H, Perry, S & Xia, J 1970, 'Single-View 3D Object Reconstruction from Shape Priors in Memory', 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Nashville, TN, USA, pp. 3151-3160.
View/Download from: Publisher's site
View description>>
Existing methods for single-view 3D object reconstruction directly learn to transform image features into 3D representations. However, these methods are vulnerable to images containing noisy backgrounds and heavy occlusions because the extracted image features do not contain enough information to reconstruct high-quality 3D shapes. Humans routinely use incomplete or noisy visual cues from an image to retrieve similar 3D shapes from their memory and reconstruct the 3D shape of an object. Inspired by this, we propose a novel method, named Mem3D, that explicitly constructs shape priors to supplement the missing information in the image. Specifically, the shape priors are in the forms of 'image-voxel' pairs in the memory network, which is stored by a well-designed writing strategy during training. We also propose a voxel triplet loss function that helps to retrieve the precise 3D shapes that are highly related to the input image from shape priors. The LSTM-based shape encoder is introduced to extract information from the retrieved 3D shapes, which are useful in recovering the 3D shape of an object that is heavily occluded or in complex environments. Experimental results demonstrate that Mem3D significantly improves reconstruction quality and performs favorably against state-of-the-art methods on the ShapeNet and Pix3D datasets.
Yang, Y, Zhang, R, Wu, W, Peng, Y & Xu, M 1970, 'Multi-camera Sports Players 3D Localization with Identification Reasoning', 2020 25th International Conference on Pattern Recognition (ICPR), 2020 25th International Conference on Pattern Recognition (ICPR), IEEE, pp. 4497-4504.
View/Download from: Publisher's site
Yao, L, Kusakunniran, W, Wu, Q, Zhang, J & Xu, J 1970, 'Part-based Collaborative Spatio-temporal Feature Learning for Cloth-changing Gait Recognition', 2020 25th International Conference on Pattern Recognition (ICPR), 2020 25th International Conference on Pattern Recognition (ICPR), IEEE, pp. 2057-2064.
View/Download from: Publisher's site
View description>>
In decades many gait recognition methods have been proposed using different techniques. However, due to a real-world scenario of clothing variations, a reduction of the recognition rate occurs for most of these methods. Thus in this paper, a part-based spatio-temporal feature learning method is proposed to tackle the problem of clothing variations for gait recognition. First, based on the anatomical properties, human bodies are segmented into two regions, which are affected and unaffected by clothing variations. A learning network is particularly proposed in this paper to grasp principal spatio-temporal features from those unaffected regions. Different from most part-based methods with spatial or temporal features solely being utilized, in our method these two features are associated in a more collaborative manner. Snapshots are created for each gait sequence from the H − W and T − W views. Stable spatial information is embedded in the H −W view and adequate temporal information is embedded in the T −W view. An inherent relationship exists between these two views. Thus, a collaborative spatio-temporal feature will be hybridized by concatenating these correlative spatial and temporal information. The robustness and efficiency of our proposed method are validated by experiments on CASIA Gait Dataset B and OU-ISIR Treadmill Gait Dataset B. Our proposed method can both achieve the state-of-the-art results on these two databases.
Yao, Y, Chen, T, Xie, G-S, Zhang, C, Shen, F, Wu, Q, Tang, Z & Zhang, J 1970, 'Non-Salient Region Object Mining for Weakly Supervised Semantic Segmentation', 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Nashville, TN, USA, pp. 2623-2632.
View/Download from: Publisher's site
View description>>
Semantic segmentation aims to classify every pixel of an input image. Considering the difficulty of acquiring dense labels, researchers have recently been resorting to weak labels to alleviate the annotation burden of segmentation. However, existing works mainly concentrate on expanding the seed of pseudo labels within the image’s salient region. In this work, we propose a non-salient region object mining approach for weakly supervised semantic segmentation. We introduce a graph-based global reasoning unit to strengthen the classification network’s ability to capture global relations among disjoint and distant regions. This helps the network activate the object features outside the salient area. To further mine the non-salient region objects, we propose to exert the segmentation network’s self-correction ability. Specifically, a potential object mining module is proposed to reduce the false-negative rate in pseudo labels. Moreover, we propose a non-salient region masking module for complex images to generate masked pseudo labels. Our non-salient region masking module helps further discover the objects in the non-salient region. Extensive experiments on the PASCAL VOC dataset demonstrate state-of-the-art results compared to current methods. The source codes are available at https://github.com/NUST-Machine-Intelligence-Laboratory/nsrom.
Yao, Y, Sun, Z, Zhang, C, Shen, F, Wu, Q, Zhang, J & Tang, Z 1970, 'Jo-SRC: A Contrastive Approach for Combating Noisy Labels', 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Nashville, TN, USA, pp. 5188-5197.
View/Download from: Publisher's site
View description>>
Due to the memorization effect in Deep Neural Networks (DNNs), training with noisy labels usually results in inferior model performance. Existing state-of-the-art methods primarily adopt a sample selection strategy, which selects small-loss samples for subsequent training. However, prior literature tends to perform sample selection within each mini-batch, neglecting the imbalance of noise ratios in different mini-batches. Moreover, valuable knowledge within high-loss samples is wasted. To this end, we propose a noise-robust approach named Jo-SRC (Joint Sample Selection and Model Regularization based on Consistency). Specifically, we train the network in a contrastive learning manner. Predictions from two different views of each sample are used to estimate its 'likelihood' of being clean or out-of-distribution. Furthermore, we propose a joint loss to advance the model generalization performance by introducing consistency regularization. Extensive experiments have validated the superiority of our approach over existing state-of-the-art methods. The source code and models have been made available at https://github.com/NUST-Machine-Intelligence-Laboratory/Jo-SRC.
Zhang, C, Guo, G, He, W & Zhu, X 1970, 'A 32-GHz Broadband mm-wave Power Amplifier in 45-nm SOI Technology', 2021 14th UK-Europe-China Workshop on Millimetre-Waves and Terahertz Technologies (UCMMT), 2021 14th UK-Europe-China Workshop on Millimetre-Waves and Terahertz Technologies (UCMMT), IEEE, pp. 1-3.
View/Download from: Publisher's site
Zhang, H, Huang, X & Zhang, JA 1970, 'Frequency Domain Pilot-Aided Channel Estimation for OTFS over Fast Fading Channels', 2021 IEEE 94th Vehicular Technology Conference (VTC2021-Fall), 2021 IEEE 94th Vehicular Technology Conference (VTC2021-Fall), IEEE, pp. 1-5.
View/Download from: Publisher's site
View description>>
Achieving better performance in high mobility scenarios has become an emerging topic for next generation wireless communications. Compared with traditional modulation techniques, the recently proposed orthogonal time frequency space (OTFS) shows outstanding performance over fast fading channels. In this paper, the OTFS system is first represented in the form of precoded orthogonal frequency division multiplexing (OFDM), enabling traditional estimation and equalization techniques to work under fast fading channels. Then, a novel frequency-domain pilot-aided channel estimation scheme is proposed to obtain the channel state information at the receiver. Simulation results show that the new channel estimation scheme works efficiently in different channel scenarios. Meanwhile, the overhead of the proposed scheme is also lower than those of the current popular schemes.
Zhang, L, Zhang, J, Shen, J, Xu, J, Li, Z & Yu, L 1970, 'Incorporating Multimodal Cues for Advertorial Discovery', 2021 IEEE International Conference on Multimedia and Expo (ICME), 2021 IEEE International Conference on Multimedia and Expo (ICME), IEEE, pp. 1-6.
View/Download from: Publisher's site
Zhang, Z, Jiang, S, Huang, C & Xu, RYD 1970, 'Resolution-Invariant Person Reid Based On Feature Transformation And Self-Weighted Attention', 2021 IEEE International Conference on Image Processing (ICIP), 2021 IEEE International Conference on Image Processing (ICIP), IEEE, pp. 1134-1138.
View/Download from: Publisher's site
Zhu, J, Li, X & Yang, Y 1970, 'Conductive and Dielectric Fully-Integrated 3D Printed Dual-Band Millimeter-Wave Fresnel Zone Plate Lens', 2021 International Symposium on Antennas and Propagation (ISAP), 2021 International Symposium on Antennas and Propagation (ISAP), IEEE, Taipei, Taiwan, pp. 1-2.
View/Download from: Publisher's site
View description>>
This conference paper presents a dual-band aperture-shared Fresnel zone plate (FZP)-based lens antenna for the V-band and D-band applications using conductive and dielectric fully-integrated 3D printing. In contrast to traditional full metal-based structures, double-screen grid structures are used to implement the concentric opaque rings of the FZP. Since the grids provide different transmission/reflection features at dual-band, they will not influence each other. A dielectric ring is directly printed atop the FZP for compensating for the phase-shifting from the grids. An antenna prototype is fabricated and measured. The radiation performance agrees well. The peak gains achieved are 20.3 dBi for the V-band and 21.9 dBi for the D-band, respectively.
Zhu, X, Ge, Z, Yang, L & Gomez-Garcia, R 1970, 'Millimeter-Wave CMOS Passive Filters for 5G Applications', 2021 IEEE MTT-S International Microwave Filter Workshop (IMFW), 2021 IEEE MTT-S International Microwave Filter Workshop (IMFW), IEEE, pp. 198-200.
View/Download from: Publisher's site