Publications

Adak, C, Chaudhuri, BB & Blumenstein, M 2021, 'A Deep Reinforcement Learning-based Study on Handwriting Difficulty Analysis' in Series on Language Processing, Pattern Recognition, and Intelligent Systems, WORLD SCIENTIFIC, pp. 97-117.
View/Download from: Publisher's site

Boroomandnia, A, Bozorg-Haddad, O, Pradhan, B & Datta, A 2021, 'GIS Application in Water Resource Management' in Springer Water, Springer Singapore, pp. 125-152.
View/Download from: Publisher's site

Meena, NK, Nimbalkar, S & Fatahi, B 2021, 'Finite Element Analysis of Soil Arching in Piled Embankment' in Challenges and Innovations in Geomechanics, Springer International Publishing, Switzerland, pp. 817-824.
View/Download from: Publisher's site
View description>>

Rigid piles are used to alleviate the detrimental characteristics of soft soil. Recently, the use of piled embankments has increased by many folds, as it facilitates rapid construction without compromising on serviceability. In the piled embankment, soil arching mechanism between adjacent piles improves the load-transfer to the piles and reduces the stress applied to the soft soil. In this study, a two-dimensional plane strain finite element model is adopted to investigate the mechanism of soil arching in a piled embankment. An idealized unit cell model is used to simulate the pile-supported embankment. The effect of different characteristics of piles and embankment soil are assessed. The outcome shows that friction angle, and embankment modulus significantly affects soil arching. Inconsistency among existing design approaches in the literature is highlighted.

Nguyen, TT & Indraratna, B 2021, 'Fluidization of Subgrade Soil Under Rail Tracks Through CFD-DEM Coupling' in Challenges and Innovations in Geomechanics, Springer International Publishing, Switzerland, pp. 274-281.
View/Download from: Publisher's site
View description>>

The increasing excess pore pressure under rail tracks especially in coastal soft soil regions has been indicated as one of the major reasons causing numerous track issues such as mud pumping. When the excess pore pressure develops to a certain degree, it causes considerable increase in hydraulic gradient associated with hydraulic forces over the soil depth that results in upward migration of fines, i.e., mud pumping followed by severe loss of soil mass and excessive deformation of soil matrix. This issue is simulated in this paper by using the computational fluid dynamics (CFD) coupled with the discrete element method (DEM). Subgrade soil is built in DEM with respect to realistic soil profiles while an increasing hydraulic gradient is generated to model upward fluid flows in CFD. The study indicates soil fluidization develops from localized scale via soil piping to overall scale where all particles become suspended and migrate upwards (i.e., heave formation). The overall fluidization results in a severe degradation in the contact network of soil particles (i.e., soil fabric) and effective stress. The study also shows reasonable predictions of the CFD-DEM coupling on the hydraulic response of subgrade soils.

Punetha, P & Nimbalkar, S 2021, 'Performance Improvement of Ballasted Railway Tracks for High-Speed Rail Operations' in Challenges and Innovations in Geomechanics, Springer International Publishing, pp. 841-849.
View/Download from: Publisher's site
View description>>

The high-speed rail (HSR) is one of the most significant technological advancements in the field of transportation, which is continuously gaining popularity worldwide. A major challenge to the development of HSR in any country is the selection of an appropriate railway track. Although ballastless/slab tracks are especially dedicated for the HSR operations, they have a few shortcomings such as, high initial construction costs, inability to align itself according to the ground movement, generation of higher levels of noise and vibration than the ballasted tracks. An alternative strategy is to strengthen the existing tracks to accommodate high-speed traffic. The present article investigates the adequacy of using geosynthetics and recycled concrete aggregates to improve the performance of the ballasted rail tracks for HSR operations. Two-dimensional finite element analysis is employed to examine the effectiveness of using geogrids, geocells, and recycled concrete aggregates in the ballasted railway tracks. The efficacy is evaluated in terms of the track settlement. The results indicate that the use of recycled aggregates and geosynthetics significantly reduce the track settlement and may permit a higher train speed for same allowable settlement. The maximum reduction in track settlement is observed with geocell reinforced capping followed by the capping layer composed of recycled aggregates and the geogrid reinforced capping. Thus, the present study shows that the geosynthetics and recycled concrete aggregates may offer cost-effective alternatives to improve the performance of ballasted railway tracks for high-speed rail operations.

Punetha, P & Nimbalkar, S 2021, 'Prediction of Extra Confinement Offered by Cellular Inclusion Under Three-Dimensional Stress State' in Challenges and Innovations in Geomechanics, Springer International Publishing, pp. 850-858.
View/Download from: Publisher's site

Shan, F, Teng, J, Yan, X, Zhang, S & Sheng, D 2021, 'Numerical Modeling of Water-Vapor Migration and Phase Transformation in Unsaturated Freezing Soils' in Challenges and Innovations in Geomechanics, Springer International Publishing, Switzerland, pp. 925-931.
View/Download from: Publisher's site
View description>>

Because of ignoring the vapor migration in freezing soils, coarse-grained soils have long been deemed not susceptible to frost heave. However, recent studies reveal that vapor migration can increase the total water content and lead to remarkable frost heave hazards in coarse-grained soils. In this paper, a new numerical model is developed based on the coupled thermal and hydrological processes. The soil water characteristic curve and the soil freezing characteristic curve are taken into account in this model. The model is established by using COMSOL Multiphysics which contains 5 equations and 5 variables. In order to validate the numerical model, laboratory experiments were performed in coarse-grained soils. The result shows that there are sharp increases in water content at the top of samples and the freezing front. A good match between measured and computed results indicates that the new model can make a good explanation for the coupled movement of heat and moisture in coarse-grained soils.

Abdollahi, A & Pradhan, B 2021, 'Integrated technique of segmentation and classification methods with connected components analysis for road extraction from orthophoto images', Expert Systems with Applications, vol. 176, pp. 114908-114908.
View/Download from: Publisher's site

Abdollahi, A & Pradhan, B 2021, 'Integrating semantic edges and segmentation information for building extraction from aerial images using UNet', Machine Learning with Applications, vol. 6, pp. 100194-100194.
View/Download from: Publisher's site

Abdollahi, A & Pradhan, B 2021, 'Urban Vegetation Mapping from Aerial Imagery Using Explainable AI (XAI)', Sensors, vol. 21, no. 14, pp. 4738-4738.
View/Download from: Publisher's site
View description>>

Urban vegetation mapping is critical in many applications, i.e., preserving biodiversity, maintaining ecological balance, and minimizing the urban heat island effect. It is still challenging to extract accurate vegetation covers from aerial imagery using traditional classification approaches, because urban vegetation categories have complex spatial structures and similar spectral properties. Deep neural networks (DNNs) have shown a significant improvement in remote sensing image classification outcomes during the last few years. These methods are promising in this domain, yet unreliable for various reasons, such as the use of irrelevant descriptor features in the building of the models and lack of quality in the labeled image. Explainable AI (XAI) can help us gain insight into these limits and, as a result, adjust the training dataset and model as needed. Thus, in this work, we explain how an explanation model called Shapley additive explanations (SHAP) can be utilized for interpreting the output of the DNN model that is designed for classifying vegetation covers. We want to not only produce high-quality vegetation maps, but also rank the input parameters and select appropriate features for classification. Therefore, we test our method on vegetation mapping from aerial imagery based on spectral and textural features. Texture features can help overcome the limitations of poor spectral resolution in aerial imagery for vegetation mapping. The model was capable of obtaining an overall accuracy (OA) of 94.44% for vegetation cover mapping. The conclusions derived from SHAP plots demonstrate the high contribution of features, such as Hue, Brightness, GLCM_Dissimilarity, GLCM_Homogeneity, and GLCM_Mean to the output of the proposed model for vegetation mapping. Therefore, the study indicates that existing vegetation mapping strategies based only on spectral characteristics are insufficient to appropriately classify vegetation covers.

Abdollahi, A, Pradhan, B & Alamri, A 2021, 'RoadVecNet: a new approach for simultaneous road network segmentation and vectorization from aerial and google earth imagery in a complex urban set-up', GIScience & Remote Sensing, vol. 58, no. 7, pp. 1151-1174.
View/Download from: Publisher's site

Abdollahi, A, Pradhan, B & Shukla, N 2021, 'Road Extraction from High-Resolution Orthophoto Images Using Convolutional Neural Network', Journal of the Indian Society of Remote Sensing, vol. 49, no. 3, pp. 569-583.
View/Download from: Publisher's site
View description>>

© 2020, Indian Society of Remote Sensing. Abstract: Two of the major applications in geospatial information system (GIS) and remote sensing fields are object detection and man-made feature extraction (e.g., road sections) from high-resolution remote sensing imagery. Extracting roads from high-resolution remotely sensed imagery plays a crucial role in multiple applications, such as navigation, emergency tasks, land cover change detection, and updating GIS maps. This study presents a deep learning technique based on a convolutional neural network (CNN) to classify and extract roads from orthophoto images. We applied the model on five orthophoto images to specify the superiority of the method for road extraction. First, we used principal component analysis and object-based image analysis for pre-processing to not only obtain spectral information but also add spatial and textural information for enhancing the classification accuracy. Then, the obtained results from the previous step were used as input for the CNN model to classify the images into road and non-road parts and trivial opening and closing operation are applied to extract connected road components from the images and remove holes inside the road parts. For the accuracy assessment of the proposed method, we used measurement factors such as precision, recall, F1 score, overall accuracy, and IOU. Achieved results showed that the average percentages of these factors were 91.09%, 95.32%, 93.15%, 94.44%, and 87.21%. The results were also compared with those of other existing methods. The comparison ascertained the reliability and superior performance of the suggested model architecture for extracting road regions from orthophoto images. Graphic Abstract: [Figure not available: see fulltext.]

Abdollahi, A, Pradhan, B, Sharma, G, Maulud, KNA & Alamri, A 2021, 'Improving Road Semantic Segmentation Using Generative Adversarial Network', IEEE Access, vol. 9, pp. 64381-64392.
View/Download from: Publisher's site

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.

Abeywickrama, A, Indraratna, B, Nguyen, TT & Rujikiatkamjorn, C 2021, 'LABORATORY INVESTIGATION ON THE USE OF VERTICAL DRAINS TO MITIGATE MUD PUMPING UNDER RAIL TRACKS', Australian Geomechanics Journal, vol. 56, no. 3, pp. 117-126.
View description>>

The build-up of excess pore water pressure (EPWP) in undrained soft subgrade under repeated rail loads is the key mechanism causing soil to fluidise, consequently yielding slurry tracks (i.e., mud pumping). This issue has substantially reduced transport efficiency associated with immense cost for track maintenance though considerable effort has been made over the past years. Therefore, this study is carried out to investigate how prefabricated vertical drains (PVDs) can be used to mitigate the accumulated EPWP and associated mud pumping. A series of cyclic triaxial tests including undrained (i.e., without PVDs) and PVD-assisted drained soils are conducted, and their results are compared to evaluate the effect of PVDs on cyclic soil behaviour. In this investigation, subgrade soil collected from a mud pumping site is used while loading parameters including the frequency, confining pressure and cyclic stress ratio (CSR) are considered with respect to heavy rail load condition in the field. The results show that PVDs can help dissipate effectively the accumulated EPWP, thus mitigating soil fluidisation. The current study shows that for undrained condition, lower frequency loading (i.e., slower trains) takes a smaller number of cycles to cause soil failure, whereas for drained cases (i.e., PVDs-assisted specimens), an opposite trend is observed. The study proves that installing PVDs into shallow layer (i.e., 3-5 m depth) is an effective approach to stabilise soft subgrade soil under rail tracks.

Abraham, MT, Satyam, N & Pradhan, B 2021, 'Forecasting Landslides Using Mobility Functions: A Case Study from Idukki District, India', Indian Geotechnical Journal, vol. 51, no. 4, pp. 684-693.
View/Download from: Publisher's site

Abraham, MT, Satyam, N, Jain, P, Pradhan, B & Alamri, A 2021, 'Effect of spatial resolution and data splitting on landslide susceptibility mapping using different machine learning algorithms', Geomatics, Natural Hazards and Risk, vol. 12, no. 1, pp. 3381-3408.
View/Download from: Publisher's site

Abraham, MT, Satyam, N, Lokesh, R, Pradhan, B & Alamri, A 2021, 'Factors Affecting Landslide Susceptibility Mapping: Assessing the Influence of Different Machine Learning Approaches, Sampling Strategies and Data Splitting', Land, vol. 10, no. 9, pp. 989-989.
View/Download from: Publisher's site
View description>>

Data driven methods are widely used for the development of Landslide Susceptibility Mapping (LSM). The results of these methods are sensitive to different factors, such as the quality of input data, choice of algorithm, sampling strategies, and data splitting ratios. In this study, five different Machine Learning (ML) algorithms are used for LSM for the Wayanad district in Kerala, India, using two different sampling strategies and nine different train to test ratios in cross validation. The results show that Random Forest (RF), K Nearest Neighbors (KNN), and Support Vector Machine (SVM) algorithms provide better results than Naïve Bayes (NB) and Logistic Regression (LR) for the study area. NB and LR algorithms are less sensitive to the sampling strategy and data splitting, while the performance of the other three algorithms is considerably influenced by the sampling strategy. From the results, both the choice of algorithm and sampling strategy are critical in obtaining the best suited landslide susceptibility map for a region. The accuracies of KNN, RF, and SVM algorithms have increased by 10.51%, 10.02%, and 4.98% with the use of polygon landslide inventory data, while for NB and LR algorithms, the performance was slightly reduced with the use of polygon data. Thus, the sampling strategy and data splitting ratio are less consequential with NB and algorithms, while more data points provide better results for KNN, RF, and SVM algorithms.

Abraham, MT, Satyam, N, Reddy, SKP & Pradhan, B 2021, 'Runout modeling and calibration of friction parameters of Kurichermala debris flow, India', Landslides, vol. 18, no. 2, pp. 737-754.
View/Download from: Publisher's site
View description>>

© 2020, Springer-Verlag GmbH Germany, part of Springer Nature. Debris flows account for a substantial economy and property loss in Western Ghats of Kerala, India, especially during monsoon seasons. Wayanad district is an active erosion zone in the plateau margins of Western Ghats, and there is a remarkable rise in the number of debris flows since 2018, due to very high-intensity rainfalls in this region. This study comprises geotechnical investigation, runout modeling, and calibration of friction parameters of Kurichermala debris flow, one of the devastating debris flow events that happened in Wayanad, during the 2018 monsoon. The detailed investigation and back analysis of such events are substantial in calibrating the flow parameters for the region. These parameters can be used for predicting the flow paths of possible debris flows and quantitative risk assessment in the future. The geotechnical investigation provided vital information regarding the soil type and shear strength parameters of the debris flow and has helped in understanding the flow behavior. A dynamic numerical model, rapid mass movements (RAMMS), was used for the back analysis of the debris flow, using the shape information of the flow. For precise calibration using statistical comparison, an image processing tool has been developed, to compare the structural similarity of simulated results with the original shape of debris flow. The dry-Coulomb friction coefficient (μ) was calibrated as 0.01 and turbulent friction coefficient (ξ) as 100 m/s2 for the event, using Voellmy-Salm rheology. The shape predicted by the model had a similarity index of 0.626 with the actual shape of debris flow. The results were found to be in accordance with the field and geotechnical observations. Hence, the results can be used to predict the shape of possible debris flows in the study area. The study is the first of its kind for the region and has significant influence in risk assessment for this highly susceptible l...

Abraham, MT, Satyam, N, Rosi, A, Pradhan, B & Segoni, S 2021, 'Usage of antecedent soil moisture for improving the performance of rainfall thresholds for landslide early warning', CATENA, vol. 200, pp. 105147-105147.
View/Download from: Publisher's site
View description>>

Landslides triggered by heavy rains are increasing in number and creating severe losses in hilly regions across the world. Rainfall thresholds on regional and local-scales are being used for forecasting such events, for efficient early warning. Empirical and probabilistic approaches for defining rainfall thresholds are traditional tools which are being used as part of the forecasting system for rainfall induced landslides. Such methods are easy-to-use and are based on statistical analyses. They can be derived without looking into the complex hydro-geological processes involved in slope failures, but are often associated with the disadvantage of higher false alarms, limiting their applications in a regional landslide early warning system (LEWS). This study is an attempt to improve the performance of conventional meteorological thresholds by considering the effect of soil moisture, using a probabilistic approach. Idukki district in southern part of India is highly susceptible to landslides and has witnessed major socio-economical setbacks in the recent disasters happened in 2018 and 2019. This tourist hub is now in need of a landslide forecasting system, which can help in landslide risk reduction. This study attempts to understand the effect of averaged soil moisture estimates derived from passive microwave remote sensing data, for improving the performance of conventional empirical and probabilistic thresholds. For defining empirical thresholds, an algorithm-based approach such as Calculation of Thresholds for Rainfall-induced Landslides Tool (CTRL-T) has been used. Probabilistic thresholds were defined using a Bayesian approach, finding the posterior probability of occurrence using the marginal and conditional probabilities of the control parameters along with the prior probability of occurrence of landslide. The derived rainfall thresholds were quantitatively compared with the Bayesian probabilistic threshold derived using rainfall severity and soil we...

Abraham, MT, Satyam, N, Shreyas, N, Pradhan, B, Segoni, S, Abdul Maulud, KN & Alamri, AM 2021, 'Forecasting landslides using SIGMA model: a case study from Idukki, India', Geomatics, Natural Hazards and Risk, vol. 12, no. 1, pp. 540-559.
View/Download from: Publisher's site

Aburas, MM, Ho, YM, Pradhan, B, Salleh, AH & Alazaiza, MYD 2021, 'Spatio-temporal simulation of future urban growth trends using an integrated CA-Markov model', Arabian Journal of Geosciences, vol. 14, no. 2.
View/Download from: Publisher's site

Abuzied, SM & Pradhan, B 2021, 'Hydro-geomorphic assessment of erosion intensity and sediment yield initiated debris-flow hazards at Wadi Dahab Watershed, Egypt', Georisk: Assessment and Management of Risk for Engineered Systems and Geohazards, vol. 15, no. 3, pp. 221-246.
View/Download from: Publisher's site
View description>>

© 2020, © 2020 Informa UK Limited, trading as Taylor & Francis Group. This study attempts to assess slope and channel erosion for modelling their implications on debris-flow occurrences in Wadi Dahab Watershed (WDW). Remote sensing and Geographic Information System (GIS) were integrated to appraise erosion rates from a hillslope and channel storage throughout WDW. A mass-wasting database was built initially for modelling hazard zones and validating the final map using a bivariate statistical analysis. An Erosion Hazard Model (EHM) was developed to evaluate the erosion intensity and sediment yield throughout WDW and to prognosticate the hazard zones due to debris-flows. The EHM was developed based on hydrological and geomorphic controls which are responsible for disintegrating bedrocks, delivering detritus downslopes, and accelerating debris through channels. Multi-source datasets, including topographic and geologic maps, climatic, satellite images, aerial photographs, and field-based datasets, were used to derive factors associated with the hydro-geomorphic processes. A spatial prediction of erosion intensity was obtained by the integration of both static and dynamic factors generated hazards in GIS platform. The erosion intensity map classifies WDW relatively to five intensity zones in which the most hazardous zones are distributed in steep sloping terrains and structurally controlled channels covered by metamorphic and clastic rocks. The erosion intensity map was correlated and tested against the debris-flows dataset which was not used during the spatial modelling process. The statistical correlation analysis has confirmed that the debris-flow locations increase exponentially in the high erosion intensity zones. The holistic integration approach provides the promising model for forecasting critical zones prone to erosion intensity and their associated hazards in WDW.

Ahmed, AA, Pradhan, B, Chakraborty, S & Alamri, A 2021, 'Developing vehicular traffic noise prediction model through ensemble machine learning algorithms with GIS', Arabian Journal of Geosciences, vol. 14, no. 16.
View/Download from: Publisher's site

Ahmed, AA, Pradhan, B, Chakraborty, S, Alamri, A & Lee, C-W 2021, 'An Optimized Deep Neural Network Approach for Vehicular Traffic Noise Trend Modeling', IEEE Access, vol. 9, pp. 107375-107386.
View/Download from: Publisher's site

Ahmed, N, Hoque, MA-A, Pradhan, B & Arabameri, A 2021, 'Spatio-Temporal Assessment of Groundwater Potential Zone in the Drought-Prone Area of Bangladesh Using GIS-Based Bivariate Models', Natural Resources Research, vol. 30, no. 5, pp. 3315-3337.
View/Download from: Publisher's site

Ahmed, N, Howlader, N, Hoque, MA-A & Pradhan, B 2021, 'Coastal erosion vulnerability assessment along the eastern coast of Bangladesh using geospatial techniques', Ocean & Coastal Management, vol. 199, pp. 105408-105408.
View/Download from: Publisher's site

Akbari, M, Meshram, SG, Krishna, RS, Pradhan, B, Shadeed, S, Khedher, KM, Sepehri, M, Ildoromi, AR, Alimerzaei, F & Darabi, F 2021, 'Identification of the Groundwater Potential Recharge Zones Using MCDM Models: Full Consistency Method (FUCOM), Best Worst Method (BWM) and Analytic Hierarchy Process (AHP)', Water Resources Management, vol. 35, no. 14, pp. 4727-4745.
View/Download from: Publisher's site

Al-Abadi, AM, Fryar, AE, Rasheed, AA & Pradhan, B 2021, 'Assessment of groundwater potential in terms of the availability and quality of the resource: a case study from Iraq', Environmental Earth Sciences, vol. 80, no. 12, pp. 1-22.
View/Download from: Publisher's site
View description>>

A semi-confined aquifer from Kirkuk Governorate, northern Iraq was taken as a case study to map groundwater potential in terms of both the availability and quality of the resource. In terms of quantity, five machine learning (ML) algorithms were used to model the relationship between locations of 1031 wells with specific-capacity data and nine influential groundwater occurrence factors. The algorithms used were linear discriminant analysis, classification and regression trees, linear vector quantization, random forest, and K-nearest neighbor. The groundwater occurrence factors used were elevation, slope, curvature, aspect, aquifer transmissivity, specific storage, soil, geology, and groundwater depth. Analysis of the worthiness of the factors used in the analysis by the information gain ratio indicated that five out of nine factors were worthy (average merit > 0): groundwater depth, elevation, transmissivity, specific storage, and soil. The remaining factors were non-worthy (average merit = 0) and thus they were removed from the analysis. The performance of the five ML algorithms was investigated using accuracy and kappa as evaluation metrics. Applying the models in the carte package of R software indicated that random forest was the best model. The probability values of this model were used for mapping quantitative groundwater potential after classification into three zones: poor, moderate, and excellent. Groundwater quality for drinking was modeled using the water quality index and the weights of the chemical constituents used (pH, TDS, Ca2+, Mg2+, Na+, SO42-, Cl -, and NO3-) were assigned using entropy information theory. A map of the groundwater quality index revealed five classes: < 50 (excellent), 50–100 (good), 100–150 (moderate), 150–200 (poor), and > 200 (extremely poor). Combining the groundwater quality index map with the groundwater potential map using summation operators revealed three zones of groundwater potential: poor, moderate, and exc...

Al-Bawi, AJ, Al-Abadi, AM, Pradhan, B & Alamri, AM 2021, 'Assessing gully erosion susceptibility using topographic derived attributes, multi-criteria decision-making, and machine learning classifiers', Geomatics, Natural Hazards and Risk, vol. 12, no. 1, pp. 3035-3062.
View/Download from: Publisher's site
View description>>

Gully erosion is an erosive process that contributes considerably to the shape of the earth’s surface and is a major contributor to land degradation and soil loss. This study applied a methodology for mapping gully erosion susceptibility using only topographic related attributes derived from a medium-resolution digital elevation model (DEM) and a hybrid analytical hierarchy process (AHP) and the technique for an order of preference by similarity to ideal solutions (TOPSIS) and compare the results with naïve Bayes (NB) and support vector machine learning (SVM) algorithms. A transboundary sub-basin in an arid area of southern Iraq was selected as a case study. The performance of the developed models was compared using the receiver operating characteristic curve (ROC). Results showed that the areas under the ROC were 0.933, 0.936, and 0.955 for AHP-TOPSIS, NB, and SVM with radial basis function, respectively, which indicated that the performance of simply derived AHP-TOPSIS model is similar to sophisticated NB and SVM models. Findings indicated that a medium resolution DEM and AHP-TOPSIS are a promising tool for mapping of gully erosion susceptibility.

Aldhshan, SRS, Abdul Maulud, KN, Wan Mohd Jaafar, WS, Karim, OA & Pradhan, B 2021, 'Energy Consumption and Spatial Assessment of Renewable Energy Penetration and Building Energy Efficiency in Malaysia: A Review', Sustainability, vol. 13, no. 16, pp. 9244-9244.
View/Download from: Publisher's site
View description>>

The development of sustainable energy systems is very important to addressing the economic, environmental, and social pressures of the energy sector. Globally, buildings consume up to 40% of the world’s total energy. By 2030, it is expected to increase to 50%. Therefore, the world is facing a great challenge to overcome these problems related to global energy production. Malaysia is one of the top consumers of primary energy in Asia. In 2018, primary energy consumption for Malaysia was 3.79 quadrillion btu at an average annual rate of 4.58%. In this paper, we have carried out a detailed literature review on several previous studies of energy consumption in the world, especially in Malaysia, and how geographical information system (GIS) methods have been used for the spatial assessment of energy efficiency. Indeed, strategies of energy efficiency are essential in energy policy that could be created using various approaches used for energy savings in buildings. The findings of this review reveal that, for estimating energy consumption, exploring renewable energy sources, and investigating solar radiation, several geographic information system techniques such as multiple criteria decision analysis (MCDA), machine learning (ML), and deep learning (DL) are mainly utilized. The result indicates that the fuzzy DS method can more reliably determine the optimal PV farm locations. The 3D models are also regarded as an effective tool for estimating solar radiation, since this method generates a 3D model exportable to software tools. In addition, GIS and 3D can contribute to several purposes, such as sunlight access to buildings in urban areas, city growth prediction models and analysis of the habitability of public places.

Alfouneh, M, Ji, J & Luo, Q 2021, 'Damping design of harmonically excited flexible structures with graded materials to minimize sound pressure and radiation', Engineering Optimization, vol. 53, no. 2, pp. 348-367.
View/Download from: Publisher's site
View description>>

© 2020, © 2020 Informa UK Limited, trading as Taylor & Francis Group. Topology optimization is an effective method in the design of acoustic media. This article presents optimization for graded damping materials to minimize sound pressure at a reference point or sound power radiation under harmonic excitation. The Helmholtz integral equation is used to calculate an acoustic field to satisfy the Sommerfeld conditions. The equation of motion is solved using a unit dynamic load method. Formulations for the sound pressure or sound power radiation in an integral form are derived in terms of mutual kinetic and strain energy densities. These integrals lead to novel physical response functions for solving the proposed optimization problem to design graded damping materials. The response function derived for individual frequency is utilized to solve the multi-objective optimization problem of minimizing sound pressure at the reference point for excitations with a range of frequencies. Numerical examples are presented to verify the efficiency of the present formulations.

Al-Fugara, A, Mabdeh, AN, Ahmadlou, M, Pourghasemi, HR, Al-Adamat, R, Pradhan, B & Al-Shabeeb, AR 2021, 'Wildland Fire Susceptibility Mapping Using Support Vector Regression and Adaptive Neuro-Fuzzy Inference System-Based Whale Optimization Algorithm and Simulated Annealing', ISPRS International Journal of Geo-Information, vol. 10, no. 6, pp. 382-382.
View/Download from: Publisher's site
View description>>

Fires are one of the most destructive forces in natural ecosystems. This study aims to develop and compare four hybrid models using two well-known machine learning models, support vector regression (SVR) and the adaptive neuro-fuzzy inference system (ANFIS), as well as two meta-heuristic models, the whale optimization algorithm (WOA) and simulated annealing (SA) to map wildland fires in Jerash Province, Jordan. For modeling, 109 fire locations were used along with 14 relevant factors, including elevation, slope, aspect, land use, normalized difference vegetation index (NDVI), rainfall, temperature, wind speed, solar radiation, soil texture, topographic wetness index (TWI), distance to drainage, and population density, as the variables affecting the fire occurrence. The area under the receiver operating characteristic (AUROC) was used to evaluate the accuracy of the models. The findings indicated that SVR-based hybrid models yielded a higher AUROC value (0.965 and 0.949) than the ANFIS-based hybrid models (0.904 and 0.894, respectively). Wildland fire susceptibility maps can play a major role in shaping firefighting tactics.

Alibeikloo, M, Khabbaz, H, Fatahi, B & Le, TM 2021, 'Reliability Assessment for Time-Dependent Behaviour of Soft Soils Considering Cross Correlation between Visco-Plastic Model Parameters', Reliability Engineering & System Safety, vol. 213, pp. 107680-107680.
View/Download from: Publisher's site
View description>>

An elastic visco-plastic creep model was combined with the Monte-Carlo probabilistic method incorporating multivariate copula and nonlinear analysis to investigate the effects of uncertainties in the elastic visco-plastic model parameters on time-dependent settlement and the distribution of excess pore water pressure in soft soils under applied loads. The elastic-plastic model parameter (λ/V) and creep coefficient (ψ0/V) were considered as random variables with lognormal distribution while considering the cross correlation between these two random variables. When λ/V and ψ0/V were used as random variables, the coefficient of variation of time-dependent deformation gradually decreased approximately 25% over time until reaching an asymptote. By adopting over 50 years of monitoring data from the case study of Väsby test fill and results from the settlement ratio, the most appropriate cross correlation coefficient between selected random variables was introduced. The results revealed that increasing the cross correlation coefficient between λ/V and ψ0/V increased the standard deviation and the coefficient of variation of settlement up to 40%. Meanwhile, the corresponding statistical features for the predicted excess pore water pressure decreased as the cross correlation coefficient increased. This study also provides a practical insight into selecting the most suitable cross correlation coefficient between elastic visco-plastic model parameters, while adopting reliability-based design approach that captures the time-dependent deformation of embankments and structures built on soft soils.

Al-Najjar, HAH & Pradhan, B 2021, 'Spatial landslide susceptibility assessment using machine learning techniques assisted by additional data created with generative adversarial networks', Geoscience Frontiers, vol. 12, no. 2, pp. 625-637.
View/Download from: Publisher's site
View description>>

In recent years, landslide susceptibility mapping has substantially improved with advances in machine learning. However, there are still challenges remain in landslide mapping due to the availability of limited inventory data. In this paper, a novel method that improves the performance of machine learning techniques is presented. The proposed method creates synthetic inventory data using Generative Adversarial Networks (GANs) for improving the prediction of landslides. In this research, landslide inventory data of 156 landslide locations were identified in Cameron Highlands, Malaysia, taken from previous projects the authors worked on. Elevation, slope, aspect, plan curvature, profile curvature, total curvature, lithology, land use and land cover (LULC), distance to the road, distance to the river, stream power index (SPI), sediment transport index (STI), terrain roughness index (TRI), topographic wetness index (TWI) and vegetation density are geo-environmental factors considered in this study based on suggestions from previous works on Cameron Highlands. To show the capability of GANs in improving landslide prediction models, this study tests the proposed GAN model with benchmark models namely Artificial Neural Network (ANN), Support Vector Machine (SVM), Decision Trees (DT), Random Forest (RF) and Bagging ensemble models with ANN and SVM models. These models were validated using the area under the receiver operating characteristic curve (AUROC). The DT, RF, SVM, ANN and Bagging ensemble could achieve the AUROC values of (0.90, 0.94, 0.86, 0.69 and 0.82) for the training; and the AUROC of (0.76, 0.81, 0.85, 0.72 and 0.75) for the test, subsequently. When using additional samples, the same models achieved the AUROC values of (0.92, 0.94, 0.88, 0.75 and 0.84) for the training and (0.78, 0.82, 0.82, 0.78 and 0.80) for the test, respectively. Using the additional samples improved the test accuracy of all the models except SVM. As a result, in data-scarce e...

Al-Najjar, HAH, Pradhan, B, Kalantar, B, Sameen, MI, Santosh, M & Alamri, A 2021, 'Landslide Susceptibility Modeling: An Integrated Novel Method Based on Machine Learning Feature Transformation', Remote Sensing, vol. 13, no. 16, pp. 3281-3281.
View/Download from: Publisher's site
View description>>

Landslide susceptibility modeling, an essential approach to mitigate natural disasters, has witnessed considerable improvement following advances in machine learning (ML) techniques. However, in most of the previous studies, the distribution of input data was assumed as being, and treated, as normal or Gaussian; this assumption is not always valid as ML is heavily dependent on the quality of the input data. Therefore, we examine the effectiveness of six feature transformations (minimax normalization (Std-X), logarithmic functions (Log-X), reciprocal function (Rec-X), power functions (Power-X), optimal features (Opt-X), and one-hot encoding (Ohe-X) over the 11conditioning factors (i.e., altitude, slope, aspect, curvature, distance to road, distance to lineament, distance to stream, terrain roughness index (TRI), normalized difference vegetation index (NDVI), land use, and vegetation density). We selected the frequent landslide-prone area in the Cameron Highlands in Malaysia as a case study to test this novel approach. These transformations were then assessed by three benchmark ML methods, namely extreme gradient boosting (XGB), logistic regression (LR), and artificial neural networks (ANN). The 10-fold cross-validation method was used for model evaluations. Our results suggest that using Ohe-X transformation over the ANN model considerably improved performance from 52.244 to 89.398 (37.154% improvement).

Alqaisi, R, Le, TM & Khabbaz, H 2021, 'Combined effects of eggshell powder and hydrated lime on the properties of expansive soils', Australian Geomechanics Journal, vol. 56, no. 1, pp. 107-118.
View description>>

This study involves the utilization of eggshell powder (ESP) as a supplementary additive to lime stabilization of expansive soil and evaluates its potential in enhancing the performance of expansive soil treated with lime. Eggshell is a waste material obtained from several sources. Some of the challenges associated with dumping eggshell are odour, insect growth, disposal costs and availability of disposal sites. In order to reduce these environmental issues, eggshells can be processed into ESP and play a role as a soil stabilizing agent. Calcium oxide is considered to be the main ingredient of the ESP. Therefore, an experimental program is carried out to test a mixture of kaolinite, bentonite and Sydney fine sand, which is simulated to be as an artificial expansive soil. The eggshell powder was used as an additive to 5% lime in four percentages of 5%, 10%, 15% and 20% by total dry weight of the soil mass. Results of linear shrinkage, proctor compaction, and unconfined compressive strength tests after various curing time are presented in detail and compared with untreated soil samples. The outcomes of these experimental investigations indicated that the combination of eggshell powder and hydrated lime led to a further decrease in linear shrinkage and the maximum dry density of expansive soil samples. It was found that the improved geotechnical characteristics were more pronounced for 5% ESP treated expansive soil. At this percentage, the compressive strength at failure and the corresponding strain increased slightly by 18% and 9%, respectively, compared to the untreated expansive soil after 28 days of curing. Moreover, in comparison with lime (5%) only stabilized expansive soil, the combined lime (5%) and ESP (5%), induced approximately 15% build-up in the compressive strength of samples. Based on the reasonable laboratory test results, this addition is recommended to improve the shrinkage properties and stabilize the expansive soils where the high perfo...

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.

Arabameri, A, Chandra Pal, S, Costache, R, Saha, A, Rezaie, F, Seyed Danesh, A, Pradhan, B, Lee, S & Hoang, N-D 2021, 'Prediction of gully erosion susceptibility mapping using novel ensemble machine learning algorithms', Geomatics, Natural Hazards and Risk, vol. 12, no. 1, pp. 469-498.
View/Download from: Publisher's site
View description>>

Spatial modelling of gully erosion at regional level is very relevant for local authorities to establish successful counter-measures and to change land-use planning. This work is exploring and researching the potential of a genetic algorithm-extreme gradient boosting (GE-XGBoost) hybrid computer education solution for spatial mapping of the susceptibility of gully erosion. The new machine learning approach is to combine the extreme gradient boosting machine (XGBoost) and the genetic algorithm (GA). The GA metaheuristic is being used to improve the efficiency of the XGBoost classification approach. A GIS database has been developed that contains recorded instances of gully erosion incidents and 18 conditioning variables. These parameters are used as predictive variables used to assess the condition of non-erosion or erosion in a given region within the Kohpayeh-Sagzi River Watershed research area in Iran. Exploratory results indicate that the proposed GE-XGBoost model is superior to the other benchmark solution with the desired predictive precision (89.56%). Therefore, the newly built model may be a promising method for large-scale mapping of gully erosion susceptibility.

Arivalagan, J, Rujikiatkamjorn, C, Indraratna, B & Warwick, A 2021, 'The role of geosynthetics in reducing the fluidisation potential of soft subgrade under cyclic loading', Geotextiles and Geomembranes, vol. 49, no. 5, pp. 1324-1338.
View/Download from: Publisher's site
View description>>

The instability of railway tracks including mud pumping, ballast degradation, and differential settlement on weak subgrade soils occurs due to cyclic stress from heavy haul trains. Although geotextiles are currently being used as a separator in railway and highway embankments, their ability to prevent the migration of fine particles and reduce cyclic pore pressure has to be investigated under adverse hydraulic conditions to prevent substructure failures. This study primarily focuses on using geosynthetics to mitigate the migration of fine particles and the accumulation of excess pore pressure (EPP) due to mud pumping (subgrade fluidisation) using dynamic filtration apparatus. The role that geosynthetics play in controlling and preventing mud pumping is analysed by assessing the development of EPP, the change in particle size distribution and the water content of subgrade soil. Using 3 types of geotextiles, the potential for fluidisation is assessed by analysing the time-dependent excess pore pressure gradient (EPPG) inside the subgrade. The experimental results are then used to evaluate the performance of selected geotextiles under heavy haul loading.

Azeez, OS, Pradhan, B & Jena, R 2021, 'Urban tree classification using discrete-return LiDAR and an object-level local binary pattern algorithm', Geocarto International, vol. 36, no. 16, pp. 1785-1803.
View/Download from: Publisher's site
View description>>

Urban trees have the potential to mitigate some of the harm brought about by rapid urbanization and population growth, as well as serious environmental degradation (e.g. soil erosion, carbon pollution and species extirpation), in cities. This paper presents a novel urban tree extraction modelling approach that uses discrete laser scanning point clouds and object-based textural analysis to (1) develop a model characterised by four sub-models, including (a) height-based split segmentation, (b) feature extraction, (c) texture analysis and (d) classification, and (2) apply this model to classify urban trees. The canopy height model is integrated with the object-level local binary pattern algorithm (LBP) to achieve high classification accuracy. The results of each sub-model reveal that the classification of urban trees based on the height at 47.14 (high) and 2.12 m (low), respectively, while based on crown widths were highest and lowest at 22.5 and 2.55 m, respectively. Results also indicate that the proposed algorithm of urban tree modelling is effective for practical use.

Balogun, A-L, Yekeen, ST, Pradhan, B & Wan Yusof, KB 2021, 'Oil spill trajectory modelling and environmental vulnerability mapping using GNOME model and GIS', Environmental Pollution, vol. 268, no. Pt A, pp. 115812-115812.
View/Download from: Publisher's site
View description>>

This study develops an oil spill environmental vulnerability model for predicting and mapping the oil slick trajectory pattern in Kota Tinggi, Malaysia. The impact of seasonal variations on the vulnerability of the coastal resources to oil spill was modelled by estimating the quantity of coastal resources affected across three climatic seasons (northeast monsoon, southwest monsoon and pre-monsoon). Twelve 100 m³ (10,000 splots) medium oil spill scenarios were simulated using General National Oceanic and Atmospheric Administration Operational Oil Modeling Environment (GNOME) model. The output was integrated with coastal resources, comprising biological, socio-economic and physical shoreline features. Results revealed that the speed of an oil slick (40.8 m per minute) is higher during the pre-monsoon period in a southwestern direction and lower during the northeast monsoon (36.9 m per minute). Evaporation, floating and spreading are the major weathering processes identified in this study, with approximately 70% of the slick reaching the shoreline or remaining in the water column during the first 24 h (h) of the spill. Oil spill impacts were most severe during the southwest monsoon, and physical shoreline resources are the most vulnerable to oil spill in the study area. The study concluded that variation in climatic seasons significantly influence the vulnerability of coastal resources to marine oil spill.

Baral, P, Indraratna, B, Rujikiatkamjorn, C, Kelly, R & Vincent, P 2021, 'Consolidation by Vertical Drains beneath a Circular Embankment under Surcharge and Vacuum Preloading', Journal of Geotechnical and Geoenvironmental Engineering, vol. 147, no. 8, pp. 05021004-05021004.
View/Download from: Publisher's site
View description>>

A membrane-type vacuum consolidation system, including surcharge loading and prefabricated vertical drains, was applied to rapidly consolidate soft clay beneath a circular embankment located at the National Field Testing Facility (NFTF) at Ballina, New South Wales (NSW), Australia. Most previous studies were devoted to multidrain systems corresponding to an embankment strip loading in two-dimensional (2D) plane strain. So far, no case study has been investigated using vacuum consolidation via prefabricated vertical drains (PVDs) beneath a circular loaded area, where the system conforms to an axisymmetric problem. This paper outlines the site investigation, construction technique, and installation of a suite of instrumentation on this circular embankment. It also describes and discusses consolidation during and after the construction of this embankment in terms of settlement, excess pore water pressure, lateral deformation, and water flow relationships as they pertain to prediction embankment with vertical drains and surcharge only. The case study demonstrates that a loss of vacuum pressure can be prevented using the proposed approach in a membrane system. Treatment of water extracted using the vacuum consolidation technique, especially in acid-sulfate terrain, is also presented.

Baral, P, Rujikiatkamjorn, C, Indraratna, B, Leroueil, S & Yin, J-H 2021, 'Closure to “Radial Consolidation Analysis Using Delayed Consolidation Approach” by Pankaj Baral, Cholachat Rujikiatkamjorn, Buddhima Indraratna, Serge Leroueil, and Jian-Hua Yin', Journal of Geotechnical and Geoenvironmental Engineering, vol. 147, no. 1, pp. 07020025-07020025.
View/Download from: Publisher's site

Barbieri, DM, Lou, B, Passavanti, M, Hui, C, Hoff, I, Lessa, DA, Sikka, G, Chang, K, Gupta, A, Fang, K, Banerjee, A, Maharaj, B, Lam, L, Ghasemi, N, Naik, B, Wang, F, Foroutan Mirhosseini, A, Naseri, S, Liu, Z, Qiao, Y, Tucker, A, Wijayaratna, K, Peprah, P, Adomako, S, Yu, L, Goswami, S, Chen, H, Shu, B, Hessami, A, Abbas, M, Agarwal, N & Rashidi, TH 2021, 'Impact of COVID-19 pandemic on mobility in ten countries and associated perceived risk for all transport modes', PLOS ONE, vol. 16, no. 2, pp. e0245886-e0245886.
View/Download from: Publisher's site
View description>>

The restrictive measures implemented in response to the COVID-19 pandemic have triggered sudden massive changes to travel behaviors of people all around the world. This study examines the individual mobility patterns for all transport modes (walk, bicycle, motorcycle, car driven alone, car driven in company, bus, subway, tram, train, airplane) before and during the restrictions adopted in ten countries on six continents: Australia, Brazil, China, Ghana, India, Iran, Italy, Norway, South Africa and the United States. This cross-country study also aims at understanding the predictors of protective behaviors related to the transport sector and COVID-19. Findings hinge upon an online survey conducted in May 2020 (N = 9,394). The empirical results quantify tremendous disruptions for both commuting and non-commuting travels, highlighting substantial reductions in the frequency of all types of trips and use of all modes. In terms of potential virus spread, airplanes and buses are perceived to be the riskiest transport modes, while avoidance of public transport is consistently found across the countries. According to the Protection Motivation Theory, the study sheds new light on the fact that two indicators, namely income inequality, expressed as Gini index, and the reported number of deaths due to COVID-19 per 100,000 inhabitants, aggravate respondents’ perceptions. This research indicates that socio-economic inequality and morbidity are not only related to actual health risks, as well documented in the relevant literature, but also to the perceived risks. These findings document the global impact of the COVID-19 crisis as well as provide guidance for transportation practitioners in developing future strategies.

Basack, S, Goswami, G & Nimbalkar, S 2021, 'Analytical and Numerical Solutions to Selected Research Problems in Geomechanics and Geohydraulics', WSEAS TRANSACTIONS ON APPLIED AND THEORETICAL MECHANICS, vol. 16, pp. 222-231.
View/Download from: Publisher's site
View description>>

Geomechanical and geohydraulic engineering is a promising study area with several emerging research concerns. Most of such problems requires advanced level of mathematics to arrive at specific solutions. A wide range of approaches includes several analytical and numerical techniques for better understanding of such problems. In this paper, a few selected research problems are identified, and their solution techniques are demonstrated. The specific areas relevant to such problems are soil-structure interaction, ground improvement and groundwater hydraulics. This paper presents the problem identification, their mathematical solutions and results as well as pertinent analyses and useful interpretations to practice.

Basaglia, BM, Li, J, Shrestha, R & Crews, K 2021, 'Response Prediction to Walking-Induced Vibrations of a Long-Span Timber Floor', Journal of Structural Engineering, vol. 147, no. 2, pp. 1-15.
View/Download from: Publisher's site
View description>>

Long-span timber floors are susceptible to annoying floor vibrations caused by human activities, which, in many cases, govern the timber floor design. Consequently, a reliable prediction of floor vibration responses under human activities, which relies on appropriate walking load models, can be crucial in the design to keep timber floors remaining competitive in the commercial building market. Much of the current design guidance for timber floor vibrations have been established from short-span floors in a residential context, and as a result, many designers refer to established design methods formulated for use with concrete and steel-framed buildings. These guidelines predict the floor response based on a deterministic single-person walking load model that differs depending on the classification of the floor as either a high- or low-frequency floor, which are assumed as a transient or resonant floor response, respectively. Recent advances in modeling human walking have been made, including a single footfall trace load that avoids the need to classify the floor, as well as load models that incorporate a probabilistic approach. To date, an investigation on different walking load models to predict the vibration response of long-span timber floors has not been undertaken, partially due to the fact that there are limited examples in practice. This paper presents the results of a recently completed state-of-the-art research project involving full-scale testing of long-span timber floors and the development of novel numerical models to investigate the applicability of the deterministic walking load model used in current floor vibration design guides, as well as two innovative single-person walking load models for predicting the floor responses of a single long-span timber cassette floor. The numerical investigation was carried out with a finite-element model calibrated with experimentally obtained modal properties. The comparison between the predicted respons...

Bayazidy-Hasanabad, M, Vayghan, SS, Ghasemkhani, N, Pradhan, B & Alamri, A 2021, 'Developing a volunteered geographic information-based system for rapidly estimating damage from natural disasters', Arabian Journal of Geosciences, vol. 14, no. 17.
View/Download from: Publisher's site

Bulzinetti, MA, Abraham, MT, Satyam, N, Pradhan, B & Segoni, S 2021, 'Combining rainfall thresholds and field monitoring data for development of LEWS.'.
View/Download from: Publisher's site
View description>>

&lt;p&gt;Landslide Early Warning Systems (LEWS) can provide enough time to take necessary precautions before the occurrence of landslides and can reduce the risk associated with it. Deriving empirical rainfall thresholds is the conventional approach in developing regional scale LEWS, but the major drawback of this approach is the relatively high number of false alarms. In this study, a prototype method for LEWS is proposed by combining rainfall thresholds and field monitoring data from MicroElectroMechanical Systems (MEMS) units that integrate a tilt sensor, a soil moisture meter and a real-time wireless transmitter. The study was conducted in the Kalimpong district of West Bengal, India. Tilt sensors were installed at different locations on unstable slopes of Kalimpong since July 2017 and the observations from July 2017 to August 2020 were used to enhance the performance of the existing rainfall thresholds.&lt;/p&gt;&lt;p&gt;During this period, both rainfall thresholds and tilt meters, when used separately, systematically overestimated landslide hazard, producing high false alarm rates. However, it was found that using a decisional algorithm that combines both approaches can reduce the false alarms and improve the overall efficiency of the system from 84 % (based on rainfall thresholds) to 92 % (combined method). The prototype LEWS is found to be promising to be developed as an operational LEWS capable to issue alerts with a lead time of 24 h.&amp;#160;&lt;/p&gt;&lt;p&gt;The method is simple and can be easy exported to other sites with historical rainfall and landslide data and a network of slope monitoring sensors. Cost of installation of a large number of sensors is a major concern for developing countries like India, hence a cost-effective approach is used in this study: the use of MEMS sensors along with empirical rainfall thresholds is thus a simple and economical approach for the prediction of l...

Cao, D-F, Zhu, H-H, Guo, C-C, Wu, J-H & Fatahi, B 2021, 'Investigating the hydro-mechanical properties of calcareous sand foundations using distributed fiber optic sensing', Engineering Geology, vol. 295, pp. 106440-106440.
View/Download from: Publisher's site

Chen, J, Indraratna, B, Vinod, JS, Ngo, NT, Gao, R & Liu, Y 2021, 'Stress-dilatancy behaviour of fouled ballast: experiments and DEM modelling', Granular Matter, vol. 23, no. 4.
View/Download from: Publisher's site
View description>>

This paper presents a study of the mechanical behaviour of ballast contaminated by different fouling agents such as coal and subgrade clay. Large-scale direct shear tests were carried out to examine the strength and deformation properties for coal-fouled and clay-fouled ballast. The experimental results show that fouled ballast (both clay and coal) exhibits a lower peak shear strength and decreased dilation during shearing. The clay-fouled ballast shows higher shear strength and smaller dilation compared to coal-fouled ballast. The relationship between shear stress and dilatancy of ballast under different fouling conditions is reported in this paper, where the numerical predictions are made using the discrete element method (DEM). The DEM simulations show that with the increase of fouling level, the coordination number, the average contact force, the particle rotation and the velocity decrease for ballast aggregates. The results indicate that coal-fouled ballast exhibits a smaller average contact forces with less stress concentrations, less major principal stress orientation and a greater coordination number, leading to less particle rotation and velocity compared to those of clay-fouled ballast for the same degree of fouling. Graphic abstract: [Figure not available: see fulltext.]

Chen, J, Wu, D, Zhao, Y, Sharma, N, Blumenstein, M & Yu, S 2021, 'Fooling intrusion detection systems using adversarially autoencoder', Digital Communications and Networks, vol. 7, no. 3, pp. 453-460.
View/Download from: Publisher's site
View description>>

Due to the increasing cyber-attacks, various Intrusion Detection Systems (IDSs) have been proposed to identify network anomalies. Most existing machine learning-based IDSs learn patterns from the features extracted from network traffic flows, and the deep learning-based approaches can learn data distribution features from the raw data to differentiate normal and anomalous network flows. Although having been used in the real world widely, the above methods are vulnerable to some types of attacks. In this paper, we propose a novel attack framework, Anti-Intrusion Detection AutoEncoder (AIDAE), to generate features to disable the IDS. In the proposed framework, an encoder transforms features into a latent space, and multiple decoders reconstruct the continuous and discrete features, respectively. Additionally, a generative adversarial network is used to learn the flexible prior distribution of the latent space. The correlation between continuous and discrete features can be kept by using the proposed training scheme. Experiments conducted on NSL-KDD, UNSW-NB15, and CICIDS2017 datasets show that the generated features indeed degrade the detection performance of existing IDSs dramatically.

Chen, Q, Peng, W, Yu, R, Tao, G & Nimbalkar, S 2021, 'Laboratory Investigation on Particle Breakage Characteristics of Calcareous Sands', Advances in Civil Engineering, vol. 2021, pp. 1-8.
View/Download from: Publisher's site
View description>>

Many studies have demonstrated the fragility of calcareous sands even under small stresses. This bears an adverse influence on their engineering properties. A series of laboratory tests were carried out on poor-graded calcareous sands to investigate the crushability mechanism. Einav’s relative breakage and fractal dimension were used as the particle breakage indices. The results show that the particles broke into smaller fragments at the low-stress level by attrition which was caused by friction and slip between particles. In contrast, particles broke in the form of crushing at the relatively higher stresses. The evolution of the particle size was reflected by the variation in Einav’s relative breakage and fractal dimension. As testing commenced, the breakage index rapidly increased. When the stress was increased to 400 kPa, the rate of increase in the breakage index was retarded. As the stress was further increased beyond 800 kPa, the rate of increase in the fractal index became much smaller. This elucidated that the well-graded calcareous sands could resist crushing depending on the range of applied stresses. Based on the test findings, a new breakage law is proposed.

Chen, Q, Yu, R, Li, Y, Tao, G & Nimbalkar, S 2021, 'Cyclic stress-strain characteristics of calcareous sand improved by polyurethane foam adhesive', Transportation Geotechnics, vol. 31, pp. 100640-100640.
View/Download from: Publisher's site

Chen, Q, Yu, R, Tao, G, Zhang, J & Nimbalkar, S 2021, 'Shear behavior of polyurethane foam adhesive improved calcareous sand under large-scale triaxial test', Marine Georesources & Geotechnology, vol. 39, no. 12, pp. 1449-1458.
View/Download from: Publisher's site

Chen, Q-S, Peng, W, Tao, G-L & Nimbalkar, S 2021, 'Strength and Deformation Characteristics of Calcareous Sands Improved by PFA', KSCE Journal of Civil Engineering, vol. 25, no. 1, pp. 60-69.
View/Download from: Publisher's site
View description>>

© 2020, Korean Society of Civil Engineers. Calcareous sand is widely distributed in the islands of the South China Sea, which could be promisingly used as the construction materials. However, particle breakage commonly occurs in calcareous sands, which may significantly influence their mechanical characteristics. To address these issues, an eco-friendly agent, i.e., polyurethane foam adhesive (PFA) is proposed to improve the engineering properties of calcareous sands, compared to the commonly used alkaline stabilizing agents (e.g., lime, cement). The objective of this work is to examine the effectiveness of using PFA in improving the strength-deformation properties of calcareous sand. A series of laboratory tests including direct shear tests, unconfined compression tests, and oedometer tests were performed on the calcareous sands improved by PFA. In addition, A scanning electron microscope (SEM) was conducted to reveal microstructural analysis of using PFA for calcareous sand. The experimental results provided insights into the shear strength, deformation modulus, as well as the micro-structural characteristics of improved calcareous sands with various PFA contents and particle size distributions.

Chiang, YK, Quan, L, Peng, Y, Sepehrirahnama, S, Oberst, S, Alù, A & Powell, DA 2021, 'Scalable Metagrating for Efficient Ultrasonic Focusing', Physical Review Applied, vol. 16, no. 6, pp. 1-9.
View/Download from: Publisher's site
View description>>

Acoustic metalenses have been pursued over the past decades due to their pivotal role in a wide variety of applications. Recent research efforts have demonstrated that, at ultrasonic regimes, acoustic levitation can be realized with standing waves, which are created by the interference between incoming and reflected focused waves. However, the conventional gradient-metasurface approach to focus ultrasonic waves is complex, leading to poor scalability. In this work, we propose a design principle for ultrasonic metalenses, based on metagratings - arrays of discrete scatters with coarser features than gradient metasurfaces. We achieve beam focusing by locally controlling the excitation of a single diffraction order with the use of metagratings, with geometry adiabatically varying over the lens aperture. We show that our metalens can effectively focus impinging ultrasonic waves to a focal point with a full width at half maximum of 0.364 of the wavelength. The focusing performance of the metalens is demonstrated experimentally, validating our proposed approach. This metagrating approach to focusing can be adopted for different operating frequencies by scaling the size of the structure, which has coarse features suitable for high-frequency designs, with potential applications ranging from biomedical science to nondestructive testing.

Cullen, M, Zhao, S, Ji, J & Qiu, X 2021, 'Classification of transfer modes in gas metal arc welding using acoustic signal analysis', The International Journal of Advanced Manufacturing Technology, vol. 115, no. 9-10, pp. 3089-3104.
View/Download from: Publisher's site
View description>>

Gas metal arc welding (GMAW) is a welding process in which an electric arc is formed between a wire electrode and a metal workpiece alongside a shielding gas to protect the arc from contaminants. There are several ways in which the molten electrode droplet can be transferred to the weld pool known as metal transfer modes. Identifying the metal transfer mode automatically is essential to monitor and control the welding process, especially in automated processes employed in modern Industry 4.0 manufacturing lines. However, limited research on this topic has been found in literature. This paper explores the automatic classification of metal transfer modes in GMAW based on machine learning techniques with various signals from the welding process, including acoustics, current, voltage and gas flow rate signals. Time and frequency domain features are first extracted from these signals and are used in a support vector machine classifier to detect the metal transfer modes. A feature selection algorithm is proposed to improve the prediction rate from 80 to 99% when all four signals are utilised. When only the non-intrusive acoustic signal is used, the prediction rates with and without the proposed feature selection algorithm are approximately 96% and 81%, respectively. The high prediction rate demonstrates the feasibility and promising accuracy of the acoustic signal–based classification method for future smart welding technology with real-time adaptive feedback control of the welding process.

Dabbaghi, F, Dehestani, M, Yousefpour, H, Rasekh, H & Navaratnam, S 2021, 'Residual compressive stress–strain relationship of lightweight aggregate concrete after exposure to elevated temperatures', Construction and Building Materials, vol. 298, pp. 123890-123890.
View/Download from: Publisher's site

Dang, CC, Dang, LC, Khabbaz, H & Sheng, D 2021, 'Numerical study on deformation characteristics of fibre-reinforced load-transfer platform and columns-supported embankments', Canadian Geotechnical Journal, vol. 58, no. 3, pp. 328-350.
View/Download from: Publisher's site
View description>>

In this investigation, a ground-modification technique utilising a fibre-reinforced load-transfer platform (FRLTP) and columns-supported (CS) embankment constructed on multi-layered soft soils is proposed and investigated. After validating the proposed model with published data in the literature, numerical analysis was firstly conducted on the two-dimensional finite element model of a CS embankment without or with FRLTP to examine the influence of the FRLTP inclusion into the CS embankment system. Secondly, an extensive parametric study was performed to further investigate the effects of the FRLTP essential parameters — including platform thickness, shear strength, and tensile strength properties — and deformation modulus on the embankment performance during the construction and post-construction stages. Additionally, the influence of the embankment design parameters, such as column spacing, column length, and diameter, was examined. The numerical results reveal that the FRLTP inclusion can be effective in enhancing the CS embankment behaviour. It is also found that when increasing the platform thickness, the shear strength properties of FRLTP play a significant role in improving the overall performance of a column embankment with FRLTP.

Dang, LC, Khabbaz, H & Ni, B-J 2021, 'Improving engineering characteristics of expansive soils using industry waste as a sustainable application for reuse of bagasse ash', Transportation Geotechnics, vol. 31, pp. 100637-100637.
View/Download from: Publisher's site
View description>>

Bagasse ash (BA) is an abundant industrial waste of the sugar-cane refining industry, and its improper disposal can result in a detrimental impact on the environment. In this investigation, BA is considered to assess the possible advantages of its pozzolanic component as a novel sustainable waste application for stabilisation of expansive soils. The engineering characteristics of expansive soils were investigated through an array of laboratory experiments on treated and untreated soil specimens mixed with various contents of additive and cured for different times. A comprehensive investigation of the microstructure evolution of soils after treatment was also undertaken using Fourier transform infrared and scanning electron microscopy techniques. The results revealed that addition of BA, lime, and in particular, combined BA-lime (BAL) remarkably improved the maximum strength (815%), the bearing capacity (9.2 times), the compressibility (83%), and the 100% swell properties of stabilised soils due to rich amorphous silica properties of BA waste that promoted higher pozzolanic reactivities of BAL-soil-mixtures and therefore, enhanced the engineering characteristics of treated soils. The findings showed that a proper combination of bagasse ash waste and lime, as a stabilising additive, can effectively enhance the engineering properties of expansive soil while addressing the environmental impact of BA waste disposal. The industrial waste (BA) can be reused as a cost-effective and green construction material for the benefit of sustainable development of civil infrastructure.

Dansana, D, Kumar, R, Parida, A, Sharma, R, Das Adhikari, J, Van Le, H, Thai Pham, B, Kant Singh, K & Pradhan, B 2021, 'Using Susceptible-Exposed-Infectious-Recovered Model to Forecast Coronavirus Outbreak', Computers, Materials & Continua, vol. 67, no. 2, pp. 1595-1612.
View/Download from: Publisher's site

Darabi, H, Torabi Haghighi, A, Rahmati, O, Jalali Shahrood, A, Rouzbeh, S, Pradhan, B & Tien Bui, D 2021, 'A hybridized model based on neural network and swarm intelligence-grey wolf algorithm for spatial prediction of urban flood-inundation', Journal of Hydrology, vol. 603, pp. 126854-126854.
View/Download from: Publisher's site
View description>>

In regions with lack of hydrological and hydraulic data, a spatial flood modeling and mapping is an opportunity for the urban authorities to predict the spatial distribution and the intensity of the flooding. It helps decision-makers to develop effective flood prevention and management plans. In this study, flood inventory data were prepared based on the historical and field surveys data by Sari municipality and regional water company of Mazandaran, Iran. The collected flood data accompanied with different variables (digital elevation model and slope have been considered as topographic variables, land use/land cover, precipitation, curve number, distance to river, distance to channel and depth to groundwater as environmental variables) were applied to novel hybridized model based on neural network and swarm intelligence-grey wolf algorithm (NN-SGW) to map flood-inundation. Several confusion matrix criteria were used for accuracy evaluation by cutoff-dependent and independent metrics (e.g., efficiency (E), positive predictive value (PPV), negative predictive value (NPV), area under the receiver operating characteristic curve (AUC)). The accuracy of the flood inundation map produced by the NN-SGW model was compared with that of maps produced by four state-of-the-art benchmark models: random forest (RF), logistic model tree (LMT), classification and regression trees (CART), and J48 decision tree (J48DT). The NN-SGW model outperformed all benchmark models in both training (E = 90.5%, PPV = 93.7%, NPV = 87.3%, AUC = 96.3%) and validation (E = 79.4%, PPV = 85.3%, NPV = 73.5%, AUC = 88.2%). As the NN-SGW model produced the most accurate flood-inundation map, it can be employed for robust flood contingency planning. Based on the obtained results from NN-SGW model, distance from channel, distance from river, and depth to groundwater were identified as the most important variables for spatial prediction of urban flood inundation. This work can serve as a basis fo...

Daviran, M, Maghsoudi, A, Ghezelbash, R & Pradhan, B 2021, 'A new strategy for spatial predictive mapping of mineral prospectivity: Automated hyperparameter tuning of random forest approach', Computers & Geosciences, vol. 148, pp. 104688-104688.
View/Download from: Publisher's site
View description>>

Machine learning algorithms (e.g., random forest (RF)) have recently been performed in data-driven mineral prospectivity mapping. These methods are highly sensitive to hyperparameter values, since the predictive accuracy of them can significantly increase when the optimized hyperparameters are predefined and then adjusted to training procedure. The main goal of this contribution is to propose a hybrid genetic-based RF model, namely GRF, which is able to automatically adjust the optimized hyperparameters of RF with the excellent predictive accuracy. Therefore, three primary parameters of RF comprising N , N and d, were well-tuned employing genetic algorithm (GA) in establishing an efficient RF model. The proposed GRF model and also conventional RF were tested on mineralization-related geo-spatial dataset and the predictive models were generated for comparing the accuracy of the proposed GRF model with that of RF. The input dataset (e.g., multi-element geochemical signature, geological-structural layer and hydrothermal alteration evidences) which acquired from Feizabad district, NE Iran, were translated into mappable targeting criteria in the form of four predictor maps. In addition, the locations of 13 known Cu–Au deposits as prospect data and the locations of 13 randomly selected non-prospect data were used as target variables to train the models. Three authentic validation measures, K-fold cross-validation, confusion matrix and success-rate curves, were employed to evaluate the overall performance of two predictive models. Experimental results suggested the superiority of GRF model over the RF, as the favorable areas derived by GRF model occupy only 9% of the study area while predicting 100% of the known deposits. T S

Deng, S, Ji, J, Wen, G & Xu, H 2021, 'A comparative study of the dynamics of a three-disk dynamo system with and without time delay', Applied Mathematics and Computation, vol. 399, pp. 126016-126016.
View/Download from: Publisher's site
View description>>

The disk dynamo plays an important role in studying the geodynamo and much research works have been devoted to the understanding of dynamo dynamics. This paper further investigates an extended disk dynamo system having three coupled conducting disks and incorporates the interaction-induced time delay in the dynamic governing equations. By carrying out a comparative analysis, the dynamic behaviors of the coupled three-disk dynamo system with and without time delay are studied to explore novel and complex nonlinear dynamic phenomena in the coupled delayed dynamo system. It is found that the double Hopf bifurcations can be induced in the time-delayed dynamo system. Three different topological structures of the unfolding are obtained under different time delays. Accordingly, it is shown that the novel dynamic behaviors, including quasi-periodic torus, three-dimensional torus and the coexistence of multiple attractors, can appear in the time-delayed dynamo system. Furthermore, by performing the continuation analysis on the periodic orbit generated from the Hopf bifurcation of equilibrium, some new coexistence patterns, e.g., the coexistence of periodic orbits and chaos, the coexistence of quasi-periodic orbits and chaos, are observed in the dynamo system with time delay. Based on the obtained results, it is believed that the inclusion of time delay in the modelling of the three-disk dynamo system is necessary and meaningful for developing an in-depth understanding of dynamo dynamics. Finally, the results of theoretical analyses are verified by the numerical simulations.

Deshpande, NM, Gite, S, Pradhan, B, Kotecha, K & Alamri, A 2021, 'Improved Otsu and Kapur approach for white blood cells segmentation based on LebTLBO optimization for the detection of Leukemia', Mathematical Biosciences and Engineering, vol. 19, no. 2, pp. 1970-2001.
View/Download from: Publisher's site
View description>>

<abstract> <p>The diagnosis of leukemia involves the detection of the abnormal characteristics of blood cells by a trained pathologist. Currently, this is done manually by observing the morphological characteristics of white blood cells in the microscopic images. Though there are some equipment- based and chemical-based tests available, the use and adaptation of the automated computer vision-based system is still an issue. There are certain software frameworks available in the literature; however, they are still not being adopted commercially. So there is a need for an automated and software- based framework for the detection of leukemia. In software-based detection, segmentation is the first critical stage that outputs the region of interest for further accurate diagnosis. Therefore, this paper explores an efficient and hybrid segmentation that proposes a more efficient and effective system for leukemia diagnosis. A very popular publicly available database, the acute lymphoblastic leukemia image database (ALL-IDB), is used in this research. First, the images are pre-processed and segmentation is done using Multilevel thresholding with Otsu and Kapur methods. To further optimize the segmentation performance, the Learning enthusiasm-based teaching-learning-based optimization (LebTLBO) algorithm is employed. Different metrics are used for measuring the system performance. A comparative analysis of the proposed methodology is done with existing benchmarks methods. The proposed approach has proven to be better than earlier techniques with measuring parameters of PSNR and Similarity index. The result shows a significant improvement in the performance measures with optimizing threshold algorithms and the LebTLBO technique.</p> </abstract>

Dikshit, A & Pradhan, B 2021, 'Explainable AI in drought forecasting', Machine Learning with Applications, vol. 6, pp. 100192-100192.
View/Download from: Publisher's site

Dikshit, A & Pradhan, B 2021, 'Interpretable and explainable AI (XAI) model for spatial drought prediction', Science of The Total Environment, vol. 801, pp. 149797-149797.
View/Download from: Publisher's site
View description>>

Accurate prediction of any type of natural hazard is a challenging task. Of all the various hazards, drought prediction is challenging as it lacks a universal definition and is getting adverse with climate change impacting drought events both spatially and temporally. The problem becomes more complex as drought occurrence is dependent on a multitude of factors ranging from hydro-meteorological to climatic variables. A paradigm shift happened in this field when it was found that the inclusion of climatic variables in the data-driven prediction model improves the accuracy. However, this understanding has been primarily using statistical metrics used to measure the model accuracy. The present work tries to explore this finding using an explainable artificial intelligence (XAI) model. The explainable deep learning model development and comparative analysis were performed using known understandings drawn from physical-based models. The work also tries to explore how the model achieves specific results at different spatio-temporal intervals, enabling us to understand the local interactions among the predictors for different drought conditions and drought periods. The drought index used in the study is Standard Precipitation Index (SPI) at 12 month scales applied for five different regions in New South Wales, Australia, with the explainable algorithm being SHapley Additive exPlanations (SHAP). The conclusions drawn from SHAP plots depict the importance of climatic variables at a monthly scale and varying ranges of annual scale. We observe that the results obtained from SHAP align with the physical model interpretations, thus suggesting the need to add climatic variables as predictors in the prediction model.

Dikshit, A, Pradhan, B & Alamri, AM 2021, 'Long lead time drought forecasting using lagged climate variables and a stacked long short-term memory model', Science of The Total Environment, vol. 755, pp. 142638-142638.
View/Download from: Publisher's site

Dikshit, A, Pradhan, B & Alamri, AM 2021, 'Pathways and challenges of the application of artificial intelligence to geohazards modelling', Gondwana Research, vol. 100, pp. 290-301.
View/Download from: Publisher's site
View description>>

© 2020 International Association for Gondwana Research The application of artificial intelligence (AI) and machine learning in geohazard modelling has been rapidly growing in recent years, a trend that is observed in several research and application areas thanks to recent advances in AI. As a result, the increasing dependence on data driven studies has made its practical applications towards geohazards (landslides, debris flows, earthquakes, droughts, floods, glacier studies) an interesting prospect. These aforementioned geohazards were responsible for roughly 80% of the economic loss in the past two decades caused by all natural hazards. The present study analyses the various domains of geohazards which have benefited from classical machine learning approaches and highlights the future course of direction in this field. The emergence of deep learning has fulfilled several gaps in: i) classification; ii) seasonal forecasting as well as forecasting at longer lead times; iii) temporal based change detection. Apart from the usual challenges of dataset availability, climate change and anthropogenic activities, this review paper emphasizes that the future studies should focus on consecutive events along with integration of physical models. The recent catastrophe in Japan and Australia makes a compelling argument to focus towards consecutive events. The availability of higher temporal resolution and multi-hazard dataset will prove to be essential, but the key would be to integrate it with physical models which would improve our understanding of the mechanism involved both in single and consecutive hazard scenario. Geohazards would eventually be a data problem, like geosciences, and therefore it is essential to develop models that would be capable of handling large voluminous data. The future works should also revolve towards interpretable models with the hope of providing a reasonable explanation of the results, thereby achieving the ultimate goal of Explainable AI.

Dikshit, A, Pradhan, B & Huete, A 2021, 'An improved SPEI drought forecasting approach using the long short-term memory neural network', Journal of Environmental Management, vol. 283, pp. 111979-111979.
View/Download from: Publisher's site
View description>>

Droughts are slow-moving natural hazards that gradually spread over large areas and capable of extending to continental scales, leading to severe socio-economic damage. A key challenge is developing accurate drought forecast model and understanding a models' capability to examine different drought characteristics. Traditionally, forecasting techniques have used various time-series approaches and machine learning models. However, the use of deep learning methods have not been tested extensively despite its potential to improve our understanding of drought characteristics. The present study uses a deep learning approach, specifically the Long Short-Term Memory (LSTM) to predict a commonly used drought measure, the Standard Precipitation Evaporation Index (SPEI) at two different time scales (SPEI 1, SPEI 3). The model was compared with other common machine learning method, Random Forests, Artificial Neural Networks and applied over the New South Wales (NSW) region of Australia, using hydro-meteorological variables as predictors. The drought index and predictor data were collected from the Climatic Research Unit (CRU) dataset spanning from 1901 to 2018. We analysed the LSTM forecasted results in terms of several drought characteristics (drought intensity, drought category, or spatial variation) to better understand how drought forecasting was improved. Evaluation of the drought intensity forecasting capabilities of the model were based on three different statistical metrics, Coefficient of Determination (R²), Root Mean Square Error (RMSE), and Mean Absolute Error (MAE). The model achieved R² value of more than 0.99 for both SPEI 1 and SPEI 3 cases. The variation in drought category forecasted results were studied using a multi-class Receiver Operating Characteristic based Area under Curves (ROC-AUC) approach. The analysis revealed an AUC value of 0.83 and 0.82 for SPEI 1 and SPEI 3 respectively. The spatial variation between observed a...

Doan, S & Fatahi, B 2021, 'Green’s function analytical solution for free strain consolidation of soft soil improved by stone columns subjected to time-dependent loading', Computers and Geotechnics, vol. 136, pp. 103941-103941.
View/Download from: Publisher's site
View description>>

This paper proposes an analytical solution in terms of Green's function formulations for axisymmetric consolidation of a stone column improved soft soil deposit subjected to time-dependent loading under free strain condition. The mathematical derivations incorporate the pore water flows in radial and vertical directions in stone column and soft soil synchronously. The capabilities of the proposed analytical solution are evaluated via worked examples investigating the influences of three common time-dependent external surcharges (namely step, ramp and sinusoidal loadings) on consolidation response of the composite ground. The examples show that a faster increase of load from an initial surcharge to an expected loading might generate more significant excess pore water pressure to be dissipated during the early stages of consolidation, but the dissipation rate in soft soil would speed up significantly afterwards. The column and soil settlements along with the differential settlement between them also proceed faster corresponding to the acceleration of loading – unloading processes. Finally, the proposed analytical solution is employed to evaluate the excess pore water pressure dissipation rate at an investigation point in soft clay of a case history foundation. The calculation results exhibit a reasonable agreement with field measurement data when various constant values of stress concentration ratio are substituted into the solution to reflect the increase of stress concentration ratio with consolidation time in real practice.

Dong, W, Li, W, Vessalas, K, He, X, Sun, Z & Sheng, D 2021, 'Piezoresistivity deterioration of smart graphene nanoplate/cement-based sensors subjected to sulphuric acid attack', Composites Communications, vol. 23, pp. 100563-100563.
View/Download from: Publisher's site
View description>>

Smart cement-based sensors with self-sensing capacity have been explored for structural health monitoring (SHM) with the intrinsic piezoresistive performance. However, few studies had studied the piezoresistivity degradation of cement-based sensors after exposure to the aggressive environments, especially under sulphate acid attacks. In this study, graphene nanoplate (GNP)/cementitious composites were immersed in sulphuric acid solutions (concentrations of 0, 1%, 2%, and 3%) for 90 and 180 days. Then surface appearance, weight loss, mechanical properties, piezoresistivity and microstructure were investigated and compared before and after sulphuric acid immersion. The results show that after acid immersion, the surface deterioration and mass loss were increased, and the compressive strength was significantly decreased. As for the intact GNP/cementitious composite, the piezoresistivity exhibited excellent linearity and repeatability, demonstrating the great potential to act as intelligent cement-based sensors for SHM. After 90 and 180 days of acid immersion, the piezoresistivity was sensitive to the initial low load initially but then turned less sensitive to the later high load. The highly corroded GNP/cementitious composites exhibited porous microstructures associated with the low compressive strength. The fractional changes to resistivity (FCR) under the low load could be attributed to the compressed pores and voids filled with erosion products that would form conductive passages. In contrast, with the increase of applied load, the intact cement matrix became much denser, which in turn constrained the further development of conductive passages in the GNP/cementitious composites.

Dong, W, Li, W, Zhu, X, Sheng, D & Shah, SP 2021, 'Multifunctional cementitious composites with integrated self-sensing and hydrophobic capacities toward smart structural health monitoring', Cement and Concrete Composites, vol. 118, pp. 103962-103962.
View/Download from: Publisher's site
View description>>

In this study, multifunctional cementitious composites with integrated self-sensing and hydrophobicity capacities were developed and investigated using conductive graphene nanoplate (GNP) and silicone hydrophobic powder (SHP). The mechanical properties, permeability, water contact angle, microstructure and piezoresistivity were studied and compared under different contents of GNP and SHP. The highest compressive and flexural strengths with 1% SHP and 2% GNP reached 62.6 MPa and 8.9 MPa, respectively. The water absorption significantly was decreased with the content of SHP, but was minorly affected by GNP. The water contact angle firstly increased but then decreased with the dosages of GNP and SHP. SHP and GNP could reduce the microscale pores and enhance the density of microstructures. The piezoresistivity under compression firstly exhibited low gauge factor, but then gradually increased to a constant value under high-stress magnitude. Moreover, compared to the conventional cement-based sensors, this piezoresistive cementitious composites containing SHP and GNP as novel cement-based sensors are less sensitive to water content and humidity. The outcomes can provide an insight into promoting the application of multifunctional cement-based sensors toward structural health monitoring under various ambient conditions.

Dzaklo, CK, Rujikiatkamjorn, C, Indraratna, B & Kelly, R 2021, 'Cyclic behaviour of compacted black soil-coal wash matrix', Engineering Geology, vol. 294, pp. 106385-106385.
View/Download from: Publisher's site

Eager, D, Halkon, B, Zhou, S, Walker, P, Covey, K & Braiden, S 2021, 'Greyhound Racing Track Lure Systems—Acoustical Measurements within and Adjacent to the Starting Boxes', Technologies, vol. 9, no. 4, pp. 74-74.
View/Download from: Publisher's site
View description>>

This study investigates and compares the acoustic signatures of a traditional wire-cable-pulled lure system and two alternative battery-operated lure systems jointly developed by Covey Associates Pty. Ltd. and Steriline Pty. Ltd. to eliminate the hazardous steel-wire cable and make the sport of greyhound racing safer for greyhounds, participants and spectators. The acoustical measurements of these three lure systems were conducted at the Murray Bridge greyhound racing track. The lure sounds were measured by the high-frequency Brüel & Kjær (B&K) Type 4191 microphones for the 395 m and 455 m starts at two positions: within the starting box and on the track adjacent to the starting boxes. The measurements capture the sounds that the greyhounds hear before and after the opening of the starting box gate. The frequency-domain analysis and sound quality analysis were conducted to compare the lure sounds. It was found when the battery-lure was installed with all nylon rollers, it presented less sound energy and lower frequency than the traditional wire-cable-pulled lure. When two of the nylon rollers were replaced with steel rollers, the battery-operated lure emitted a louder and higher frequency sound than the traditional wire-cable-pulled lure. The different acoustic characteristics of these lure systems suggest future research is warranted on the reaction of greyhounds to different lure sounds, particularly their excitement level within the starting box as the lure approaches. This initial research also suggests some greyhounds may not clearly hear the battery-operated lure with all nylon rollers approaching the starting boxes and the timing of these greyhounds to jump may be delayed, particularly during high wind conditions.

El-Haddad, BA, Youssef, AM, Pourghasemi, HR, Pradhan, B, El-Shater, A-H & El-Khashab, MH 2021, 'Flood susceptibility prediction using four machine learning techniques and comparison of their performance at Wadi Qena Basin, Egypt', Natural Hazards, vol. 105, no. 1, pp. 83-114.
View/Download from: Publisher's site
View description>>

Floods represent catastrophic environmental hazards that have a significant impact on the environment and human life and their activities. Environmental and water management in many countries require modeling of flood susceptibility to help in reducing the damages and impact of floods. The objective of the current work is to employ four data mining/machine learning models to generate flood susceptibility maps, namely boosted regression tree (BRT), functional data analysis (FDA), general linear model (GLM), and multivariate discriminant analysis (MDA). This study was done in Wadi Qena Basin in Egypt. Flood inundated locations were determined and extracted from the interpretation of different datasets, including high-resolution satellite images (sentinel-2 and Astro digital) (after flood events), historical records, and intensive field works. In total, 342 flood inundated locations were mapped using ArcGIS 10.5, which separated into two groups; training (has 239 flood locations represents 70%) and validating (has 103 flood locations represents 30%), respectively. Nine themes of flood-influencing factors were prepared, including slope-angle, slope length, altitude, distance from main wadis, landuse/landcover, lithological units, curvature, slope-aspect, and topographic wetness index. The relationships between the flood-influencing factors and the flood inventory map were evaluated using the mentioned models (BRT, FDA, GLM, and MDA). The results were compared with flood inundating locations (validating flood sites), which were not used in constructing the models. The accuracy of the models was calculated through the success (training data) and prediction (validation data) rate curves according to the receiver operating characteristics (ROC) and the area under the curve (AUC). The results showed that the AUC for success and prediction rates are 0.783, 0.958, 0.816, 0.821 and 0.812, 0.856, 0.862, 0.769 for BRT, FDA, GLM, and MDA models, respectively. Subseque...

El-Magd, SAA, Pradhan, B & Alamri, A 2021, 'Machine learning algorithm for flash flood prediction mapping in Wadi El-Laqeita and surroundings, Central Eastern Desert, Egypt', Arabian Journal of Geosciences, vol. 14, no. 4.
View/Download from: Publisher's site

Farooq, MA, Nimbalkar, S & Fatahi, B 2021, 'Three-dimensional finite element analyses of tyre derived aggregates in ballasted and ballastless tracks', Computers and Geotechnics, vol. 136, pp. 104220-104220.
View/Download from: Publisher's site
View description>>

Scrap tyres are a significant source of pollution and pose a grave threat to the environment and human health. The present study aims to examine the application of Tyre Derived Aggregate (TDA) in a concrete slab track and ballasted track and compare its performance in both track forms. In this study, long-term performance of slab track and ballasted track subjected to train induced loading is demonstrated based on the three-dimensional finite element modelling. The most suitable constitutive hyperelastic model for TDA has been identified. Subsequently, the most suitable position for the location of TDA is determined for both track types. A comparative analysis between slab track and ballasted track, with and without TDA, is presented in terms of stress transfer, vibration reduction and displacement (elastic and plastic). It is shown that TDA helps in reducing up to 50% vibration levels of both track types. The influence of train speed and axle load on the vertical and horizontal displacement and stress response of both track forms is shown for a large number of load cycles. Overall, it is observed that the long-term performance of TDA is better in slab track compared to ballasted track.

Gao, F, He, X & Zhang, S 2021, 'Pumping effect of rainfall-induced excess pore pressure on particle migration', Transportation Geotechnics, vol. 31, pp. 100669-100669.
View/Download from: Publisher's site

Ge, M, Pineda, JA, Sheng, D, Burton, GJ & Li, N 2021, 'Microstructural effects on the wetting-induced collapse in compacted loess', Computers and Geotechnics, vol. 138, pp. 104359-104359.
View/Download from: Publisher's site
View description>>

This paper presents the results of an experimental study aimed at evaluating the effects of soil microstructure on volume change and wetting-induced collapse of a compacted loess from Xi'an, China. One-dimensional (1D) compression tests are combined with Mercury Intrusion Porosimetry (MIP) tests and Scanning Electron Microscopy (SEM) analysis to examine the collapse behaviour for different compaction states and applied stresses. A phenomenon of partial collapse occurs upon full saturation (wetting), whose magnitude depends on the as-compacted suction, the as-compacted microstructure and the stress level applied. Following partial collapse upon full saturation some of the initially meta-stable microstructure of the compacted soil is preserved which leads to higher compressibility in subsequent loading stages. Additional collapse tests carried out under isotropic conditions show that partial collapse upon full saturation takes place only under zero-lateral deformation (1D) conditions due to the residual (‘locked-in’) horizontal stresses maintained in the sample after compaction. Microstructural results and a simple macroscopic model for soil compaction are used to qualitatively explain the phenomenon of partial collapse observed in compacted loess.

Ghosh, B, Fatahi, B, Khabbaz, H, Nguyen, HH & Kelly, R 2021, 'Field study and numerical modelling for a road embankment built on soft soil improved with concrete injected columns and geosynthetics reinforced platform', Geotextiles and Geomembranes, vol. 49, no. 3, pp. 804-824.
View/Download from: Publisher's site

Gite, S, Pradhan, B, Alamri, A & Kotecha, K 2021, 'ADMT: Advanced Driver’s Movement Tracking System Using Spatio-Temporal Interest Points and Maneuver Anticipation Using Deep Neural Networks', IEEE Access, vol. 9, pp. 99312-99326.
View/Download from: Publisher's site
View description>>

Assistive driving is a complex engineering problem and is influenced by several factors such as the sporadic nature of the quality of the environment, the response of the driver, and the standard of the roads on which the vehicle is being driven. The authors track the driver's anticipation based on his head movements using Spatio-Temporal Interest Point (STIP) extraction and enhance the anticipation of action accuracy well before using the RNN-LSTM framework. This research tackles a fundamental problem of lane change assistance by developing a novel model called Advanced Driver's Movement Tracking (ADMT). ADMT uses customized convolution-based deep learning networks by using Recurrent Convolutional Neural Network (RCNN). STIP with eye gaze extraction and RCNN performed in ADMT on brain4cars dataset for driver movement tracking. Its performance is compared with the traditional machine learning and deep learning models, namely Support Vector Machines (SVM), Hidden Markov Model (HMM), Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), and provided an increment of almost 12% in the prediction accuracy and 44% in the anticipation time. Furthermore, ADMT systems outperformed all of the models in terms of both the accuracy of the system and the previously mentioned time of anticipation that is discussed at length in the paper. Thus it assists the driver with additional anticipation time to access the typical reaction time for better preparedness to respond to undesired future behavior. The driver is then assured of a safe and assisted driving experience with the proposed system.

He, X, Wang, F, Li, W & Sheng, D 2021, 'Efficient reliability analysis considering uncertainty in random field parameters: Trained neural networks as surrogate models', Computers and Geotechnics, vol. 136, pp. 104212-104212.
View/Download from: Publisher's site
View description>>

This paper presents an efficient reliability analysis framework, by using trained artificial neural networks (ANNs) as surrogate models, for geotechnical problems where the random field parameters like the mean and standard deviation are themselves uncertain. Random field theory has been extensively used to model soil uncertainty and spatial variability. However, due to limited availability of data, random field parameters can rarely be estimated accurately, often estimated in confidence intervals (uncertain parameters). Monte Carlo based reliability analysis is computationally extremely demanding because the function to map outcomes of random fields to structural response can only be calculated via numerical simulations. The authors have used trained ANNs as surrogate models in reliability analysis. However, these ANNs are specific for random fields with deterministic parameters. This paper presents a new framework in which trained ANN models are for random fields with variable parameters. A key component is the design of experiments – generating representative outcomes. In the prediction of the bearing capacity for strip footings, the efficiency and accuracy of this framework are successfully demonstrated. This framework is also efficient in reliability sensitivity studies. One main finding is that ignoring random field parameter uncertainty could lead to underestimated failure probability and hence unsafe design.

Hembram, TK, Saha, S, Pradhan, B, Abdul Maulud, KN & Alamri, AM 2021, 'Robustness analysis of machine learning classifiers in predicting spatial gully erosion susceptibility with altered training samples', Geomatics, Natural Hazards and Risk, vol. 12, no. 1, pp. 794-828.
View/Download from: Publisher's site

Hoque, MA-A, Pradhan, B, Ahmed, N & Sohel, MSI 2021, 'Agricultural drought risk assessment of Northern New South Wales, Australia using geospatial techniques', Science of The Total Environment, vol. 756, pp. 143600-143600.
View/Download from: Publisher's site

Hoque, MA-A, Pradhan, B, Ahmed, N, Ahmed, B & Alamri, AM 2021, 'Cyclone vulnerability assessment of the western coast of Bangladesh', Geomatics, Natural Hazards and Risk, vol. 12, no. 1, pp. 198-221.
View/Download from: Publisher's site
View description>>

Coastal Bangladesh is one of the hotspots of tropical cyclone’s landfall in South Asia. A spatial vulnerability assessment is required to formulate disaster risk reduction strategies. This study develops a comprehensive tropical cyclone vulnerability mapping approach by applying Fuzzy Analytical Hierarchy Process (FAHP) and geospatial techniques and examines the spatial distribution of tropical cyclone vulnerability in the western coastal region of Bangladesh. We have selected 18 spatial criteria under the physical, social, and mitigation capacity categories as the components of vulnerability. Results indicate that the southern and south-eastern peripheral areas exhibit higher vulnerability to tropical cyclones since these areas comprise low elevation, gentle slope, closeness to the sea, a high number of historical cyclone tracks, vulnerable land cover classes (settlements and crops land), and poor socio-economic structures. These areas cover most of the Barguna, Khulna, Bagerhat, Jhalokati, and southern parts of Satkhira, and Pirojpur districts. The existing mitigation capacity measures, for example, the construction of cyclone shelters, embankments, road networks, and effective warning systems in these areas are not adequate levels. The findings would be useful for policymakers and local authorities in formulating appropriate cyclone risk mitigation plans in coastal Bangladesh.

Horry, MJ, Chakraborty, S, Pradhan, B, Fallahpoor, M, Chegeni, H & Paul, M 2021, 'Factors determining generalization in deep learning models for scoring COVID-CT images', Mathematical Biosciences and Engineering, vol. 18, no. 6, pp. 9264-9293.
View/Download from: Publisher's site
View description>>

<abstract> <p>The COVID-19 pandemic has inspired unprecedented data collection and computer vision modelling efforts worldwide, focused on the diagnosis of COVID-19 from medical images. However, these models have found limited, if any, clinical application due in part to unproven generalization to data sets beyond their source training corpus. This study investigates the generalizability of deep learning models using publicly available COVID-19 Computed Tomography data through cross dataset validation. The predictive ability of these models for COVID-19 severity is assessed using an independent dataset that is stratified for COVID-19 lung involvement. Each inter-dataset study is performed using histogram equalization, and contrast limited adaptive histogram equalization with and without a learning Gabor filter. We show that under certain conditions, deep learning models can generalize well to an external dataset with F1 scores up to 86%. The best performing model shows predictive accuracy of between 75% and 96% for lung involvement scoring against an external expertly stratified dataset. From these results we identify key factors promoting deep learning generalization, being primarily the uniform acquisition of training images, and secondly diversity in CT slice position.</p> </abstract>

Huang, J & Ji, J 2021, 'Vibration control of coupled Duffing oscillators in flexible single-link manipulators', Journal of Vibration and Control, vol. 27, no. 17-18, pp. 2058-2068.
View/Download from: Publisher's site
View description>>

Motion-induced oscillations of the flexible single link and its payload at the tip have negative impact on the anticipated performance of the flexible manipulators and thus should be suppressed to achieve tip positioning accuracy and high-speed operation. Because of the structural flexibility, the dynamics of the flexible manipulator can be described by coupled Duffing oscillators when considering the inherent structural nonlinearity of the flexible link into the dynamic modeling. However, little research has been focused on addressing the dynamic coupling issue in the nonlinear modeling of flexible-link manipulators using coupled Duffing oscillators. This article presents coupled Duffing oscillators for the nonlinear modeling of flexible single-link manipulators and then proposes a control method for suppressing the nonlinear vibrations of the coupled Duffing oscillators. Simulated and experimental results obtained from a flexible single-link manipulator test bench are in good agreement with the proposed nonlinear modeling and also demonstrate the effectiveness of the proposed control techniques for vibration suppression of the flexible manipulator.

Huang, S, Samali, B & Li, J 2021, 'Numerical and experimental investigations of a thermal break composite façade mullion under four-point bending', Journal of Building Engineering, vol. 34, pp. 101590-101590.
View/Download from: Publisher's site
View description>>

© 2020 Elsevier Ltd This paper presents numerical and experimental investigations on a typical thermal break composite façade profile under four-point bending. The purpose of this study is to gain the knowledge of the interfacial behaviour between aluminum extrusion and polyamide insert beyond elastic range. Understanding the behaviour of this energy efficient façade profile within plastic range is important for the design under extreme loading, such as earthquakes, strong wind conditions and even blast loads. The experimental investigation was carried out on four types of beam specimens. The specimens were grouped by their span lengths with three specimens for each span length. As the specimens’ geometry and composite action are complicated, seven strain gauges were used per specimen including small strain gauges to fit in the limited space of the thermal break section. A three stage failure process was observed during the experiments. A numerical investigation was carried out by using Finite Element modelling to simulate behaviour of the thermal break composite façade profile under similar loading condition in order to compare with the testing results as well as to capture the corresponding failure mechanisms. Numerical simulations were setup by applying a proposed partitioned multi-phase failure model to simulate three stage failure process discovered by experiments. The results from FE models were compared and discussed with experimental counterparts. In summary, FE models showed consistent results to the experimental counterparts and it also provided the insight and more details of failure mechanism and stress distribution including interfacial condition details. Behaviour of the thermal break façade profile in the plastic range displayed excellent ductility and high strength capacity of this type of thermal break section in the plastic range after slip.

Huang, Z, Shivakumara, P, Lu, T, Pal, U, Blumenstein, M, Chetty, B & Kumar, GH 2021, 'Improved Ring Radius Transform-Based Reconstruction for Video Character Recognition', International Journal of Pattern Recognition and Artificial Intelligence, vol. 35, no. 07, pp. 2150023-2150023.
View/Download from: Publisher's site
View description>>

Character shape reconstruction in video is challenging due to low contrast, complex backgrounds and arbitrary orientation of characters. This work proposes an Improved Ring Radius Transform (IRRT) for reconstructing impaired characters through medial axis prediction. At first, the technique proposes a novel idea based on the Tangent Vector (TV) concept that identifies each actual pair of end pixels caused by gaps in impaired character components. Next, the actual direction to predict medial axis pixels using IRRT for each pair of end pixels is proposed with a new normal vector concept. The process of prediction repeats iteratively to find all the medial axis pixels for every gap in question. Further, medial axis pixels with their radii are used to reconstruct the shapes of impaired characters. The proposed technique is tested on benchmark datasets consisting of video, natural scenes, objects and multi-lingual data to demonstrate that it reconstructs shapes well, even for heterogeneous data. Comparative studies with different binarization and character recognition methods show that the proposed technique is effective, useful and outperforms existing methods.

Indraratna, B, Ngo, T, Ferreira, FB, Rujikiatkamjorn, C & Tucho, A 2021, 'Large-scale testing facility for heavy haul track', Transportation Geotechnics, vol. 28, pp. 100517-100517.
View/Download from: Publisher's site
View description>>

Given the substantially increased demand for increased axle loads of heavy haul trains, there is an imperative need to develop sustainable track infrastructure. When subjected to heavy axle loading, ballast aggregates rapidly break down, compromising the particle friction and associated load bearing capacity. Therefore, understanding the deformation and degradation (breakage) of ballast subjected to various boundary and loading conditions is crucial for improved track design and performance monitoring. Ideally, field testing should be carried out in real-life tracks to avoid laboratory scale and boundary effects, but field tests are often expensive, time-consuming and may disrupt rail traffic, hence not always feasible. A prototype test facility that can simulate appropriate axle loading and boundary conditions for standard gauge heavy haul tracks is presented in this paper. In collaboration with more than a dozen Universities and Industry organisations, Australia's first and only National Facility for Heavy-haul Railroad Testing (NFHRT) has recently been constructed and is now fully operational. This new facility enables a real-size (1:1 scale) instrumented track section to be subjected to continuous cyclic loading simulated via two pairs of dynamic actuators in synchronized operation. The results of a typical test are presented in this paper including the measured track settlement and lateral deformation, transient vertical and lateral stresses, rail and sleeper accelerations, resilient modulus and breakage of ballast. The test results show that an average track settlement of about 14 mm and lateral displacements up to 9 mm are recorded after 500,000 load cycles. Subjected to a 25-tonne axle load, the maximum vertical stress measured at the sleeper-ballast interface is about 225 kPa and this attenuates with depth. The test results of this iconic facility are generally consistent with actual field measurements obtained in heavy-haul tracks located in t...

Indraratna, B, Nguyen, TT, Singh, M, Rujikiatkamjorn, C, Carter, JP, Ni, J & Truong, MH 2021, 'Cyclic loading response and associated yield criteria for soft railway subgrade – Theoretical and experimental perspectives', Computers and Geotechnics, vol. 138, pp. 104366-104366.
View/Download from: Publisher's site

Indraratna, B, Phan, NM, Nguyen, TT & Huang, J 2021, 'Simulating Subgrade Soil Fluidization Using LBM-DEM Coupling', International Journal of Geomechanics, vol. 21, no. 5, pp. 1-14.
View/Download from: Publisher's site
View description>>

The loss of effective stress due to increasing excess pore pressure that results in the upward migration of soil particles, that is, subgrade fluidization and mud pumping, has been a critical issue for railways over many years. Traditional methods such as experimental and analytical approaches can capture macroscopic quantities such as the hydraulic conductivity and critical hydraulic gradient, but they have many limitations when microscopic and localized behavior must be captured. This paper, therefore, presents a novel numerical approach where the microscopic properties of fluid and particles can be better captured when the soil is subjected to an increasing hydraulic gradient. While particle behavior is simulated using the discrete element method (DEM), the fluid dynamics can be described in greater detail using the lattice Boltzmann method (LBM). The mutual LBM-DEM interaction is carried out, so the particle and fluid variables are constantly updated. To validate this numerical method, laboratory testing on a selected subgrade soil is conducted. The results show that the numerical method can reasonably predict the coupled hydraulic and soil fluidization aspects, in relation to the experimental data. Microscopic properties such as the interstitial fluid flowing through the porous spaces of the soil are also captured well by the proposed fluid-particle coupling approach.

Indraratna, B, Qi, Y, Jayasuriya, C, Rujikiatkamjorn, C & Arachchige, CMK 2021, 'Use of recycled rubber inclusions with granular waste for enhanced track performance', Transportation Engineering, vol. 6, pp. 100093-100093.
View/Download from: Publisher's site

Indraratna, B, Rujikiatkamjorn, C, Kelly, R, Kianfar, K & Sloan, LS 2021, 'COLLABORATIONS IN GEOTECHNICAL ENGINEERING: LESSONS FROM THE BALLINA BYPASS AND THE NATIONAL SOFT SOIL FIELD TESTING FACILITY', Australian Geomechanics Journal, vol. 56, no. 2, pp. 85-93.
View description>>

Collaboration assists both academics and industry partners to achieve innovations, scientific advancement, and maintain technical competencies. The Ballina Bypass is used here to demonstrate collaboration via an Australian Research Council (ARC) Linkage project on vacuum consolidation, and to discuss how the lessons learned from the Ballina Bypass led to establishing a national facility in Ballina to field test soft soils. The outcomes of the work at the field testing facility have been transferred back to the industry via an international numerical prediction symposium. The project background, roles, and responsibilities of researchers and industry members are discussed and explained, as are the innovative outcomes, stakeholder benefits, and cultural impacts.

Indraratna, B, Singh, M, Nguyen, TT, Leroueil, S, Abeywickrama, A, Kelly, R & Neville, T 2021, 'Correction: Laboratory study on subgrade fluidization under undrained cyclic triaxial loading', Canadian Geotechnical Journal, vol. 58, no. 11, pp. 1790-1790.
View/Download from: Publisher's site
View description>>

In the Acknowledgements section, “(ITTC),” should be replaced with “(ITTC-Rail) at the”; and “ARTC (Australian Rail Track Corpora-tion)” should be replaced with “ACRI (Australasian Centre for Rail Innovation)”. The corrected text of the Acknowledgements section is as follows: This research was supported by the Australian Government through the Australian Research Council’s Linkage Projects funding scheme (project LP160101254) and the Industrial Transformation Training Centre for Advanced Technologies in Rail Track Infrastructure (ITTC-Rail) at the University of Wollongong. The financial and technical support from SMEC-Australia and ACRI (Australasian Centre for Rail Innovation) is acknowledged.

Indraratna, B, Soomro, MHAA & Rujikiatkamjorn, C 2021, 'Semi-empirical analytical modelling of equivalent dynamic shear strength (EDSS) of rock joint', Transportation Geotechnics, vol. 29, pp. 100569-100569.
View/Download from: Publisher's site
View description>>

A systematic dynamic triaxial series of tests on replicated rough rock joints were carried out, and results clearly highlight the strength attenuation as a function of joint degradation with respect to the number of loading cycles. A novel semi-empirical mathematical model to evaluate the equivalent dynamic shear strength (EDSS) of rock joint is proposed and validated with experimental results based on two sets of rock joints using rough (JRC = 12.6) and relatively smoother (JRC = 7.2) joint specimens.

Iqbal, J 2021, 'Landslide susceptibility assessment along the Dubair-Dudishal section of the Karakoram Highway, Northwestern Himalayas, Pakistan', Acta Geodynamica et Geomaterialia, pp. 137-155.
View/Download from: Publisher's site
View description>>

The primary objective of this study is to analyze and characterize landslides in North Pakistan along Karakoram Highway (KKH) to produce a landslide susceptibility map using GIS and remote sensing technology. Using satellite images followed by field investigations, spatial distribution of landslide database was generated. Next, an integrated study was undertaken in the study area to perform the landslide susceptibility mapping. Dubaur-Dudishal section of KKH (about 150 km) which is a part of Kohistan Island Arc, is investigated in this study with a buffer zone of about 8 km along both sides of the KKH. Several thematic maps, e.g., lithology, distance to faults, distance to streams, distance to roads, normalized difference vegetation index (NDVI), slope, aspect, elevation, relative relief, plan-curvature and profile-curvature were prepared. Subsequently, these thematic data layers were analyzed by frequency ratio (FR) model and weights-of-evidence (WoE) model to generate the landslide susceptibility maps. In order to check the accuracy of the models, the area under the curve (AUC) was to quantitatively compare the two models used in this study. The predictive ability of AUC values indicate that the success rates of FR model and WoE model are 0.807 and 0.866, whereas the prediction rates are 0.785 and 0.846, respectively. Both methods show that nearly 50 % landslides in the study area fall in either high or very high susceptibility zones. The landslide susceptibility maps presented in this study are of great importance to the policy makers and the engineers for highway construction as well as the mega dams construction projects (Dasu dam and Bhasha dam which lie within the vicinity of the study area); so that proper prevention as well as mitigation could be done in advance to avoid the possible economic as well as the human loss in future.

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.

Jain, K & Pradhan, B 2021, 'Editorial', Journal of the Indian Society of Remote Sensing, vol. 49, no. 3, pp. 461-462.
View/Download from: Publisher's site

Jayathilaka, P, Indraratna, B & Heitor, A 2021, 'Influence of Salinity-Based Osmotic Suction on the Shear Strength of a Compacted Clay', International Journal of Geomechanics, vol. 21, no. 5, pp. 04021041-04021041.
View/Download from: Publisher's site

Jena, R, Ghansar, TAA, Pradhan, B & Rai, AK 2021, 'Estimation of fractal dimension and b-value of earthquakes in the Himalayan region', Arabian Journal of Geosciences, vol. 14, no. 10.
View/Download from: Publisher's site

Jena, R, Naik, SP, Pradhan, B, Beydoun, G, Park, H-J & Alamri, A 2021, 'Earthquake vulnerability assessment for the Indian subcontinent using the Long Short-Term Memory model (LSTM)', International Journal of Disaster Risk Reduction, vol. 66, pp. 102642-102642.
View/Download from: Publisher's site
View description>>

Earthquakes are one of the most destructive and unpredictable natural hazards with a long-term physical, psychological, and economic impact to the society. In the past century, more than 1100 destructive earthquakes occurred, and caused around 1.5 million deaths worldwide. Some recent studies have suggested that a future earthquake in the Himalayan region of magnitude range MW 7.5–8 can cause more than 0.2 million human lives and around 150 billion dollar financial loss. Deep learning methods in recent studies proved very useful in natural hazards forecasting and prediction modelling. Long Short-Term Memory (LSTM) model has been particularly popular in several natural hazard forecasting. In this research, for the first time, LSTM model is implemented with suitable Geospatial Information Systems (GIS) techniques to assess the earthquake vulnerability for whole of India. In India, most of the seismic vulnerability assessment available are at city level or state level using traditional techniques. Several factors such as land use, geology, geomorphology, fault distribution, transportation facility, population density were all used to develop the social, structural, and geotechnical vulnerability maps. The results show that the areas around Delhi, NE region of India, major parts of Gujrat, West Bengal plain exhibit high to very-high seismic vulnerability. This model achieved an accuracy of 87.8%, sensitivity (90%) and specificity (84.9%). The present analysis can be helpful towards prioritization of regions which are in higher need of risk reduction interventions. Also, based on this vulnerability index map, the risk metrics can be attenuated.

Jena, R, Pradhan, B, Naik, SP & Alamri, AM 2021, 'Earthquake risk assessment in NE India using deep learning and geospatial analysis', Geoscience Frontiers, vol. 12, no. 3, pp. 101110-101110.
View/Download from: Publisher's site

Ji, JC, Luo, Q & Ye, K 2021, 'Vibration control based metamaterials and origami structures: A state-of-the-art review', Mechanical Systems and Signal Processing, vol. 161, pp. 107945-107945.
View/Download from: Publisher's site
View description>>

Vibration and sound control is critical to many practical engineering systems in order to minimise the detrimental effects caused by unavoidable vibrations and noises. Metamaterials and origami-based structures, which have attracted increasing interests in interdisciplinary research fields, possess many peculiar physical properties, including negative Poisson's ratios, bi- or multi-stable states, nonlinear and tuneable stiffness features, and thus offer promising applications for vibration and sound control. This paper presents a review of metamaterials and origami-based structures as well as their applications to vibration and sound control. Metamaterials are artificially engineered materials having extremal properties which are not found in conventional materials. Metamaterials with abnormal features are firstly discussed on the basis of the unusual values of their elastic constants. Recent advances of auxetic, band gap and pentamode metamaterials are reviewed together with their applications to vibration and sound mitigations. Origami, as the ancient Japanese art of paper folding, has emerged as a new design paradigm for different applications. Origami-based structures can be adopted for vibration isolation by using their multi-stable states and desirable stiffness characteristics. Different origami patterns are reviewed to show their configurations and base structures. Special features, such as bi- or multi-stable states, dynamic Poisson's ratios, and nonlinear force–displacement relationships are discussed for their applications for vibration control. Finally, possible future research directions are elaborated for this emerging and promising interdisciplinary research field.

Kan, ME, Indraratna, B & Rujikiatkamjorn, C 2021, 'On numerical simulation of vertical drains using linear 1-dimensional drain elements', Computers and Geotechnics, vol. 132, pp. 103960-103960.
View/Download from: Publisher's site

Khade, S, Gite, S, Thepade, SD, Pradhan, B & Alamri, A 2021, 'Detection of Iris Presentation Attacks Using Hybridization of Discrete Cosine Transform and Haar Transform With Machine Learning Classifiers and Ensembles', IEEE Access, vol. 9, no. 99, pp. 169231-169249.
View/Download from: Publisher's site
View description>>

Iris biometric identification allows for contactless authentication, which helps to avoid the transmission of diseases like COVID-19. Biometric systems become unstable and hazardous due to spoofing attacks involving contact lenses, replayed video, cadaver iris, synthetic Iris, and printed iris. This work demonstrates the iris presentation attacks detection (Iris-PAD) approach that uses fragmental coefficients of transform iris images as features obtained using Discrete Cosine Transform (DCT), Haar Transform, and hybrid Transform. In experimental validations of the proposed method, three main types of feature creation are investigated. The extracted features are utilized for training seven different machine learning classifiers alias Support Vector Machine (SVM), Naive Bayes (NB), Random Forest (RF), and decision tree(J48) with ensembles of SVM+RF+NB, SVM+RF+RT, and RF+SVM+MLP (multi-layer perceptron) for proposed iris liveness detection. The proposed iris liveness detection variants are evaluated using various statistical measures: accuracy, Attack Presentation Classification Error Rate (APCER), Normal Presentation Classification Error Rate (NPCER), Average Classification Error Rate (ACER). Six standard datasets are used in the investigations. Total nine iris spoofing attacks are getting identified in the proposed method. Among all investigated variations of proposed iris-PAD methods, the 4 ×4 of fragmental coefficients of a Hybrid transformed iris image with RF algorithm have shown superior iris liveness detection with 99.95% accuracy. The proposed hybridization of transform for features extraction has demonstrated the ability to identify all nine types of iris spoofing attacks and proved it robust. The proposed method offers exceptional performances against the Synthetic iris spoofing images by using a random forest classifier. Machine learning has massive potential in a similar domain and could be explored further based on the research requirements.

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.

Kolekar, S, Gite, S, Pradhan, B & Kotecha, K 2021, 'Behavior Prediction of Traffic Actors for Intelligent Vehicle Using Artificial Intelligence Techniques: A Review', IEEE Access, vol. 9, pp. 135034-135058.
View/Download from: Publisher's site
View description>>

Intelligent vehicle technology has made tremendous progress due to Artificial Intelligence (AI) techniques. Accurate behavior prediction of surrounding traffic actors is essential for the safe and secure navigation of the intelligent vehicle. Minor misbehavior of these vehicles on the busy roads may lead to an accident. Due to this, there is a need for vehicle behavior research work in today's era. This research article reviews traffic actors' behavior prediction techniques for intelligent vehicles to perceive, infer, and anticipate other vehicles' intentions and future actions. It identifies the key strategies and methods for AI, emerging trends, datasets, and ongoing research issues in these fields. As per the authors' knowledge, this is the first systematic literature review dedicated to the vehicle behavior study examining existing academic literature published by peer review venues between 2011 and 2021. A systematic review was undertaken to examine these papers, and five primary research questions have been addressed. The findings show that using sophisticated input representation that includes traffic rules and road geometry, artificial intelligence-based solutions applied to behavior prediction of traffic actors for intelligent vehicles have shown promising success, particularly in complex driving scenarios. Finally, the paper summarizes the most widely used approaches in behavior prediction of traffic actors for intelligent vehicles, which the authors believe serves as a foundation for future research in behavior prediction of surrounding traffic actors for secure and accurate intelligent vehicle navigation.

Kolekar, SS, Gite, SS & Pradhan, B 2021, 'Demystifying Artificial Intelligence based Behavior Prediction of Traffic Actors for Autonomous Vehicle- A Bibliometric Analysis of Trends and Techniques', Library Philosophy and Practice, vol. 2021, pp. 1-25.
View description>>

Background: The purpose of this study is to examine, using bibliometric methods, the work done on behavior prediction of traffic actors for autonomous vehicles using various artificial intelligence algorithms from 2011 to 2020. Methods: Using one of the most common databases, Scopus, numerous papers on behavior prediction of traffic actors for autonomous vehicles were retrieved. The research papers are being considered for the period from 2011 to 2020. The Scopus analyzer is used to obtain some results of the study, such as documents by year, source, and country and so on. VOSviewer Version 1.6.16 is used for the analysis of different units such as co-authorship, co-occurrences, citation analysis etc. Results: In our study, a database search outputs a total of 275 articles on behavior prediction for autonomous vehicle from 2011 to 2020. Statistical analysis and network analysis shows the maximum articles are published in the years 2019 and 2020 with United State contributed the largest number of documents. Network analysis of different parameters shows a good potential of the topic in terms of research. Conclusions: Scopus keyword search outcome has 272 articles with English language having the largest number. Authors, documents, country, affiliation etc are statically analyzed and indicates the potential of the topic. Network analysis of different parameters indicates that, there is a lot of scope to contribute in the further research in terms of advanced algorithms of computer vision, deep learning, machine learning and explainable artificial intelligence.

Kute, DV, Pradhan, B, Shukla, N & Alamri, A 2021, 'Deep Learning and Explainable Artificial Intelligence Techniques Applied for Detecting Money Laundering–A Critical Review', IEEE Access, vol. 9, pp. 82300-82317.
View/Download from: Publisher's site
View description>>

Money laundering has been a global issue for decades, which is one of the major threat for economy and society. Government, regulatory and financial institutions are combating it together in their respective capacity, however still billions of dollars in fines by authorities make the headlines in the news. High-speed internet services have enabled financial institutions to deliver better customer experience through multi-channel engagements, which has led to exponential growth in transactions and new avenues for laundering the money for fraudsters. Literature shows the usage of statistical methods, data mining and Machine Learning (ML) techniques for money laundering detection, but limited research on Deep Learning (DL) techniques, primarily due to lack of model interpretability and explainability of the decisions made. Several studies are conducted on application of ML for Anti-Money Laundering (AML), and Explainable Artificial Intelligence (XAI) techniques in general, but lacks the study on usage of DL techniques together with XAI. This paper aims to review the current state-of-the-art literature on DL together with XAI for identifying suspicious money laundering transactions and identify future research areas. Key findings of the review are, researchers have preferred variants of Convolutional Neural Networks, and AutoEncoder; graph deep learning together with natural language processing is emerging as an important technology for AML; XAI use is not seen in AML domain; 51% ML methods used in AML are non-interpretable, 58% studies used sample of old real data; key challenges for researchers are access to recent real transaction data and scarcity of labelled training data; and data being highly imbalanced. Future research directions are, application of XAI techniques to bring-out explainability, graph deep learning using natural language processing (NLP), unsupervised and reinforcement learning to handle lack of labelled data; and joint research progra...

Li, B, Guo, T, Li, R, Wang, Y, Ou, Y & Chen, F 2021, 'Delay Propagation in Large Railway Networks with Data-Driven Bayesian Modeling', Transportation Research Record: Journal of the Transportation Research Board, vol. 2675, no. 11, pp. 472-485.
View/Download from: Publisher's site
View description>>

Reliability and punctuality are the key evaluation criteria in railway service for both passengers and operators. Delays spanning over spatial and temporal dimensions significantly affect the reliability and punctuality level of train operation. The optimization of capacity utilization and timetable design requires the prediction of the reliability and punctuality level of train operations, which is determined by train delays and delay propagation. To predict the punctuality level of train operations, the distributions of arrival and departure delays must be estimated as realistically as possible by taking into account the complex railway network structure and different types of delays caused by route conflict and connected trips. This paper aims to predict the propagation of delays on the railway network in the Greater Sydney area by developing a conditional Bayesian model. In the model, the propagation satisfies the Markov property if one can predict future delay propagation in the network based solely on its present state just as well as one could knowing the process’s full history, so that it is independent of such historical procedures. Meanwhile, we consider the throughput estimation for the cases of delay caused by interchange line conflicts and train connection in this model. To the best of the authors’ knowledge, this is the first work of data-driven delay propagation modeling that examines both spatial and temporal dimensions under four different scenarios for railway networks. Implementation on real-world railway network operation data shows the feasibility and accuracy of the proposed model compared with traditional probability models.

Li, H, Askari, M, Li, J, Li, Y & Yu, Y 2021, 'A novel structural seismic protection system with negative stiffness and controllable damping', Structural Control and Health Monitoring, vol. 28, no. 10.
View/Download from: Publisher's site
View description>>

In this paper, an innovative controllable negative stiffness system (CNSS) integrating adaptive negative stiffness and controllable damping characteristics is proposed to realise desirable vibration protection and improve adaptability, hence being effective to various earthquakes. The force-displacement relationship of the CNSS is derived as the forward model to describe its nonlinear properties. Three representative control algorithms, i.e., Linear Quadratic Regular (LQR) control, H∞ control and Sliding Mode (SM) control, are utilised for the CNSS to attain optimal control force. Based on the Takagi-Sugeno-Kang (TSK) Fuzzy inference system optimised by Non-Dominated Sorted Genetic Algorithm II (NSGAII), a novel inverse model is proposed accordingly to obtain input current according to the required control force and real-time system responses. To demonstrate the feasibility and efficiency of the CNSS for structural seismic protection, a numerical case study is conducted on a three-storey building model with CNSS installed on its first floor. Four scaled benchmark earthquakes are employed as excitations for the case study. Ten evaluation criteria are adopted to assess and verify the performance of the CNSS, and comparisons are made with that of uncontrolled and passive controlled systems. The numerical results indicate that the proposed CNSS can significantly improve the vibration control performance on all evaluation criteria simultaneously in comparison with the other two conventional systems. In addition to having good suppression effects on peak floor displacement and peak inter-storey drift, the CNSS with the SM controller demonstrates superior performance on mitigating peak structure shear and peak acceleration response of the first floor.

Li, H, Li, J, Yu, Y & Li, Y 2021, 'Modified Adaptive Negative Stiffness Device with Variable Negative Stiffness and Geometrically Nonlinear Damping for Seismic Protection of Structures', International Journal of Structural Stability and Dynamics, vol. 21, no. 8, pp. 2150107-2150107.
View/Download from: Publisher's site
View description>>

Adaptive negative stiffness device is one of the promising seismic protection devices since it can generate seismic isolation effect through negative stiffness when it is mostly needed and achieve similar vibration mitigation as a semi-active control device. However, the adaptive negative stiffness device generally combined with linear viscous damping underpins the drawback of degrading the vibration isolation effect during the high-frequency region. In this paper, a modified adaptive negative stiffness device (MANSD) with the ability to provide both lateral negative stiffness and nonlinear damping by configuring linear springs and linear viscous dampers is proposed to address the above issue. The negative stiffness and nonlinear damping are realised through a linkage mechanism. The fundamentals and dynamic characteristics of a SDOF system with such a device are analyzed and formulated using the Harmonic Balance Method, with a special focus on the amplitude–frequency response and transmissibility of the system. The system with damping nonlinearity as a function of displacement and velocity has been proven to have attractive advantages over linear damping in reducing the transmissibility in the resonance region without increasing that in the high-frequency region. The effect of nonlinear damping on suppressing displacement and acceleration responses is numerically verified under different sinusoidal excitations and earthquakes with different intensities. Compared with linear damping, the MANSD with nonlinear damping could achieve additional reductions on displacement and acceleration under scaled earthquakes, especially intensive earthquakes.

Li, H, Yu, Y, Li, J & Li, Y 2021, 'Analysis and optimization of a typical quasi-zero stiffness vibration isolator', Smart Structures and Systems, vol. 27, no. 3, pp. 525-536.
View/Download from: Publisher's site
View description>>

To isolate vibration at a low-frequency range and at the same time to provide sufficient loading support to the isolated structure impose a challenge in vibration isolation. Quasi-zero stiffness (QZS) vibration isolator, as a potential solution to the challenge, has been widely investigated due to its unique property of high-static & low-dynamic stiffness. This paper provides an in-depth analysis and potential optimization of a typical QZS vibration isolator to illustrate the complexity and importance of design optimization. By carefully examining the governing fundamentals of the QZS vibration isolator, a simplified approximation of force and stiffness relationship is derived to enable the characteristic analysis of the QZS vibration isolator. The explicit formulae of the amplitude-frequency response (AFR) and transmissibility of the QZS vibration isolator are obtained by employing the Harmonic Balance Method. The transmissibility curves under force excitation with different values of nonlinear coefficient, damping ratio, and amplitude of excitation are further investigated. As the result, an optimization of the structural parameter has been demonstrated using a comprehensive objective function with considering multiple dynamic characteristic parameters simultaneously. Finally, the genetic algorithm (GA) is adopted to minimise the objective function to obtain the optimal stiffness ratios under different conditions. General recommendations are provided and discussed in the end.

Li, H, Yu, Y, Li, J, Li, Y & Askari, M 2021, 'Multi-objective optimisation for improving the seismic protection performance of a multi-storey adaptive negative stiffness system based on modified NSGA-II with DCD', Journal of Building Engineering, vol. 43, pp. 103145-103145.
View/Download from: Publisher's site
View description>>

Installing adaptive negative stiffness devices (ANSD) on multiple storeys of a building structure to develop a smart seismic protection system, namely multi-storey adaptive negative stiffness system (MANSS), is an effective approach to mitigate the structural responses under earthquake events. However, like other base isolators, the MANSS cannot reach its full potential to address the contradiction between effective vibration isolation and suppression, due to improper setting of structural parameters. In this paper, a comprehensive multi-objective nonlinear optimisation for obtaining the optimal structural parameters of the ANSD is conducted to effectively improve the performance of MANSS on seismic protection. After the characteristic analysis of the ANSD, six optimisation variables and one constraint are determined. Four objective functions are defined by considering the two adverse requirements simultaneously, i.e. enhancing vibration isolation and improving vibration suppression. The highly nonlinear optimisation problem can be adequately resolved by the modified non-dominated sorting genetic algorithm type II (NSGA-II) with dynamic crowding distance (DCD) algorithm, which generates a series of Pareto front, hence obtaining the optimal parameter combination. Furthermore, to verify and evaluate the feasibility and capacity of the proposed optimisation method, a numerical case study is conducted based on a five-storey benchmark building model subjected to six different earthquakes. Four systems, including bare building, bare building with ANSD on the first floor, bare building with dampers on each floor and preliminarily designed MANSS are also investigated to conduct comparative analysis. The results demonstrate that the optimised MANSS can largely reduce both peak and root mean square (RMS) values of inter-storey drift, acceleration, and displacement responses of the benchmark building under all six earthquakes, which proves the effectiveness and su...

Li, M, Chen, Q, Wen, K, Nimbalkar, S & Dai, R 2021, 'Improved Vacuum Preloading Method Combined with Sand Sandwich Structure for Consolidation of Dredged Clay-Slurry Fill and Original Marine Soft Clay', International Journal of Geomechanics, vol. 21, no. 10, pp. 04021182-04021182.
View/Download from: Publisher's site

Li, P, Li, W, Sun, Z, Shen, L & Sheng, D 2021, 'Development of sustainable concrete incorporating seawater: A critical review on cement hydration, microstructure and mechanical strength', Cement and Concrete Composites, vol. 121, pp. 104100-104100.
View/Download from: Publisher's site
View description>>

Many countries are experiencing freshwater crises due to the increasing growth of the population together with the infrastructure construction that is aligned with the needs of freshwater for concrete production. There are also deficiencies in freshwater in many coastal areas where seawater is more accessible. To reduce unnecessary resource-wasting and meanwhile drive sustainable development in the construction industry, great efforts have been made to utilize seawater as the alternative mixing water for concrete casting, which presents potential economical and environmental benefits in the coastal and island regions. This paper comprehensively reviews the current studies on the predominant performance differences between seawater-mixed and conventional concretes with freshwater. Particular attention is paid to the chloride-induced hydration mechanism due to the chloride ions in seawater. The main findings of this review reveal that although harmful ingredients in seawater may weaken some of the concrete performances, applying proper curing conditions and adding moderate additives and admixtures could significantly and effectively mitigate these defects in properties. However, the unstable chloride binding ability in cement hydrates cannot eliminate the risk of rebar corrosion caused by chlorides in seawater, resulting in a limited scope of practical application. Finally, some trade-offs are recommended in using seawater in concrete, suggesting prospects of applications in the future construction industry. This study guides for the safer use of seawater in sustainable concrete through reviewing the advanced research progress.

Li, S, Li, Y & Li, J 2021, 'Thixotropy of magnetorheological gel composites: Experimental testing and modelling', Composites Science and Technology, vol. 214, pp. 108996-108996.
View/Download from: Publisher's site

Li, W, Dong, W, Castel, A & Sheng, D 2021, 'Self-sensing cement-based sensors for structural health monitoring toward smart infrastructure', Journal and Proceedings of the Royal Society of New South Wales, vol. 154, pp. 24-32.
View description>>

Since its first appearance more than 100 years ago, concrete has had a significant impact on urban development — buildings, roads, bridges, ports, tunnels, railways and other structures. While traditional concrete is a structural material without any function, a new branch of concrete technology has produced smart (or intelligent) concrete, with superior self-sensing capabilities that can detect stress, strain, cracks and damage, and monitor temperature and humidity. With the incorporation of functional conductive fillers, traditional concrete can exhibit electrical conductivity with intrinsic piezoresistivity. This piezoresistivity means that the electrical resistivity of concrete is synchronously altered under applied load or environmental factors. The self-sensing electrical resistivity thus obtained can be an index or parameter to detect stress or strain changes in concrete, or cracks and damage to concrete. On the other hand, because of the relationship between electrical resistivity, temperature and humidity, self-sensing concrete can also monitor environmental factors. This smart self-sensing concrete can therefore be a promising alternative to conventional sensors for monitoring structural health and detecting traffic information from concrete roads, all of which are critical to achieving smart automation in concrete infrastructures.

Li, W, Ji, J, Huang, L & Guo, Z 2021, 'Global dynamics of a controlled discontinuous diffusive SIR epidemic system', Applied Mathematics Letters, vol. 121, pp. 107420-107420.
View/Download from: Publisher's site
View description>>

In this work, we investigate the global dynamics of a controlled discontinuous diffusive SIR epidemic system under Neumann boundary conditions. We first establish the conditions for the existence of the solution and obtain the boundedness of the solution for the controlled discontinuous diffusive system. Then, under the framework of differential inclusion, we study the existence of constant equilibria of the controlled diffusive epidemic system. Furthermore, we discuss the global dynamical behaviour of the controlled discontinuous diffusive epidemic system.

Liu, C, Indraratna, B & Rujikiatkamjorn, C 2021, 'An analytical model for particle-geogrid aperture interaction', Geotextiles and Geomembranes, vol. 49, no. 1, pp. 41-44.
View/Download from: Publisher's site
View description>>

© 2020 The shear strength of geogrid-reinforced ballast is often dependent on the aperture size of geogrids and the nominal size of ballast. This paper presents a theoretical analysis based on probabilistic mechanics of how aperture size affects the interaction between particles and geogrid. Unlike past literature, in this study, the properties of the particle size distribution is analysed using a Weibull distribution. The probability of grain interlock is proposed to describe the interactive mechanisms between particles and geogrids based on the relative particle size, which is defined as the ratio of particle size to aperture size. The mathematical model is calibrated by a set of large-scale direct shear tests with almost single-size (highly uniform) ballast aggregates, and then validated by independent set of data taken from both literature and current study. The study concludes that more uniform particle size distribution increases the probability of grain interlock at the optimum aperture size but decreases it at non-optimum aperture sizes.

Liu, J, Li, H, Ji, J & Luo, J 2021, 'Bipartite Consensus Control for a Swarm of Robots', Journal of Dynamic Systems, Measurement, and Control, vol. 143, no. 1.
View/Download from: Publisher's site
View description>>

Abstract This paper studies the bipartite consensus problem of a swarm of robots whose dynamics are formulated by Lagrangian equations. Two distributed bipartite consensus control protocols are proposed for a swarm of robots without a leader or with a virtual leader. For the nonleader case, the networked Lagrangian system can reach static bipartite consensus under the control protocol developed, and the final convergent states can be explicitly determined by the specific structure of the Laplacian matrix associated with the cooperative–competitive network topology. For the virtual leader case, all the followers can track the leader's state in a bipartite formation to realize bipartite tracking consensus. Finally, the simulation results are given to verify the theoretical results.

Luo, S, Chu, VW, Li, Z, Wang, Y, Zhou, J, Chen, F & Wong, RK 2021, 'Multi-task learning by hierarchical Dirichlet mixture model for sparse failure prediction', International Journal of Data Science and Analytics, vol. 12, no. 1, pp. 15-29.
View/Download from: Publisher's site
View description>>

© 2020, Springer Nature Switzerland AG. Sparsity and noisy labels occur inherently in real-world data. Previously, strong assumptions were made by domain experts to use their experience and expertise to select parameters for their models. Similar approach has been adopted in machine learning for hyper-parameter setting. However, these assumptions are often subjective and are not necessarily the optimal choice. To address this problem, we propose a data-driven approach to automate model parameter learning via a Bayesian nonparametric formulation. We propose hierarchical Dirichlet process mixture model (HDPMM) as a multi-task learning framework. It is used to learn the common parameters across different datasets in the same industry. In our experiments, we verified the capability of HDPMM for multi-task learning in infrastructure failure predictions. It was done by combining HDPMM with hierarchical beta process, which is our failure prediction model. In particular, multi-task learning was used to gain additional knowledge from failure records of water supply networks managed by other utility companies to improve prediction accuracy of our model. Notably, we have achieved superior accuracy for sparse predictions than previous state-of-the-art models. Moreover, we have demonstrated the capability of our proposed model in supporting preventive maintenance of critical infrastructure.

Luo, Z, Li, W, Gan, Y, He, X, Castel, A & Sheng, D 2021, 'Nanoindentation on micromechanical properties and microstructure of geopolymer with nano-SiO2 and nano-TiO2', Cement and Concrete Composites, vol. 117, pp. 103883-103883.
View/Download from: Publisher's site
View description>>

Fly ash-based geopolymers incorporated with 2% nano-SiO2 (NS)/nano-TiO2 (NT) particles were subjected to microstructural and statistical nanoindentation analysis. With the addition of both types of nanoparticles, the compressive strength of geopolymer and the micromechanical properties of N-A-S-H gel were increased. NS exhibited higher reinforcement effect than NT on macro-strength. However, NT more significantly enhanced gel micromechanical properties. NT and especially the NS were found to have a positive effect on the early reaction rate of geopolymer. After 28 days, the gel proportion obtained by Backscattered electron (BSE) images analysis was close values of 49.16%, 55.69% and 54.02% for reference sample and NS, NT reinforced geopolymer, which were more than two times of that from the statistical nanoindentation. The effects of NS and NT on microstructure, gel proportion and gel micromechanical properties were discussed to reveal the macro-strength reinforcement mechanism. The results obtained from different techniques were also compared and discussed.

Mallick, SK, Das, P, Maity, B, Rudra, S, Pramanik, M, Pradhan, B & Sahana, M 2021, 'Understanding future urban growth, urban resilience and sustainable development of small cities using prediction-adaptation-resilience (PAR) approach', Sustainable Cities and Society, vol. 74, pp. 103196-103196.
View/Download from: Publisher's site
View description>>

Rapid urban proliferation is an indispensable and reciprocal issue in contemporary urban planning and development. This study envisages the prediction-adaptation-resilience (PAR) approach to analyze the future urban landscape resilience and sustainable development goals (SDGs). We have selected a small, unplanned growing up city, namely, Krishnanagar urban agglomeration (KUA), in India, to apply the PAR approach. Therefore, land use land cover map has been prepared for 2000, 2010, and 2020. The result shows the built-up area has been increased most in past 20 years, from 6.36 km2 to 13.23 km2. Then, the cellular automata-Markov chain model is applied to predict the future potential urban development surface for 2030 and 2040. The receiver operating characteristic (ROC) curve shows 83.6% success rate between the predicted and actual map of CA-Markov. The prediction map of 2030 and 2040 shows that the built-up area continuously expands (13.23 km2 to 16.52 km2) towards KUA's surrounding regions. Consequently, other decreasing land classes will be a threat to SDGs and urban resilience. So, people of KUA are adopting the changing hostile nature of urbanisation and urban vulnerability. Hence, this study will help the local administration to make a proper urban planning and adaptation strategies by maintaining good urban governance to achieve 8 SDGs of UN's 2030 Agenda in future.

Mao, Y-Z, Yang, J-X & Ji, J-C 2021, 'Theoretical and experimental study of surface texturing with laser machining', Advances in Manufacturing, vol. 9, no. 4, pp. 538-557.
View/Download from: Publisher's site
View description>>

To explore the forming process and mechanism of the surface texture of laser micropits, this paper presents the thermal model of laser machining based on the Neumann boundary conditions and an investigation on the effects of various parameters on the processing. The surface profile and quality of the formed micropits were analyzed using NanoFocus 3D equipment through a design of experiment (DOE). The results showed that more intense melting and splashing occurred with higher power density and narrower pulse widths. Moreover, the compressive stress is an important indicator of the damage effects, and the circumferential thermal stress is the primary factor influencing the diameter expansion. During the process of laser machining, not only did oxides such as CuO and ZnO generate, the energy distribution also tended to decrease gradually from region #1 to region #3 based on an energy dispersive spectrometer (EDS) analysis. The factors significantly affecting the surface quality of the micropit surface texture are the energy and pulse width. The relationship between taper angle and energy is appropriately linear. Research on the formation process and mechanism of the surface texture of laser micropits provides important guidance for precision machining.

Mehrabi, P, Shariati, M, Kabirifar, K, Jarrah, M, Rasekh, H, Trung, NT, Shariati, A & Jahandari, S 2021, 'Effect of pumice powder and nano-clay on the strength and permeability of fiber-reinforced pervious concrete incorporating recycled concrete aggregate', Construction and Building Materials, vol. 287, pp. 122652-122652.
View/Download from: Publisher's site

Meilianda, E, Lavigne, F, Pradhan, B, Wassmer, P, Darusman, D & Dohmen-Janssen, M 2021, 'Barrier Islands Resilience to Extreme Events: Do Earthquake and Tsunami Play a Role?', Water, vol. 13, no. 2, pp. 178-178.
View/Download from: Publisher's site
View description>>

Barrier islands are indicators of coastal resilience. Previous studies have proven that barrier islands are surprisingly resilient to extreme storm events. At present, little is known about barrier systems’ resilience to seismic events triggering tsunamis, co-seismic subsidence, and liquefaction. The objective of this study is, therefore, to investigate the morphological resilience of the barrier islands in responding to those secondary effects of seismic activity of the Sumatra–Andaman subduction zone and the Great Sumatran Fault system. Spatial analysis in Geographical Information Systems (GIS) was utilized to detect shoreline changes from the multi-source datasets of centennial time scale, including old topographic maps and satellite images from 1898 until 2017. Additionally, the earthquake and tsunami records and established conceptual models of storm effects to barrier systems, are corroborated to support possible forcing factors analysis. Two selected coastal sections possess different geomorphic settings are investigated: (1) Lambadeuk, the coast overlying the Sumatran Fault system, (2) Kuala Gigieng, located in between two segments of the Sumatran Fault System. Seven consecutive pairs of comparable old topographic maps and satellite images reveal remarkable morphological changes in the form of breaching, landward migrating, sinking, and complete disappearing in different periods of observation. While semi-protected embayed Lambadeuk is not resilient to repeated co-seismic land subsidence, the wave-dominated Kuala Gigieng coast is not resilient to the combination of tsunami and liquefaction events. The mega-tsunami triggered by the 2004 earthquake led to irreversible changes in the barrier islands on both coasts.

Mirzaei, S, Vafakhah, M, Pradhan, B & Alavi, SJ 2021, 'Flood susceptibility assessment using extreme gradient boosting (EGB), Iran', Earth Science Informatics, vol. 14, no. 1, pp. 51-67.
View/Download from: Publisher's site
View description>>

Flood occurs as a result of high intensity and long-term rainfalls accompanied by snowmelt which flow out of the main river channel onto the flood prone areas and damage the buildings, roads, and facilities and cause life losses. This study aims to implement extreme gradient boosting (EGB) method for the first time in flood susceptibility modelling and compare its performance with three advanced benchmark models including Frequency Ratio (FR), Random Forest (RF), and Generalized Additive Model (GAM). Flood susceptibility map is an efficient tool to make decision for flood control. To do this, the altitude, slope degree, profile curvature, topographic wetness index (TWI), distance from rivers, normalized difference vegetation index, plan curvature, rainfall, land use, stream power index, and lithology were fed to the models. To run the models, 243 flood locations were detected by field surveys and national reports. The same number of locations were randomly created in the study regions and considered as non-flood locations. The flood and non-flood locations were split in 70% ratio for the training dataset and 30% ratio for the testing dataset. Both flood and non-flood locations were fed into the models and output flood susceptibility maps were produced. In order to evaluate the performance of the algorithms, receiver operating characteristics (ROC) curve was implemented. The results of the current research show that the RF model and EGB have the best performances with the area under ROC curve (AUC) of 0.985, and 0.980, followed by the GAM and FR algorithms with AUC values of 0.97, and 0.953, respectively. The results of variable importance by the RF model show that distance from rivers has an important influence on flood susceptibility mapping (FSM), followed by profile curvature, slope, TWI, and altitude. Considering the high performances of the RF and EGB models in flood susceptibility modelling, application of these models is recommended for such studies.

Naghibi, SA, Hashemi, H & Pradhan, B 2021, 'APG: A novel python-based ArcGIS toolbox to generate absence-datasets for geospatial studies', Geoscience Frontiers, vol. 12, no. 6, pp. 101232-101232.
View/Download from: Publisher's site

Nandanwar, L, Shivakumara, P, Kanchan, S, Basavaraja, V, Guru, DS, Pal, U, Lu, T & Blumenstein, M 2021, 'DCT-phase statistics for forged IMEI numbers and air ticket detection', Expert Systems with Applications, vol. 164, pp. 114014-114014.
View/Download from: Publisher's site
View description>>

New tools have been developing with the intention of having more flexibility and greater user-friendliness for editing the images and documents in digital technologies, but, unfortunately, they are also being used for manipulating and tampering information. Examples of such crimes include creating forged International Mobile Equipment Identity (IMEI) numbers which are embedded on mobile packages and inside smart mobile cases for illicit activities. Another example of such crimes is altering the name or date on air tickets for breaching security at the airport. This paper presents a new expert system for detecting forged IMEI numbers as well as altered air ticket images. The proposed method derives the phase spectrum using the Discrete Cosine Transform (DCT) to highlight the suspicious regions; it is unlike the phase spectrum from a Fourier transform, which is ineffective due to power spectrum noise. From the phase spectrum, our method extracts phase statistics to study the effect of distortions introduced by forgery operations. This results in feature vectors, which are fed to a Support Vector Machine (SVM) classifier for detection of forged IMEI numbers and air ticket images. Experimental results on our dataset of forged IMEI numbers (which is created by us for this work), on altered air tickets, on benchmark datasets of video caption text (which is tampered text), and on altered receipts of the ICPR 2018 FDC dataset, show that the proposed method is robust across different datasets. Furthermore, comparative studies of the proposed method with the existing methods on the same datasets show that the proposed method outperforms the existing methods. The dataset created will be available freely on request to the authors.

Nandanwar, L, Shivakumara, P, Pal, U, Lu, T & Blumenstein, M 2021, 'A New Hybrid Method for Caption and Scene Text Classification in Action Video Images', International Journal of Pattern Recognition and Artificial Intelligence, vol. 35, no. 12.
View/Download from: Publisher's site
View description>>

Achieving a better recognition rate for text in action video images is challenging due to multiple types of text with unpredictable actions in the background. In this paper, we propose a new method for the classification of caption (which is edited text) and scene text (text that is a part of the video) in video images. This work considers five action classes, namely, Yoga, Concert, Teleshopping, Craft, and Recipes, where it is expected that both types of text play a vital role in understanding the video content. The proposed method introduces a new fusion criterion based on Discrete Cosine Transform (DCT) and Fourier coefficients to obtain the reconstructed images for caption and scene text. The fusion criterion involves computing the variances for coefficients of corresponding pixels of DCT and Fourier images, and the same variances are considered as the respective weights. This step results in Reconstructed image-1. Inspired by the special property of Chebyshev-Harmonic-Fourier-Moments (CHFM) that has the ability to reconstruct a redundancy-free image, we explore CHFM for obtaining the Reconstructed image-2. The reconstructed images along with the input image are passed to a Deep Convolutional Neural Network (DCNN) for classification of caption/scene text. Experimental results on five action classes and a comparative study with the existing methods demonstrate that the proposed method is effective. In addition, the recognition results of the before and after the classification obtained from different methods show that the recognition performance improves significantly after classification, compared to before classification.

Nguyen, TT, Indraratna, B & Singh, M 2021, 'Dynamic parameters of subgrade soils prone to mud pumping considering the influence of kaolin content and the cyclic stress ratio', Transportation Geotechnics, vol. 29, pp. 100581-100581.
View/Download from: Publisher's site

Nguyen, V, Pineda, JA, Romero, E & Sheng, D 2021, 'Influence of soil microstructure on air permeability in compacted clay', Géotechnique, vol. 71, no. 5, pp. 373-391.
View/Download from: Publisher's site
View description>>

This paper describes an experimental study aimed at evaluating the influence of soil microstructure on air permeability in compacted clay. Air permeability measurements, estimated using the gas pressure decay method, were carried out for a wide range of compaction states. The evolution of the air permeability during wetting and drying paths was also evaluated. The experimental results show that, for an increase in the as-compacted degree of saturation, air permeability may either increase or decrease depending on the as-compacted dry density. Air permeability increases with increasing the degree of saturation in loose specimens, whereas the opposite trend is observed for dense specimens. Microstructural analysis, carried out using mercury intrusion porosimetry (MIP) tests, shows a strong dependency of the air permeability on the as-compacted soil microstructure. This behaviour is also noticed in specimens that experienced a large variation in the degree of saturation during wetting and drying. Microstructural data indicate that air permeability is mainly controlled by large pores that display high connectivity. The degree of saturation plays a dual role in soil microstructure which, in turn, affects the air permeability. Denser specimens (dry density ≥ 1·5 Mg/m3) show a reduction in keff due to the expansion of the clay aggregates with increasing the as-compacted degree of saturation. The increase in the as-compacted degree of saturation in loose samples (dry density ≤1·3 Mg/m3) produces an enhancement in the proportion of macro pores, thus increasing keff, as a consequence of modifications in the pore size distribution. A threshold value has been identified, above which further increase in degree of saturation causes a reduction in the proportion of macro pores, and therefore in keff. A new proposal for estimating the air permeability is pr...

Ni, Q, Ji, JC, Feng, K & Halkon, B 2021, 'A novel correntropy-based band selection method for the fault diagnosis of bearings under fault-irrelevant impulsive and cyclostationary interferences', Mechanical Systems and Signal Processing, vol. 153, pp. 107498-107498.
View/Download from: Publisher's site
View description>>

Demodulation analysis is one of the most effective methods for bearing fault diagnosis. However, in practical applications, the interferences from ambient noises or other rotating components may create great challenges to demodulation analysis and thus decrease its effectiveness. Generally, a selection procedure for the most informative frequency band (IFB) is usually implemented in advance to extract the fault features that are hidden by the interferences. The fast kurtogram (FK) has been utilized as a benchmark for the IFB selection. Although designed to identify the most impulsive part of the signal, the FK is inevitably affected by the fault-irrelevant impulsive and cyclostationary interferences due to the dual sensitiveness to the impulsiveness and cyclostationarity of the kurtosis, and thus it may produce a misleading band for demodulation. To address this issue, a novel and robust IFB selection method based on the fault energy of correntropy (named FECgram) is proposed in this paper to replace the FK, through which the IFB can capture the fault symptom without being influenced by the fault-irrelevant impulsive and cyclostationary interferences. The superiority of the FECgram in combination with the squared envelope spectrum (SES) is validated on both simulation data and three different challenging experimental datasets.

Nikraftar, Z, Mostafaie, A, Sadegh, M, Afkueieh, JH & Pradhan, B 2021, 'Multi-type assessment of global droughts and teleconnections', Weather and Climate Extremes, vol. 34, pp. 100402-100402.
View/Download from: Publisher's site

Oberst, S, Halkon, B, Ji, J & Brown, T 2021, 'Preface', Vibration Engineering for a Sustainable Future: Numerical and Analytical Methods to Study Dynamical Systems, Vol. 3, pp. v-vi.

Oberst, S, Halkon, B, Ji, J & Brown, T 2021, 'Preface', Vibration Engineering for a Sustainable Future: Experiments, Materials and Signal Processing, Vol. 2, vol. 2, pp. v-vi.

Oberst, S, Martin, R, Halkon, BJ, Lai, JCS, Evans, TA & Saadatfar, M 2021, 'Submillimetre mechanistic designs of termite-built structures', Journal of The Royal Society Interface, vol. 18, no. 178, pp. 1-10.
View/Download from: Publisher's site
View description>>

Termites inhabit complex underground mounds of intricate stigmergic labyrinthine designs with multiple functions as nursery, food storage and refuge, while maintaining a homeostatic microclimate. Past research studied termite building activities rather than the actual material structure. Yet, prior to understanding how multi-functionality shaped termite building, a thorough grasp of submillimetre mechanistic architecture of mounds is required. Here, we identify for Nasutitermes exitiosus via granulometry and Fourier transform infrared spectroscopy analysis, preferential particle sizes related to coarse silts and unknown mixtures of organic/inorganic components. High-resolution micro-computed X-ray tomography and microindentation tests reveal wall patterns of filigree laminated layers and sub-millimetre porosity wrapped around a coarse-grained inner scaffold. The scaffold geometry, which is designed of a lignin-based composite and densely biocementitious stercoral mortar, resembles that of trabecula cancellous bones. Fractal dimension estimates indicate multi-scaled porosity, important for enhanced evaporative cooling and structural stability. The indentation moduli increase from the outer to the inner wall parts to values higher than those found in loose clays and which exceed locally the properties of anthropogenic cementitious materials. Termites engineer intricately layered biocementitious composites of high elasticity. The multiple-scales and porosity of the structure indicate a potential to pioneer bio-architected lightweight and high-strength materials.

Paryani, S, Neshat, A & Pradhan, B 2021, 'Improvement of landslide spatial modeling using machine learning methods and two Harris hawks and bat algorithms', The Egyptian Journal of Remote Sensing and Space Science, vol. 24, no. 3, pp. 845-855.
View/Download from: Publisher's site

Paryani, S, Neshat, A & Pradhan, B 2021, 'Spatial landslide susceptibility mapping using integrating an adaptive neuro-fuzzy inference system (ANFIS) with two multi-criteria decision-making approaches', Theoretical and Applied Climatology, vol. 146, no. 1-2, pp. 489-509.
View/Download from: Publisher's site
View description>>

Landslide is a type of slope process causing a plethora of economic damage and loss of lives worldwide every year. This study aimed to analyze spatial landslide susceptibility mapping in the Khalkhal-Tarom Basin by integrating an adaptive neuro-fuzzy inference system (ANFIS) with two multi-criteria decision-making approaches, i.e., the best-worst method (BWM) and the stepwise weight assessment ratio analysis (SWARA) techniques. For this purpose, the first step was to prepare a landslide inventory map, which was then divided randomly into the ratio of 70/30% for model training and validation. Thirteen conditioning factors were selected based on the previous studies and available data. In the next step, the BWM and the SWARA methods were utilized to determine the relationships between the sub-criteria and landslides. Finally, landslide susceptibility maps were generated by implementing ANFIS-BWM and ANFIS-SWARA ensemble models, and then several quantitative indices such as positive predictive value, negative predictive value, sensitivity, specificity, accuracy, root-mean-square-error, and the ROC curve were employed to appraise the predictive accuracy of each model. The results indicated that the ANFIS-BWM ensemble model (AUC = 75%, RMSE = 0.443) has better performance than ANFIS-SWARA (AUC = 73.6%, RMSE = 0.477). At the same time, the ANFIS-BWM model had the maximum sensitivity, specificity, and accuracy with values of 87.1%, 54.3%, and 40.7%, respectively. As a result, the BWM method was more efficient in training the ANFIS. Evidently, the generated landslide susceptibility maps (LSMs) can be very efficient in managing land use and preventing the damage caused by the landslide phenomenon.