Jaddoa, M, Gonzalez, L, Cuthbertson, H & Al-Jumaily, A 2020, 'Multi View Face Detection in Cattle Using Infrared Thermography' in Communications in Computer and Information Science, Springer International Publishing, pp. 223-236.
View/Download from: Publisher's site
Hagihghi, R, Razmjou, A, Orooji, Y, Warkiani, ME & Asadnia, M 2020, 'A miniaturized piezoresistive flow sensor for real-time monitoring of intravenous infusion', Journal of Biomedical Materials Research - Part B Applied Biomaterials, vol. 108, no. 2, pp. 568-576.
View/Download from: Publisher's site
View description>>
© 2019 Wiley Periodicals, Inc. Drug overdose (DO) is considered one of the current issues of intravenous (IV) infusion particularly resulting in serious injuries and deaths. Malfunction of infusion pumps is reported as the main cause of the drug overdose. Live monitoring and flow rate calculation by health professionals have been practicing to avoid DO. However, human errors and miscalculations are inevitable. A secondary measurement tool is required to avoid the risk of OD when infusion pump malfunctions cannot be detected immediately. Here, inspired by nature, we developed a real-time monitoring device through which an administrator can review, evaluate, and modify the IV infusion process. Our flow sensor possesses an erected polymer hair cell on a multi-layered silicon base forming from a patterned gold strained gauge layer on a piezoresistive liquid crystal polymer (LCP) membrane. Gold strain gauges on an LCP membrane have been used instead of a piezoresistive silicon membrane as the sensing element. The combination of gold strain gauges and LCP membrane provides better sensitivity than a piezoresistive silicon membrane of the same dimensions and thickness. We also miniaturized our biocompatible sensor such that it can be possible to install it inside the IV tube in contact with the liquid providing an in-suite online flow monitoring. The proposed LCP membrane sensor is compared with two commercially available IV sensors to validate its flow sensing ability. The experimental results demonstrate that the proposed sensor provides a low threshold detection limit of 5 mL/hr, which betters the performance of other commercial sensors at low flow rates.
Huang, Y, Song, R, Argha, A, Savkin, AV, Celler, BG & Su, SW 2020, 'Continuous Description of Human 3D Motion Intent Through Switching Mechanism', IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 28, no. 1, pp. 277-286.
View/Download from: Publisher's site
Wang, Y, Sayyadi, N, Zheng, X, Woods, TA, Leif, RC, Shi, B, Graves, SW, Piper, JA & Lu, Y 2020, 'Time-resolved microfluidic flow cytometer for decoding luminescence lifetimes in the microsecond region.', Lab on a chip.
View/Download from: Publisher's site
View description>>
Time-resolved luminescence detection using long-lived probes with lifetimes in the microsecond region have shown great potential in ultrasensitive and multiplexed bioanalysis. In flow cytometry, however, the long lifetime poses a significant challenge to measure wherein the detection window is often too short to determine the decay characteristics. Here we report a time-resolved microfluidic flow cytometer (tr-mFCM) incorporating an acoustic-focusing chip, which allows slowing down of the flow while providing the same detection conditions for every target, achieving accurate lifetime measurement free of autofluorescence interference. Through configuration of the flow velocity and detection aperture with respect to the time-gating sequence, a multi-cycle luminescence decay profile is captured for every event under maximum excitation and detection efficiency. A custom fitting algorithm is then developed to resolve europium-stained polymer microspheres as well as leukemia cells against abundant fluorescent particles, achieving counting efficiency approaching 100% and lifetime CVs (coefficient of variation) around 2-6%. We further demonstrate lifetime-multiplexed detection of prostate and bladder cancer cells stained with different europium probes. Our acoustic-focusing tr-mFCM offers a practical technique for rapid screening of biofluidic samples containing multiple cell types, especially in resource-limited environments such as regional and/or underdeveloped areas as well as for point-of-care applications.
Almansor, EH, Al-Ani, A & Hussain, FK 2020, 'Transferring Informal Text in Arabic as Low Resource Languages: State-of-the-Art and Future Research Directions', Advances in Intelligent Systems and Computing, pp. 176-187.
View/Download from: Publisher's site
View description>>
© 2020, Springer Nature Switzerland AG. Rapid growth in internet technology lead to increase the usage of social media platforms which make communication between users easier. Through the communication users used their daily languages which considered as non-standard language. The non-slandered text contains lots of noise, such as abbreviations, slang which used more in English languages and dialect words which are widely used in Arabic language. These texts face challenging using any natural language processing tools. Therefore, these texts need to be treated and transferred to be similar to their standard form. According to that the normalization and translation approach have been used to transfer the informal text. However, using these approach need large label or parallel datasets. While high resource languages such as English have enough parallel datasets, low resource languages such as Arabic is lack of enough parallel dataset. Therefore, in this paper we focus on the Arabic and Arabic dialects as a low resource language in the era of transferring non-stander text using normalization and translation approach.
Al-Tae, AA & Al-Jumaily, A 2020, 'Electrogastrogram Based Medical Applications an Overview and Processing Frame Work', Advances in Intelligent Systems and Computing, pp. 511-520.
View/Download from: Publisher's site
View description>>
© 2020, Springer Nature Switzerland AG. Surface Electrogastrogram (sEGG) examination is a noninvasive method based on recording the electrical signals of stomach muscles that can be used for investigation of a stomach wave propagation. sEGG records by placing electrodes on the abdominal skin. The recording of gastric dysrhythmias is an important tool for the clinician when patients have symptoms that suggest gastric dysfunction such as unexplained nausea, bloating, postprandial fullness, and early satiety. On the other hand, these upper gastrointestinal (GI) symptoms are nonspecific, and diseases or disorders of other organ such as esophagus, gallbladder, small bowel, colon, and non-GI diseases also can be considered. The progress of the EGG based application is very slow as EGG still suffers from several limitations. The aim of this study is to review the Electrogastrogram detection, analyzing methods and its application to enter the clinical world with recommendations for future study.
Masood, A & Al-Jumaily, A 2020, 'Orientation Sensitive Fuzzy C Means Based Fast Level Set Evolution for Segmentation of Histopathological Images to Detect Skin Cancer', Advances in Intelligent Systems and Computing, pp. 501-510.
View/Download from: Publisher's site
View description>>
© 2020, Springer Nature Switzerland AG. Malignant Melanoma in one of the most deadly skin cancer. In latest cancer diagnosis, pathologists examine biopsies for analysing cell morphology and tissue distribution for making diagnostic assessments. However, this process is quite subjective and has considerable variability. Automated computational diagnostic tools based on quantitative measures can help the diagnosis done by pathologists. The first and foremost step in automated histopathological image analysis is to properly segment the tissue structures such as nest, irregular distribution and melanocytic cells which indicate some disorder or potential cancer. This paper presents a novel technique for automatic segmentation of histopathological skin images, without user intervention. It is based on an innovative approach for utilizing the concepts of clustering and level set evolution. Firstly, the image is pre-processed to enhance the differentiating structural details. Then a novel orientation sensitive Fuzzy C mean clustering is used to generate the initial coarse segmentation and to calculate the controlling parameters for level set evolution. Later, refined fast level set based algorithm is used to finalize the segmentation process. Experimental analysis on a database of 150 histopathological images display the accuracy of the proposed method for detecting the melanocytic areas of the image, with true detection rate of 87.66% and Dice similarity coefficient of 0.88, when segmentation results are compared with images marked by expert pathologists.
Naji, M, Braytee, A, Anaissi, A, Sianaki, OA & Al-Ani, A 2020, 'Optimizing the Waiting Time for Airport Security Screening Using Multiple Queues and Servers', Advances in Intelligent Systems and Computing, pp. 496-507.
View/Download from: Publisher's site
View description>>
© 2020, Springer Nature Switzerland AG. Airport security screening processes are essential to ensure the safety of passengers and the aviation industry. Security at airports has improved noticeably in recent years through the utilisation of state-of-the-art technologies and highly trained security officers. However, maintaining a high level of security can be costly to operate and implement and can cause delays for passengers and airlines. In optimising a security process it is essential to strike a balance between time delays, security and reduced operation cost. This paper uses queueing theory as a method to study the impact of queue formation and the size of the security area on the average waiting time for the case of multi-lane parallel servers. An experiment is conducted to validate the proposed approach.
Wedyan, M, Al-Jumaily, A & Crippa, A 2020, 'Early Diagnose of Autism Spectrum Disorder Using Machine Learning Based on Simple Upper Limb Movements', Advances in Intelligent Systems and Computing, pp. 491-500.
View/Download from: Publisher's site
View description>>
© 2020, Springer Nature Switzerland AG. The importance of early diagnosis of autism that leads to early intervention such thing shall increase the results of treating it. The Autism Spectrum Disorder (ASD) affects the children activities and caused difficulties in interaction, impairments in communication, delayed speech, and weak eye contact. These activities used as the base for ASD diagnosis decision. Children move their upper limb before some of the other activities. Moving upper limb can be based for ASD diagnosis decision for autistic children. Such paper examines diagnosing the ASD that depends on motioning the children’s upper-limb aged between two and four years based on executing specific procedures and machine learning. The approach that such study utilized is both (LDA) Linear Discriminant Analysis in order to elicit the features and (SVM) Support Vector Machines for classifying thirty children such study selected fifteen autistic children out of fifteen non-autistic children by testing the collected data that are collected from doing an easy task. The results of such study have accomplished an optimal sortation accuracy of 100% and the average accuracy of 93.8%. Such outcomes provide more proof of simple brachium motioning that might be utilized in sorting poor performance of autistic children precisely.