Wireless Sensor Networks (WSNs) are vulnerable to faults because of their deployment in unpredictable and hazardous environments. This makes WSN prone to failures such as software, hardware, and communication failures. Due to the sensor’s limited resources and diverse deployment fields, fault detection in WSNs has become a daunting task. To solve this problem, Support Vector Machine (SVM), Convolutional Neural Network (CNN), Stochastic Gradient Descent (SGD), Multilayer Perceptron (MLP), Random Forest (RF), and Probabilistic Neural Network (PNN) classifiers are used for classification of gain, offset, spike, data loss, out of bounds, and stuck-at faults at the sensor level. Out of six faults, two of them are induced in the datasets, i.e., spike and data loss faults. The results are compared on the basis of their Detection Accuracy (DA), True Positive Rate (TPR), Matthews Correlation Coefficients (MCC), and F1-score. In this paper, a comparative analysis is performed among the classifiers mentioned previously on real-world datasets. Simulations show that the RF algorithm secures a better fault detection rate than the rest of the classifiers.

Decision fusion is used to fuse classification results and improve the classification accuracy in order to reduce the consumption of energy and bandwidth demand for data transmission. The decentralized classification fusion problem was the reason to use the belief function-based decision fusion approach in Wireless Sensor Networks (WSNs). With the consideration of improving the belief function fusion approach, we have proposed four classification techniques, namely Enhanced K-Nearest Neighbor (EKNN), Enhanced Extreme Learning Machine (EELM), Enhanced Support Vector Machine (ESVM), and Enhanced Recurrent Extreme Learning Machine (ERELM). In addition, WSNs are prone to errors and faults because of their different software, hardware failures, and their deployment in diverse fields. Because of these challenges, efficient fault detection methods must be used to detect faults in a WSN in a timely manner. We have induced four types of faults: offset fault, gain fault, stuck-at fault, and out of bounds fault, and used enhanced classification methods to solve the sensor failure issues. Experimental results show that ERELM gave the first best result for the improvement of the belief function fusion approach. The other three proposed techniques ESVM, EELM, and EKNN provided the second, third, and fourth best results, respectively. The proposed enhanced classifiers are used for fault detection and are evaluated using three performance metrics, i.e., Detection Accuracy (DA), True Positive Rate (TPR), and Error Rate (ER). Simulations show that the proposed methods outperform the existing techniques and give better results for the belief function and fault detection in WSNs.

Autism spectrum disorder (ASD) is a neurodevelopmental disorder associated with brain development that subsequently affects the physical appearance of the face. Autistic children have different patterns of facial features, which set them distinctively apart from typically developed (TD) children. This study is aimed at helping families and psychiatrists diagnose autism using an easy technique, viz., a deep learning-based web application for detecting autism based on experimentally tested facial features using a convolutional neural network with transfer learning and a flask framework. MobileNet, Xception, and InceptionV3 were the pretrained models used for classification. The facial images were taken from a publicly available dataset on Kaggle, which consists of 3,014 facial images of a heterogeneous group of children, i.e., 1,507 autistic children and 1,507 nonautistic children. Given the accuracy of the classification results for the validation data, MobileNet reached 95% accuracy, Xception achieved 94%, and InceptionV3 attained 0.89%.

Background The immunological factors involved in protection against the disease caused by SARS-CoV-2 are insufficiently defined and understood. However, previous knowledge pertaining to the related SARS virus and other human coronaviruses may prove useful. Population-based serosurveys measuring anti-SARS-CoV-2 antibodies may provide a pattern for estimating infection degrees and observing the development of the epidemic. In this study, we aimed to investigate the persistence of antibody against the SARS-CoV-2 in recovered patients in Al Madinah region of Saudi Arabia. Materials and methods A total of 150 recovered COVID-19 patients participated in this study. All the patients tested positive for the presence of SARS-CoV-2 RNA, using qualitative RT-PCR. An ELISA was used to measure anti-Spike (S) IgG antibodies in serum samples and screen for their persistence at various time points post-infection. Results The patients were categorized as asymptomatic (27.3%), mild (28%) and moderate (44.7%) according to the disease severity. Amongst them, 35.3% were females (n=53) and 64.7% were males (n=97). Significant anti-S IgG antibody levels were observed among the different groups, with the patients in moderate group exhibiting the highest levels followed by the mild group; while the lowest levels were detected among the asymptomatic. There was a significant positive correlation between the patients’ age and anti-S IgG antibody concentrations (Pearson r=0.45; p<0.001). Conclusion Our findings provide a solid evidence to support the use of an anti-S IgG ELISA as a diagnostic tool to indicate SARS-CoV-2 infection. IgG seropositivity was sustained in recovered patients up to a hundred days' post-infection, the latest time point for antibody measurement in our study. Ours is the first report in Saudi Arabia to investigate the durability of humoral immune response in recovered COVID-19 patients.

Most consumers rely on online reviews when deciding to purchase e-commerce services or products. Unfortunately, the main problem of these reviews, which is not completely tackled, is the existence of deceptive reviews. The novelty of the proposed system is the application of opinion mining on consumers’ reviews to help businesses and organizations continually improve their market strategies and obtain an in-depth analysis of the consumers’ opinions regarding their products and brands. In this paper, the long short-term memory (LSTM) and deep learning convolutional neural network integrated with LSTM (CNN-LSTM) models were used for sentiment analysis of reviews in the e-commerce domain. The system was tested and evaluated by using real-time data that included reviews of cameras, laptops, mobile phones, tablets, televisions, and video surveillance products from the Amazon website. Data preprocessing steps, such as lowercase processing, stopword removal, punctuation removal, and tokenization, were used for data cleaning. The clean data were processed with the LSTM and CNN-LSTM models for the detection and classification of the consumers’ sentiment into positive or negative. The LSTM and CNN-LSTM algorithms achieved an accuracy of 94% and 91%, respectively. We conclude that the deep learning techniques applied here provide optimal results for the classification of the customers’ sentiment toward the products.