Archive-based coronavirus herd immunity algorithm for optimizing weights in neural networks.

The success of the supervised learning process for feedforward neural networks, especially multilayer perceptron neural network (MLP), depends on the suitable configuration of its controlling parameters (i.e., weights and biases). Normally, the gradient descent method is used to find the optimal values of weights and biases. The gradient descent method suffers from the local optimal trap and slow convergence. Therefore, stochastic approximation methods such as metaheuristics are invited. Coronavirus herd immunity optimizer (CHIO) is a recent metaheuristic human-based algorithm stemmed from the herd immunity mechanism as a way to treat the spread of the coronavirus pandemic. In this paper, an external archive strategy is proposed and applied to direct the population closer to more promising search regions. The external archive is implemented during the algorithm evolution, and it saves the best solutions to be used later. This enhanced version of CHIO is called ACHIO. The algorithm is utilized in the training process of MLP to find its optimal controlling parameters thus empowering their classification accuracy. The proposed approach is evaluated using 15 classification datasets with classes ranging between 2 to 10. The performance of ACHIO is compared against six well-known swarm intelligence algorithms and the original CHIO in terms of classification accuracy. Interestingly, ACHIO is able to produce accurate results that excel other comparative methods in ten out of the fifteen classification datasets and very competitive results for others.

Data-Driven Resilient Load Forecasting Model for Smart Metered Distribution System

The change in the electricity demand pattern globally due to sudden extreme weather conditions or situations like COVID 19 pandemic has brought unanticipated challenges for the electric utilities and operators around the world. This work primarily deals with the issue of load forecasting during such type of high impact low frequency (HILF) events. In this paper, we propose a novel resilient short-term load forecasting model capable of producing good forecasting performance for normal as well as critical situations during the COVID 19 pandemic and will also be useful for load forecasting for other HILF situations like natural calamity effect on load demand of the power system. The proposed method uses a feed-forward neural network (FFNN) with an added training feature named resiliency factor to forecast load in both regular and special scenarios. The resiliency factor for any type of node in the distribution system is decided by the power utility using the historical data and declared in advance. The proposed model is tested using the smart metered data available from a real-life distribution grid of an academic cum residential campus. The model is giving satisfactory results for both normal as well as COVID scenario for the said network. © 2023 Taylor & Francis Group, LLC.

Knowledge Retrieval using Question Answering approach on Epidemiology data

The tried and tested way for effective Knowledge Retrieval is by posting questions and retrieving data from the huge information repository. In the recent past the prevalence of pandemics and the spread of COVID-19, has led people to rigorously question the various forms of epidemiology data available on different sources. In general, the amount of information gathered is proportionate to the questioning patterns by the knowledge seeker. Question answering (QA) system is useful during unexpected situations, especially during a pandemic. In this paper, we have proposed a Knowledge Retrieval Question Answering system (KRQA) for answering the queries of users related to COVID-19. The KRQA system is divided into two modules. The first module consists of preprocessing (tokenization, stemming, bag of words) of the question to produce a word vector. The second module involves building, training, and testing the data repository. Feedforward neural network is used to extract the most relevant answer from a repository of all possible answers. The volume and quality of information about the pandemic scenario around the world are increased at a tremendous rate. Hence our work focuses on effective knowledge retrieval using question and answering approach. Our experimental results are found to give better results based on Percentage closeness, precision, and recall parameters. KRQA has the novelty of retrieving more relevant answers with good quality. © 2022 IEEE.

Image Classification of Coronavirus (COVID-19) Using CT Scan Images with Transfer Learning Method

Coronavirus Disease 2019 better known as COVID-19 is an infection caused by Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2). Coronavirus is a virus that attacks the human respiratory system. World Health Organization (WHO) has declared this viral infection as global pandemic. An alternative way to diagnose the virus is by quick and accurate screening using images Chest Computed Tomography Scans (CT Scans) in humans. This research discuss about classifier comparison for CT image classification indicated COVID-19 and non COVID. Using Visual Geometry Group-19's (VGG-19) and ResNet-50 architecture for transfer learning to get extraction features. Images resized to a size 224 × 224. Using 3 classifier, that is k-nearest neighbor, logistic regression and feedforward neural networks. This research uses 500 principal component with Principal Component Analysis technique to reduce dimensions after being flattened. This research shows the best classifier is logistic regression from the results of the VGG-19 feature extraction, which can produce 88% accuracy, 80.9% specificity, 96.9% sensitivity, 83.7% f2-score. © 2022 IEEE.

Combining Linear Regressions to Determine the Future of the Covid in Mexico from the News

This paper presents an approach to determine the Semaphore Covid in Mexico from the news to participate in the Rest-Mex 2022 evaluation forum. The purpose of the task is to determine the covid semaphore color (red, orange, yellow, and green) in different time spaces. The proposed approach consists of two main steps. First, to generate a list of topics of the news, and second, to implement several linear regressions methods in order to these results serve to feed a deep neural network. For the first step, the LDA algorithm was implemented, and for the second, well-known methods such as Lasso, Ridge, Lars, among others, were utilized. With this approach, a weighted average of 0.48 was obtained, which is considerably higher than the baseline proposed by the organizers, which is 0.12. The best result to classify the semaphore was two weeks in the future with 0.56 of F-measure. © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

CSDLEEG: Identifying Confused Students Based on EEG Using Multi-View Deep Learning

Distance learning has dramatically increased in recent years because of advanced technology. In addition, numerous universities had to offer courses in online mode in 2020 and 2021 because of the COVID-19 pandemic. However, there are more challenges in distance learning than in the traditional learning method (e.g., feedback and interaction). Recently, researchers started using simple EEG headsets to identify confused students during online courses based on machine learning approaches. However, they faced unpleasant accuracy using traditional machine learning algorithms or nondeep neural networks. In this paper, we present a data-driven approach based on a multi-view deep learning technique called CSDLEEG to identify confused students. We employ the students' demographic information and EEG signals to feed our novel neural networks. The results show that our proposed approach is superior to state-of-the-art methods for 98% accuracy and 98% F1-score. © 2022 IEEE.

Diagnosis of Covid 19 disease, flu, allergies, colds

In 2020 and by spreading the Covid 19 all over the world, one of the most challenging issues is how to distinguish Covid 19 from similar sicknesses since Covid 19 has lots of similar symptoms in comparison between allergies, colds and flu. Another way to distinguish Covid 19 is testing but it has some challenges, for example in some testing, the accuracy of the test is 50 percent and another test which have more accurate result, some days are needed to provide the result in some developing countries and this can be dangerous if the person has Covid 19. There will be great if we can distinguish the Covid 19 from the patient's symptoms and in this research, an artificial neural network is trained to distinguish the Covid 19 just by the patient's symptoms. For this purpose different types of supervised learning algorithms are implemented to find the best result for classification. We have focused on the symptoms of each patient and assumed them as inputs for our models and the output is the type of sickness. The structure which is used for this neural network is a multilayer feed-forward neural network. © 2022 IEEE.

Covid-19 Detection by Wavelet Entropy and Cat Swarm Optimization

The rapid global spread of COVID-19 poses a huge threat to human security. Accurate and rapid diagnosis is essential to contain COVID-19, and an artificial intelligence-based classification model is an ideal solution to this problem. In this paper, we propose a method based on wavelet entropy and Cat Swarm Optimization to classify chest CT images for the diagnosis of COVID-19 and achieve the best performance among similar methods. The mean and standard deviation of sensitivity is 74.93 ± 2.12, specificity is 77.57 ± 2.25, precision is 76.99 ± 1.79, accuracy is 76.25 ± 1.49, F1-score is 75.93 ± 1.53, Matthews correlation coefficient is 52.54 ± 2.97, Feature Mutual Information is 75.94 ± 1.53. © 2022, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

Exploiting Diverse Contextual Features through Transformers for Detecting Informative Tweets

Twitter is deemed the most reliable and convenient microblogging platform for getting real-time news and information. During the COVID-19 pandemic, people are keen to share various information ranging from new cases, healthcare guidelines, medication, and vaccine news on Twitter. However, a major portion of the shared tweets is uninformative and misleading which may create mass panic. Hence, it is an important task to distinguish and label a COVID-19 tweet as informative or uninformative. Prior works mostly focused on various pretrained transformer models and different types of contextual feature extractors to address this task. However, most of the works applied these models one at a time and didn't employ any effective neural layer at the bottom to distill the tweet contexts effectively. Since a tweet may contain a multifarious context, therefore, representing a tweet using only one kind of feature extractor may not work well. To overcome this limitation, we present an approach that leverages an ensemble of various cutting-edge transformer models to capture the diverse contextual dimension of the tweets. We exploit the BERT, CTBERT, BERTweet, RoBERTa, and XLM-RoBERTa models in our proposed method. Next, we perform a pooling operation on those extracted embedding features to transform them into document embedding vectors. Then, we utilize a feed-forward neural architecture with a linear activation function for the classification task. To generate final prediction, we utilize the majority voting-driven ensemble technique. Experiments on WNUT-2020 COVID-19 English Tweet dataset manifested the efficacy of our method over other state-of-the-art methods. © 2022 IEEE.

Covid-19 Detection by Wavelet Entropy and Self-adaptive PSO

The rapid global spread of COVID-19 disease poses a huge threat to human health and the global economy. The rapid increase in the number of patients diagnosed has strained already scarce healthcare resources to track and treat Covid-19 patients in a timely and effective manner. The search for a fast and accurate way to diagnose Covid-19 has attracted the attention of many researchers. In our study, a deep learning framework for the Covid-19 diagnosis task was constructed using wavelet entropy as a feature extraction method and a feedforward neural network classifier, which was trained using an adaptive particle swarm algorithm. The model achieved an average sensitivity of 85.14% ± 2.74%, specificity of 86.76% ± 1.75%, precision of 86.57% ± 1.36%, accuracy of 85.95% ± 1.14%, and F1 score of 85.82% ± 1.30%, Matthews correlation coefficient of 71.95 ± 2.26%, and Fowlkes-Mallows Index of 85.83% ± 1.30%. Our experiments validate the usability of wavelet entropy-based feature extraction methods in the medical image domain and show the non-negligible impact of different optimisation algorithms on the models by comparing them with other models. © 2022, Springer Nature Switzerland AG.

Exploiting Facial Action Unit in Video for Recognizing Depression using Metaheuristic and Neural Networks

The ubiquity of coronavirus cases around the world has been severe and its impact is not only affecting the economy and physical health, but also mental health such as depression. Unfortunately, the number of coronavirus cases may inhibit people to look for general practitioners or hospitals. This study represents research on facial behaviour analysis on recognizing depression from facial action units extracted from images or videos. We aimed to find a reduced set of facial action unit features using the metaheuristic approach. We utilized particle swarm optimization to select the best predictors and feed them to optimized standard feedforward neural networks. We obtained 97.83% accuracy for depression detection based on Distress Analysis Interview Corpus Wizard-of-Oz (DAIC WOZ) database containing 189 video sessions associated with the Patient Health Questionnaire depression label. This level of accuracy requires almost 9 minutes. However, this level of accuracy is higher than other state-of-The-Art methods. © 2021 IEEE.

Finding Novel Links in COVID-19 Knowledge Graph Using Graph Embedding Techniques

With the rapid proliferation of scientific literature, it has become increasingly impossible for researchers to keep up with all published papers, especially in the biomedical fields with thousands of citations indexed every day. This has created a demand for algorithms to assist in literature search and discovery. A particular case is the literature related to SARS-CoV-2 where a large volume of papers was generated in a short span. As part of the 2021 Smoky Mountains Data Challenge, a COVID-19 knowledge graph constructed using links between concepts and papers from PubMed, Semantic MEDLINE, and CORD-19, was provided for analysis and knowledge mining. In this paper, we analyze this COVID-19 knowledge graph and implement various algorithms to predict as-yet-undiscovered links between concepts, using methods of embedding concepts in Euclidean space followed by link prediction using machine learning algorithms. Three embedding techniques: the Large-scale Information Network Embedding (LINE), the High-Order Proximity-preserved Embedding (HOPE) and the Structural Deep Network Embedding (SDNE) are implemented in conjunction with three machine learning algorithms (logistic regression, random forests, and feed forward neural-networks). We also implement GraphSAGE, another framework for inductive representation on large graphs. Among the methods, we observed that SDNE in conjunction with feed-forward neural network performed the best with an F1 score of 88.0% followed by GraphSAGE with F1 score of 86.3%. The predicted links are ranked using PageRank product to assess the relative importance of predictions. Finally, we visualize the knowledge graphs and predictions to gain insight into the structure of the graph. © 2022, Springer Nature Switzerland AG.

Time Warping Clustering for the Forecast and Analysis of COVID-19

This paper presents an effective algorithm for the clustering of confirmed COVID-19 cases at the county-level in the United States. Dynamic time warping and Euclidean distance are examined as the k-means clustering distance metrics. Dynamic time warping can compare time series varying in speed, as counties often experience similar outbreak trends without the timelines matching up exactly. The effect of data preprocessing on clustering was systematically studied. Further analyses demonstrate the immediate value of our clusters for both retrospective interpretation of the pandemic and as informative inputs for case prediction models. We visualize the time progression of COVID-19 from April 5, 2020 to August 23, 2020. We proposed a Monte-Carlo dropout feedforward neural network with the ability to forecast four weeks into the future. Predictions evaluated from July 24, 2020 to August 20, 2020 demonstrate the better empirical performance of the model when trained on the clusters, in comparison with the model trained on individual counties and the model trained on counties clustered by state. © 2020 IEEE.

Coronavirus Detection Using Two Step-AS Clustering and Ensemble Neural Network Model

This study presents a model of computer-aided intelligence capable of automatically detecting positive COVID-19 instances for use in regular medical applications. The proposed model is based on an Ensemble boosting Neural Network architecture and can automatically detect discriminatory features on chest X-ray images through Two Step-As clustering algorithm with rich filter families, ion and weight-sharing properties. In contrast to the generally used transformational learning approach, the proposed model was trained before and after clustering. The compilation procedure divides the datasets samples and categories into numerous sub-samples and subcategories and then assigns new group labels to each new group, with each subject group displayed as a distinct category. The retrieved characteristics discriminant cases were used to feed the Multiple Neural Network method, which was then utilised to classify the instances. The Two Step-AS clustering method has been modified by pre-aggregating the dataset before applying Multiple Neural Network algorithm to detect COVID-19 cases from chest X-ray findings. Models for Multiple Neural Network and Two Step-As clustering algorithms were optimised by utilising Ensemble Bootstrap Aggregating algorithm to reduce the number of hyper parameters they include. The tests were carried out using the COVID-19 public radiology database, and a cross-validation method ensured accuracy. The proposed classifier with an accuracy of 98.02% percent was found to provide the most efficient outcomes possible. The result is a low-cost, quick and reliable intelligence tool for detecting COVID-19 infection. © 2022 Tech Science Press. All rights reserved.