Effect of Covid-19 lockdown on traffic and the crash rate of national highway: Evidence from Bangladesh

This study aims to evaluate the impacts of the COVID-19 lockdown on traffic volume of national highways connecting Dhaka with other divisional cities considering pre, during and post-lockdown periods during COVID-19. Bangladesh Government imposed countrywide lockdown at different steps in different timeline, based on the dissemination rate of COVID-19 virus. As a part of controlling measures, the first lockdown was imposed on March 2020 and vehicular movement on highways connecting capital Dhaka with other divisional cities got banned. Thus, the vehicular traffic contributing to Dhaka using different highways got lessened over period. Before imposing every movement ban, people migrated and left cities. Considering all these scenarios, traffic volume has been studied for the eight National Highways (N1-N8). Along with this, the change in road crash rate over these periods has also been studied. Although it seems that, with the reduction of vehicular movements on road the crash rate would also be lessened, but the observed scenario is opposite. For example, on N1 from March 9 to March 25, 2019, the crash number was 3 and the fatality rate was 4, however in 2020, the numbers were 4 and 18. Moreover, the crash number on N5 was 6 during the shutdown period from March 26 to May 29, 2020, and it was 5 in 2019. The fatality rates were the same in both times, indicating that the travel restrictions did not reduce the number of crashes. The main causes of these collisions during the lockdown were mostly irresponsible driving and high speeds due to comparatively low traffic volume. On the other hand, the crash number on N7 was 17 after shutdown from 30 May 2020 to 28 November 2020, and it was 15 in 2019. It appears that, because passenger vehicle movement was restricted for a long period, vehicular mobility was exegeted, resulting in a rise in ADT values on national highways, as well as an increase in crash counts. Each year, many unexpected crashes occur on these national highways due to uncontrolled driving, overtaking, and high speeds. The study findings can help policy makers to understand the factors behind roadway crashes on the highways during the COVID-19 period. It would eventually govern reliable, efficient roadway system ensuring mobility with safety. © 2023 Author(s).

Efficient Machine Learning Approaches to Detect Fake News of Covid-19

In recent years, the growth of fake news has been significantly high. Advancement in the field of technology is one of the reasons that lie behind this phenomenon. Fake news are presented in such a way that it is quite hard to identify as fake on various social platforms these days and that has a huge impact on people or communities. Such fake news is most destructive when it plays with life. COVID-19 has changed and shaken the entire universe, and fake news that are related to COVID-19 make the destruction deadlier. So, an effort regarding COVID-19-related fake news detection will guard a lot of people or communities against bogus news and can make lives better with proper news in a pandemic. For our research in this paper, a methodology has been espoused to detect COVID-19-allied fake news. Our methodology consists of two different approaches. One approach deals with machine learning models (Logistic regression, support vector machine, decision tree, random forest) using the term frequency-inverse document frequency (TF-IDF) attributes of textual documents, and the other approach involves an association of convolutional neural networks (CNNs) and bidirectional long short-term memory (BiLSTM) using the sequence of vectors of tokens or words in documents. Logistic regression using the TF-IDF is the best performer among all these models having 95% accuracy and an F1-score of 0.94 on test data with Cohen’s kappa coefficient of 0.89 and Mathews correlation coefficient of 0.89. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Development of a Smartphone-Based Expert System for COVID-19 Risk Prediction at Early Stage.

COVID-19 has imposed many challenges and barriers on traditional healthcare systems due to the high risk of being infected by the coronavirus. Modern electronic devices like smartphones with information technology can play an essential role in handling the current pandemic by contributing to different telemedical services. This study has focused on determining the presence of this virus by employing smartphone technology, as it is available to a large number of people. A publicly available COVID-19 dataset consisting of 33 features has been utilized to develop the aimed model, which can be collected from an in-house facility. The chosen dataset has 2.82% positive and 97.18% negative samples, demonstrating a high imbalance of class populations. The Adaptive Synthetic (ADASYN) has been applied to overcome the class imbalance problem with imbalanced data. Ten optimal features are chosen from the given 33 features, employing two different feature selection algorithms, such as K Best and recursive feature elimination methods. Mainly, three classification schemes, Random Forest (RF), eXtreme Gradient Boosting (XGB), and Support Vector Machine (SVM), have been applied for the ablation studies, where the accuracy from the XGB, RF, and SVM classifiers achieved 97.91%, 97.81%, and 73.37%, respectively. As the XGB algorithm confers the best results, it has been implemented in designing the Android operating system base and web applications. By analyzing 10 users' questionnaires, the developed expert system can predict the presence of COVID-19 in the human body of the primary suspect. The preprocessed data and codes are available on the GitHub repository.

COVID-19 Fake News Detection on Social Media

Since the outbreak of COVID-19, social media plays an important role to circulate pandemic news around the world. Some malevolent users may take an advantage of this and spread fake news to attract people for business and research purposes. In this paper, we take an approach by applying existing machine learning algorithms to detect fake news in social media and show a comparison of their performances. In our study, the support vector classifier (SVC) outperforms the rest of the classifiers based on different statistical metrics. Therefore, the SVC classifier has been considered as our proposed classifier model to identify fake COVID-19 news in social media. Two word clouds have also been generated based on the appearance of words in the news that shows an insignificant difference between true and fake news. © 2021 IEEE.

Face Recognition Using Convolutional Neural Network Architectures on Mask-Occluded Face Images

In epidemic situations such as the novel coronavirus disease (COVID-19) pandemic that spreads through physical contact, security and presence systems that previously used fingerprints-based or were contact-based are no longer safe for users. Compared to other popular biometrics such as fingerprints, irises, palms, and veins, the face has much better potential to recognize identity in a nonintrusive manner. Therefore, this study will employ two convolutional neural network (CNN) architectures, LeNet-5 and MobileNetV2, for face recognition on mask-occluded face images. Data were taken from 12 subjects face-to-face were preprocessed by cropping, artificial mask augmentation, resizing, and image augmentation. The model was trained with the configured hyperparameter for 50 epochs with a 60:40 data split. Model testing was performed using image data without augmentation wearing a mask. The test results are measured with classification accuracy for 12 classes. The highest testing accuracy on LeNet-5 models is 98.15%, with $64\times 64$ input size and 64 batch size. Meanwhile, the highest testing accuracy for MobileNetV2 is 97.22% with input size $96\times 96$, batch size 16, and the weight of the MobileNetV2 model initialized with ImageNet $96\times 96$. © 2021 IEEE.

Prediction Model for Mortality Analysis of Pregnant Women Affected with COVID-19

COVID-19 pandemic is an ongoing global pandemic which has caused unprecedented disruptions in the public health sector and global economy. The virus, SARS-CoV-2 is responsible for the rapid transmission of coronavirus disease. Due to its contagious nature, the virus can easily infect an unprotected and exposed individual from mild to severe symptoms. The study of the virus's effects on pregnant mothers and neonatal is now a concerning issue globally among civilians and public health workers considering how the virus will affect the mother and the neonate's health. This paper aims to develop a predictive model to estimate the possibility of death for a COVID-diagnosed mother based on documented symptoms: dyspnea, cough, rhinorrhea, arthralgia, and the diagnosis of pneumonia. The machine learning models that have been used in our study are support vector machine, decision tree, random forest, gradient boosting, and artificial neural network. The models have provided impressive results and can accurately predict the mortality of pregnant mother's with a given input. The precision rate for 3 models(ANN, Gradient Boost, Random Forest) is 100% The highest accuracy score(Gradient Boosting, ANN) is 95%, highest recall(Support Vector Machine) is 92.75% and highest f1 score(Gradient Boosting, ANN) is 94.66%. Due to the accuracy of the model, pregnant mother can expect immediate medical treatment based on their possibility of death due to the virus. The model can be utilized by health workers globally to list down emergency patients, which can ultimately reduce the death rate of COVID-19 diagnosed pregnant mothers. © 2021 IEEE.

Classification of COVID-19 Patients Using Deep Learning Architecture of InceptionV3 and ResNet50

This paper aims to compare the deep learning Convolutional Neural Network (CNN) model for a case study of 3 classes chest x-ray classification of patients with "COVID-19", "pneumonia", and "normal people"using 2 architectures, namely InceptionV3 and ResNet50. This model was created using the GoogleColab platform with the Python programming language. This comparison aims to find the best results using 4 evaluation metrics and several scenarios for dividing the number of datasets used for training and validation. The evaluation metrics used include accuracy, precision, recall, and F1-score. The best accuracy is generated on a model with the ResNet50 architecture with a training accuracy value of 98.62% and accuracy validation of 96.53%. While in the InceptionV3 architecture, the resulting value for training accuracy is 96.13% and accuracy validation is 91.52%. © 2021 IEEE.

Fake News Detection of COVID-19 Using Machine Learning Techniques

Covid-19 or Coronavirus is the most popular common term in recent time. The SARS-CoV-2 virus caused a pandemic of respiratory disturbance which is named as COVID-19. The coronavirus is outspread through drop liquids as well as virus bits which are released into the air by an infected person’s breathing, coughing or sneezing. This pandemic has become a great death threat to the people, even the children too. It’s quite unexpected that some corrupted individuals spread false or fake news to disrupt the social balance. Due to the news misguidance, numerous people have been misled for taking proper care. For this issue, we have analyzed some machine learning techniques, among them, an ensemble method Random forest has gained 90% with the best exactitude. The other models Naive Bayes got 85%, as well as another ensemble method created by Naive Bayes with Support Vector Machine (SVM), gained the exactitude as 88%. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Hydrating large-scale coronavirus pandemic tweets: A review of software for transportation research

The coronavirus (COVID-19) pandemic has challenged the established societal structure, and the transportation sector is not out of this new normal. The primary objective of this research is to analyze and review the performance of software models used for extracting and processing large-scale data from Twitter streams related to COVID-19. The study extends the previous research efforts of machine learning applications on social media by providing a review of contemporary tools, including their computing maturity, and their potential usefulness. The paper also provides an open data repository for the processed data frames to facilitate the swift development of new transportation research. Transportation researchers and the American Society of Civil Engineers (ASCE) community are believed to benefit from this study. © ASCE

A Multi-Model Based Ensembling Approach to Detect COVID-19 from Chest X-Ray Images

Since the onset of COVID-19, radiographic image analysis coupled with artificial intelligence (AI) has become popular due to insufficient RT-PCR test kits. In this paper, an automated AI-assisted COVID-19 diagnosis scheme is proposed utilizing the ensembling approach of multiple convolutional neural networks (CNNs). Two different strategies have been carried out for ensembling: A feature level fusionbased ensembling method and a decision level ensembling method. Several traditional CNN architectures are tested and finally in the ensembling operation, MobileNet, InceptionV3, DenseNet201, DenseNet121 and Xception are used. To handle the computational complexity of multiple networks, transfer learning strategy is incorporated through ImageNet pre-trained weight initialization. For feature-level ensembling scheme, global averages of the convolutional feature maps generated from multiple networks are aggregated and undergo through fully connected layers for combined optimization. Additionally, for decision level ensembling scheme, final prediction generated from multiple networks are converged into a single prediction by utilizing the maximum voting criterion. Both strategies perform better than any individual network. Outstanding performances have been achieved through extensive experimentation on a public database with 96% accuracy on 3-class (COVID-19/normal/pneumonia) diagnosis and 89.21% on 4-class (COVID-19/normal/viral pneumonia/bacterial pneumonia) diagnosis. © 2020 IEEE.

Mental health consequences of COVID-19 pandemic on adult population: a systematic review

Purpose: The spread of novel coronavirus 2019 (COVID-19) has infected millions of people worldwide. Public health emergencies caused by COVID-19 affect not only people’s physical health but also mental health. This paper aims to summarize recent research findings on the mental health impact of COVID-19 experienced by the general adult population. Design/methodology/approach: This paper used a systematic approach and aimed to review the literature on mental health problems faced by general adults during the COVID-19 pandemic. The PubMed database has been selected randomly from the Google Scholar, Cochrane Library, Embase and PubMed databases. Ten journal articles published between January and July 2020 were selected from the PubMed database for the final review. Findings: There is growing evidence that COVID-19 may be an objective risk factor for mental distress among the general adult population. More psychological and social support should be provided to protect adult people’s mental health. Practical implications: This review will help policymakers develop mental health interventions for the general adult population vulnerable to psychological distress because of COVID-19 pandemic. Originality/value: This paper is original and contributes to the existing knowledge that the mental health challenges of COVID-19 are widespread. There is, therefore, a need for more psychological interventions for adults, older adults, in particular, to promote mental health and reduce the distress associated with public health emergencies caused by COVID-19. © 2020, Emerald Publishing Limited.