COVID 19 Prediction Using Chest X-Ray And CNN Hyperparameter Optimizer

According to mid-June 2020, the abrupt escalation of coronavirus reported widespread fear and crossed 16 million confirmed cases. To fight against this growth, clinical imaging is recommended, and for illustration, X-Ray images can be applied for opinion. This paper categorizes chest X-ray images into three classes- COVID-19 positive, normal, and pneumonia affected. We have used a CNN model for analysis, and hyperparameters are used to train and optimize the CNN layers. Swarm-based artificial intelligent algorithm - Grey Wolf Optimizer algorithm has been used for further analysis. We have tested our proposed methodology, and comparative analysis has been done with two openly accessible dataset containing COVID- 19 affected, pneumonia affected, and normal images. The optimized CNN model features delicacy, insight, values of F1 scores of 97.77, 97.74, 96.24 to 92.86, uniqueness, and perfection, which are better than models at the leading edge of technology. © 2022 IEEE.

Outcome of Kidney Transplant Recipients during Covid-19 Pandemic

Background: Kidney recipients constitute a vulnerable group of population and may have high risk of morbidity and mortality when infected with COVID-19. Objective(s): To a assess the overall outcome as well as the incidence and impact of COVID-19 among recipients who underwent transplantation during the pandemic Methods: A pre-designed follow up protocol was set to prospectively analyse the data obtaining from the recipients who underwent renal transplantation since 8 March 2010, the first appearance of COVID-19 in Bangladesh till 31 December, 2020. Outcome parameters were renal functional status;surgical, urological, immunological and medical complications;and incidence of COVID-19 and its outcome during the first 12 weeks post-transplant period. Result(s): Out of 100 patients, 82.0% were male and 18.0% were female. Serum creatinine levels (micromol/L) at 4, 8 and 12 weeks post-transplant were 200 in 6.0%, 5.0% and 6.0% respectively. Graft nephrectomy was done in 3 cases due to vascular complications. Five (5.0%) patients presented with symptoms of COVID-19, among them, 2 cases were confirmed with RT-PCR. There were 6 death cases, and septicaemia was the most common cause of death. The overall mortality rate was 6.0% in our study population but in COVID-19 confirmed cases it was 50.0%. Conclusion(s): During this pandemic, the overall outcome of renal transplantation was excellent and the incidence of symptomatic COVID-19 among transplant recipients was not higher than the incidence observed in general population of Bangladesh. But among the COVID-19 confirmed recipients, mortality rate was significantly higher. Copyright © 2022 Bangladesh Medical Research Council. All rights reserved.

Performance Analysis of Convolutional Neural Network Architectures for the Identification of COVID-19 from Chest X-ray Images

The 2019 Novel Coronavirus (COVID-19) has spread quickly over the world and continues to impact the health and well-being of people. The application of deep learning coupled with radiological images is effective for early diagnosis and prevention of the spread. In this study, we introduced a 2D Convolutional Neural Network (CNN) to automatically diagnose Chest X-ray images for multi-class classification (COVID-19 vs. Viral Pneumonia vs. Normal). The objective of the research is to maximize the accuracy of detection by altering various internal parameters of a 2D CNN architecture. A dataset consisting of 1000 COVID-19, 1000 Viral Pneumonia, and 1000 Normal images was considered, and preprocessing steps and augmentation strategies were applied. The training and evaluation of the results were performed on eight 2D CNN architectures with internal parameters changed specifically in each case, and a COVID-19 classification model was proposed. Our proposed computer-aided diagnostic tool produced a significant performance with a classification accuracy of 97.3 %, a sensitivity of 97.3 %, specificity of 98.7%, and precision of 97.4 % on test datasets. These results suggest that it can reliably detect COVID-19 cases and expedite treatment to those in the most need. © 2022 IEEE.

Brief survey on phytochemicals to prevent COVID-19

Background: The recent pandemic by COVID-19 is a global threat to human health. The disease is caused by SARS-CoV-2 and the infection rate is increased more quickly than MERS and SARS as their rapid adaptation to varied climatic conditions through rapid mutations. It becomes more severe due to the lack of proper therapeutic drugs, insufficient diagnostic tool, scarcity of appropriate drug, life supporting medical facility and mostly lack of awareness. Therefore, preventive measure is one of the important strategies to control. In this context, herbal medicinal plants received a noticeable attention to treat COVID-19 in Indian subcontinent. Here, 44 Indian traditional plants have been discussed with their novel phytochemicals that prevent the novel corona virus. The basic of SARS-CoV-2, their common way of transmission including their effect on immune and nervous system have been discussed. We have analysed their mechanism of action against COVID-19 following in-silico analysis. Their probable mechanism and therapeutic approaches behind the activity of phytochemicals to stimulate immune response as well as inhibition of viral multiplication discussed rationally. Thus, mixtures of active secondary metabolites/phytochemicals are the only choice to prevent the disease in countries where vaccination will take long time due to overcrowded population density. © 2021 Indian Chemical Society

Tracking urban heartbeat and policy compliance through vision and language-based sensing

Sensing activities at the city scale using big data can enable applications to improve the quality of citizen life. While there are approaches to sense the urban heartbeat using sound, vision, radio frequency (RF), and other sensors, capturing changes at urban scale using such sensing modalities is challenging. Due to the enormous amount of data they produce and the associated annotation and processing requirement, such data can be of limited use. In this paper, we present a vision-to-language modeling approach to capture patterns and transitions that occur in New York City from March 2020 to August 2020. We use the model on ∼1 million street images captured by dashcams over 6 months. We then use the captions to train a language model based on Latent Dirichlet Allocation [4] and compare models from different periods using probabilistic distance measures. We observe distribution shifts in the model that correlate well with social distancing policies and are corroborated by different data sources, such as mobility traces. This language-based sensing introduces a new sensing modality to capture dynamics in the city with lower storage requirements and privacy concerns. © 2021 ACM.

Towards sensing urban-scale COVID-19 policy compliance in new york city

Big data on the urban scale can enable many applications for improving city life and provide a more holistic understanding of urban life to researchers. While there are approaches to sense and model urban occupant behaviors using sound, radio frequency, and vision, how such behaviors are altered due to city governance and policies in response to emergencies such as a natural disaster or a public health crisis has been less explored. In this paper, we present a computer vision-based approach to capture patterns and interference in the urban life of New York City dwellers from March 2020 to August 2020. Using ∼1 million images gathered with cameras mounted on ride-sharing vehicles throughout the city, we approximated the social proximity of pedestrians to understand policy compliance on the street. Our analysis reveals a correlation between policy violation and virus transmission. We believe that such big data-driven city-scale citizen modeling can inform policy design and crisis management schemes for urban scale smart infrastructure. © 2021 ACM.

Analysis and Prediction of COVID-19 Confirmed Cases Using Deep Learning Models: A Comparative Study

COVID-19 or Novel coronavirus is an infectious disease that was first noticed in December, 2019 and it eventually emerged as a pandemic as it is highly contagious in nature. It affected the economic and social structure worldwide and caused a huge loss of human life. Due to the scarcity of medical infrastructure, it has become nearly impossible to cure every case of COVID-19 and hence the loss of lives is exceedingly increasing. So, if the cases can be forecasted beforehand, proper precautions can be taken on time and thousands of human lives can be saved. In this paper, predictions of the number of coronavirus confirmed cases for the five topmost affected countries across the world have been made. Along with it, a comparative study of ANN (Artificial Neural Network) and RNN (Recurrent Neural Network) based LSTM (Long Short Term Memory) Model has been carried out. The countries taken into consideration for this paper are USA, India, Brazil, Russia, and France. The models have been used to train the dataset and validate the prediction results against the original data based on the predefined metric of MSE or Mean Squared Error. The prediction results have been visualized graphically and it was inferred that the LSTM model outperformed the ANN model. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Poster: A Smart Agent Guided Contactless Data Collection System Amid A Pandemic

The COVID-19 pandemic has impacted academic life in different ways. In the mobile and pervasive computing community, there was a struggle on data collection for the evaluation of human-sensing systems. An automated and contactless solution to collect data from users at home is one way that can help in the continuation of user-centric studies. In this poster, we present a portable system for remote, in-home data collection. The system is powered by a Raspberry Pi © and input peripherals (a camera, a microphone, and a wireless receiver). Our system uses a speech interface for text-to-speech and speech-to-text conversions. The system acts as a voice-based "smart agent"that guides the user during an experiment session. We aim to use our system to collect data from a set of smart pill bottles that we previously designed for medication adherence monitoring [1] and user identification [3].

On Mathematical Modelling of the Indian Human Hair Industry in the Post-COVID-19 Era

An attempt to model the human hair industry in the post-COVID-19 pandemic situation using mathematical modelling has been the goal of this article. Here we introduce a novel mathematical modelling using a system of ordinary differential equations to model the human hair industry as well as the human hair waste management and related job opportunities. The growth of human hair in the months of nationwide total lockdown has been taken into account and graphs have been plotted to analyze the effect of Lockdown in this model. The alternative employment opportunities that can be created for collecting excessive hair in the post-pandemic period has been discussed. A probable useful mathematical model and mechanism to utilize the migrant labours who became jobless due to the pandemic situation and the corresponding inevitable lockdown situation resulting out of that crisis has been discussed in this paper. We discussed the stability analysis of the proposed model and obtained the criteria for an optimal profit of the said model. Graphs have also been plotted to analyze the impact of the control parameter on the optimal profit. © 2021

Ayurveda may play a preventive role against viral infections including SARS-CoV-2 by the inactivation of furin protease

Ayurveda extends various concepts which direct us about the management of infectious diseases including deadly viral infections in either preventive or curative manner. In cases of emerging viral diseases where there is little scientific knowledge, a vigilant observation can help prepare plan and management in future outbreaks. This work summarizes few important viral pathogens that have gained particular attention in recent years and their possible remedies with ayurvedic medicine. To challenge against the deadly viruses without medicine, immunity is the only choice. Ayurvedic medicines guide us to strengthen our natural defense systems by increasing the body's immunity level. The recent viral pandemic of SARS-CoV-2 is a novel coronavirus, identified as the cause of COVID-19 and there is no approved drug to control the infection yet. The viral proteases including human proteases have significant role in disease progression. Among all the human proteases, furin is a promising target for therapeutic intervention in viral diseases as it cleaves and activates several types of viral proteins including the spike protein of SARS-CoV-2. Results obtained from in silico analysis of the common metabolites of tulsi (Ocimum sp.) revealed their effectiveness to inactive the furin enzyme. Interestingly, Ayurvedic medicines have been prepared as different formulations with several ingredients or metabolites might have potential to inactivate the furin protein by binding at various positions. Thus, it suggests that the combined or synergistic action of metabolites present in ayurvedic medicine may be a promising therapeutics to prevent viral diseases. © 2020 Scientific Publishers. All rights reserved.

In silico identification of a potent arsenic based lead drug di-phenyl phenoxy roxarsone against SARS-CoV-2

In this article we have tried to address the plausible identification of a novel lead drug molecule against COVID-19. Nine different arsenic (As) based molecules, roxarsone derivatives were designed and optimized for computational analysis to determine its binding affinity against SARS-CoV-2. The molecules were screened based on their chemical reactivity with respect to conceptual density functional theory (CDFT) and global reactivity descriptors. The screened molecules were docked blindly against RNA dependent RNA polymerase (RdRp) using molecular docking software iGEMDOCK v2.1. On the basis of idock score in their respective catalytic domain, di-phenyl phenoxy roxarsone identified as promising inhibitor against SARS-CoV-2 with binding free energy calculated as -86.8 kcal/mol. Site specific docking was also executed with target site, receptor binding domain (RDB) of spike glycoprotein of SARS-CoV-2 whose structure was computationally designed using Phyre2 server. The interaction study of RDB with di-phenyl phenoxy roxarsone revealed a binding energy -133.3 kcal/mol. Thus it can be concluded from the above in silico experiment that screening of potential arsenic based roxarsone derivative would help in development of new therapeutic drug for COVID-19. © 2020 Scientific Publishers. All rights reserved.