Status of Antibody against Severe Acute Respiratory Syndrome Coronavirus 2: Preliminary Reports on Seroprevalence of Covid 19 in among Health Care Workers

Introduction: Large number of health care workers (HCW) were infected and died due to COVID-19 infection. It is needed to know the actual seroprevalence of COVID in HCWs to assess the risk and to take protective measures. This study was aimed to measure IgG antibodies against nucleocapsid protein (N) of COVID as a serological marker for detection of viral status in risk prone HCW of Bangladesh and possible association with reno-cardio-metabolic risk factors Methods: This longitudinal study was conducted from May 2021 to January 2022 among physicians and non-physician health care workers (HCW) in three non- COVID designated tertiary hospitals in Bangladesh. Participants' demographic data, medical history and information on past COVID-19 infection and vaccination status were collected. Serial blood samples were collected at 1.5 month in all (n=633) later at 3, 6 and 9 months in vaccinated group. A qualitative measurement of IgG antibody against nucleocapsid protein (N) of SARS-CoV-2 was done by was done by CMIA developed by Abbott (FDA-EUA approved). Result(s): The mean age was 35+/-10years where70% were female. Physician 32%, Nurse 45% and others was 23%. Diabetics were 9.5%, hypertensive 9% and asthma in 5.1%. The two doses of vaccine against COVID-19was completed in 56%. History of past COVID-19 infection was found among 20% participants at recruitment, out of which 13% was diagnosed by rt-PCR. History of past COVID-19 infection was found among 18% participants based on 1gG against N protein. But the subjects in two groups were different. Combination of RTPCR and N protein igG showed 35% seropositive for covid. Comparisons between covid infection positive vs. negative showed only age was different (37+/-11 vs. 34+/-9, years p<0.001) but other risk factors like BMI, SBP, DBP, S Albumin, glucose, hemoglobin were not different (P=NS) between the two groups. Further comparisons for eGFR cut-offs showed higher infection in lower eGFR (infection present vs. absent for >90ml/min group was 17% & 83% and in 60-90 ml/min group 32% &. 68 %). Prevalence of COVID 19 infection based on presence of N antibody (cutoff value >1.5) among vaccinated HCWs at 1.5, 6 and 9 month was 13.6%, 8.8% and 7.7% respectively. The mean titer of IgG (against N protein) >1.5 among vaccinated HCWs at 1.5 month was 3.1+/-1.5 and reduced to 0.87+/-0.96 at month 6 (p<0.001). Conclusion(s): The prevalence of COVID-19 infection in HCWs during the second wave was 35% based on test for RTPR or IgG against N protein positivity. In vaccinated persons, based on antibody against N protein, re-infection rate was around 8% up to 9 months post vaccine. Although no difference was seen for covid infection for cardio-metabolic risk factors, there seems to have some relation of higher infectivity with decreased GFR level. No conflict of interestCopyright © 2023

A Deep Learning Model for Classification of COVID-19 Related Fake News

The health crisis caused by COVID-19 throws the whole world into the biggest emergency of the century. Moreover, the pandemic has become awful because of the spread of inadequate and fake news or information among common people. Fake news, gossip and misleading information are on the rise due to the popularity of web-based information sources among people, such as social media, news feeds, online blogs and e-news articles. Monitoring and identifying such fake stories is a prerequisite to cease unwanted panic in this pandemic. But carrying out this task manually is challenging and labour intensive. Computer-assisted pattern recognition can now be used to replace human contact thanks to developments in machine learning, deep learning models and natural language processing. This is also essential for accurately distinguishing between true and false information automatically. A hybrid deep learning classification model has been proposed here to identify and classify the fake news and misleading information on the ‘COVID-19 Fake News Dataset’ (taken from Mendeley) which is a collection of news or web article related to COVID-19. The proposed classification model has achieved an accuracy of 75.34% and outperforms the existing LSTM and BiLSTM techniques. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Prediction of Used Car Prices Using Machine Learning

As the Indian auto-industry entered BS-VI era from April 2020, the value proposition of used cars grew stronger, as the new cars became expensive due to additional technology costs. Moreover, the unavailability of public transport and fear of infection force people toward self-mobility during the outbreak of Covid-19 pandemic. But, the surge in demand for used cars made some car sellers to take advantage from customers by listing higher prices than normal. In order to help consumers aware of market trends and prices for used cars, there comes the need to create a model that can predict the cost of used cars by taking into consideration about different features and prices of other cars present in the country. In this paper, we have used different machine learning algorithms such as k-nearest neighbor (KNN), random forest regression, decision tree, and light gradient boosting machine (LightGBM) which is able to predict the price of used cars based on different features specific to Indian buyers, and we have implemented the best model by comparing with other models to serve our cause. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

A Deep Learning Approach for Face Mask Detection

The whole world is passing through a very difficult time since the outbreak of Covid-19. Wave after wave of this pandemic hitting people very hard across the globe. We have lost around 3.8 million lives so far to this pandemic. Moreover, the impact of this pandemic and the pandemic-induced lockdown on the lives and livelihoods of the people in the developing world is very significant. Till now there is no one-shot remedy available to stop this pandemic. However, spread can be controlled by social distancing, frequent hand sanitization, and using a face mask in public places. So, in this paper, we proposed a model to detect face mask of people in public places. The proposed model uses OpenCv module to pre-process the input images, it then uses a deep learning classifier MobileNetV3 for face mask detection. The accuracy of the proposed model is almost 97%. The proposed model is very light and can be installed on any mobile or embedded system. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Computer Vision-based Social Distancing Surveillance with Automated Camera Calibration for Large-scale Deployment

Social distancing has been suggested as one of the effective measures to break the chain of viral transmission in the ongoing COVID-19 pandemic. We herein describe a computer vision-based AI-assisted solution to aid compliance with social distancing norms. The solution consists of modules to detect and track people, and to identify distance violations. It provides the flexibility to choose between a tool-based mode requiring user input or a fully automated mode of camera calibration (devised in-house), making the latter suitable for large-scale deployments. We also outline a strategy to estimate the number of video feeds which can be supported in parallel for scalability. Finally, we discuss different metrics to assess the risk associated with social distancing violations, including the use of 'violation clusters', and how we can differentiate between transient or persistent violations. Our proposed solution performs satisfactorily under different test scenarios, processes video feed at real-time speed, as well as addresses data privacy regulations by blurring faces of detected people, making it ideal for deployments. © 2021 IEEE.