Computerized Face Mask Detection System Using Deep CNN and Transfer Learning

Since the COVID-19 pandemic is on the rise again with hazardous effects in China, it has become very crucial for global individuals and the authorities to avoid spreading of the virus. This research aims to identify algorithms with high accuracy and moderate computing complexity at the same time (although conventional machine learning works on low computation power, we have rather used CNN for our research work as the accuracy of CNN is drastically greater than the former), to identify the proper enforcement of face masks. In order to find the best Neural Network architecture we used many deep CNN Methodologies to solve classification problem in regards of masked and non masked image dataset. In this approach we applied different model architectures, like VGG16, Resnet50, Resnet101 and VGG19, on a large dataset to train on and compared the model on the basis of accuracy in which VGG16 came out to be the best. VGG16 was further tuned with different optimizers to determine the one best fit of the model. VGG16 gave an ideal accuracy of 99.37% with the best fit optimizer over a real life data set. © 2023 IEEE.

Inflammatory Marker Variations in Predicting Deaths in COVID-19

Introduction. Patients with coronavirus illness experienced a cytokine storm as a major cause of morbidity and mortality in 2019. (COVID-19). The goal of the study was to ascertain the predictive value of pro-inflammatory cytokines with regard to the overall prognosis of COVID-19 patients. Methods. This study was conducted by the Department of Microbiology, Santosh Medical College & Hospital, Ghaziabad, Uttar Pradesh from April to July 2021. We followed 189 patients hospitalized for suspected or confirmed COVID-19 from the day of hospitalization to the day of discharge or death. We measured serum IL-6, CRP, D - Dimer, Ferritin levels upon admission and correlated these results with clinical and laboratory markers of disease severity and with disease outcome. Results. Most of the patients were males and greater than 60 years of age. The mean ferritin level prior to the terminal event (survival or death) among non-survivors was 746 ng/mL as compared to 294 ng/mL among survivors and this difference was statistically significant (p-value <0.05). A decrease in ferritin levels prior to the terminal event (survival or death) and at admission were associated with a greater probability of survival. Ferritin levels prior to the terminal event were more strongly correlated with death than ferritin levels at baseline. Mean CRP level at admission among non-survivors was 69 mg/L as compared to 283 mg/L among survivors and this difference was not statistically significant (p >0.05). Conclusion. In patients with COVID-19, inflammatory markers have prognostic value, with higher levels being associated with worse outcomes.

In silico screening of phytochemicals as potential inhibitors of sars-cov-2 mpro and human ace-2

Background and Objective: An enzyme that inhibits the receptor could make it more difficult for coronavirus to reach cells. The key protease necessary for coronavirus proteolytic maturation is the recognized coronavirus 3-chymotrypsin-like protease 3CLpro, also known as Mpro. This Mpro is needed for immune control and the cleavage of the polyproteins pp1a and pp1ab, making it a promising target for anti-COVID-19 drugs. As a result, inhibiting the Mpro enzyme inhibits viral maturation. Bioactive constituents obtained from some selected indigenous plants of India, which have been reported to have antiviral potential, were subjected to virtual screening against ACE-2 and Mpro in the current study. Materials and Methods: Cresset's Flare 4.0 was used to establish the 3-D structure of all the compounds. Complete optimizations of these constructed structures were carried out. While performing the minimization, the spin state of the wave function was set to the singlet and standard SCF convergence was used for optimization, all other parameters were left at their default values. The Protein Data Bank (https://www.rcsb.org) was used to download the 3-D structures of Mpro from COVID-19 (PDB ID 6LU7) and ACE-2 receptor from Human (PDB ID 1R4L). Results: The findings show that these phytochemicals can bind to ACE-2 and Mpro more effectively as compared to reference compounds and act as inhibitors. Conclusion: The findings of virtual screening of these bioactive constituents revealed that most of them are more active than the reference compounds. Therefore, they could be used to produce antiviral drugs against Coronavirus in the future.

Recent diagnostic techniques for COVID-19

An outbreak of coronavirus pneumonia was firstly documented in Wuhan, Hubei Province, China (December 2019), with an indication of human-to-human transmission. The causative agent identified for coronavirus disease 2019 (COVID-19) is the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). America, Italy, India, and Africa became new venues of COVID infection;the overall data of patients and death is increasing day by day. Generally inplace of most of the infected people develop respiratory symptoms (throat pain, cough, etc.), fever, and chest opacity on CT scan and X-ray. A few numbers of suspected persons are found asymptomatic;they may serve as carriers for infection. As a point of care, the patient diagnosis is compulsory, and only the diagnosis can provide a real-time condition of patients and can be helpful in arresting the spreading of the infection. In the present chapter, we focused on illustrating various diagnostic techniques that have been employed by the world for the detection of the coronavirus. The diagnostic techniques are categorized into molecular and serologic assay techniques. The nucleic acid is detected in molecular assay, whereas the serologic assay uses antigen-antibody reaction. © Springer Nature Switzerland AG 2021.