A Novel Real-time Automated Face Classification and Detection system using Machine Learning Technique

In recent days, Image classification and detection technique has become an important and more essential in the Image processing research field. Creating effective face detection is an essential aspect of handling the detection mechanism, Tracking mechanism and Validation mechanism. The classical methods used for face detection do not have sufficient output. This research paper presents various studies and how machine learning methods are become to solve many challenges present in the face detection system. The first phase of work has a classification model with support vector machines, decision trees and Hybrid Ensemble Transfer learning algorithm. The second phase of work is investigated with real-the world's most popular dataset from World Masked Face Image Dataset and Label Faces in the wild (RMFD). Moreover, the experiment, results show how better accuracy and fast computation which has been achieved by Hybrid Ensemble algorithm with SVM and Decision Trees machine learning techniques. This research helps to assist many social applications such as during pandemics like covid-19 and personal identity, it can be verifying the mask-worn persons. © 2023 IEEE.

In-silico ADME and Docking-based Virtual Screening Study Aiming at the Sigma-Covalent Inhibition of SARS-CoV-2 RdRp

The objectives of the study were to examine the virtual screening of the compounds and sigma-covalent inhibition of SARS-CoV-2 RdRp (RNA-Dependent RNA-Polymerase), which is conserved and is an essential enzyme for RNA transcription and replication of this virus. In this study, we collected around 1225 similar compounds of Penciclovir and Acyclovir inhibitors from PubChem and predicted ADME (Adsorption, Distribution, Metabolism and Excretion) molecular descriptors using Swiss-ADME server. Virtually screened 24/1225 compounds based on drug-likeliness five rules (Lipinski, Ghose, Veber, Egan, and Muegge) and lead-likeliness properties. Further 10/24 compounds screened, based on high binding affinity and RMSD<3.5 angstrom against RdRp structure using PyRx docking software. Furthermore, the molecular interactions of 10 compounds studied using Discovery studio software and finally screened five PubChem compounds 57201841, 135408972, 54552823, 135409422 and 467850, based on bioactivity score using Molinsipiration cheminformatics software. All these five compounds showed up anti-SARS CoV-2 activity, though further in-vitro studies are required.