No Cover Image

Journal article 270 views 91 downloads

Probing the Stochastic Dynamics of Coronaviruses: Machine Learning Assisted Deep Computational Insights with Exploitable Dimensions

T. Mukhopadhyay, S. Naskar, K. K. Gupta, R. Kumar, S. Dey, Sondipon Adhikari

Advanced Theory and Simulations, Volume: 4, Issue: 7, Start page: 2000291

Swansea University Author: Sondipon Adhikari

  • VOR.57326.pdf

    PDF | Version of Record

    Copyright: The Authors. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

    Download (1.56MB)

Check full text

DOI (Published version): 10.1002/adts.202000291

Abstract

A machine learning assisted efficient, yet comprehensive characterization ofthe dynamics of coronaviruses, in conjunction with finite element (FE)approach, is presented. Without affecting the accuracy of prediction inlow-frequency vibration analysis, an equivalent model for the FE analysis ispropose...

Full description

Published in: Advanced Theory and Simulations
ISSN: 2513-0390 2513-0390
Published: Wiley 2021
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa57326
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract: A machine learning assisted efficient, yet comprehensive characterization ofthe dynamics of coronaviruses, in conjunction with finite element (FE)approach, is presented. Without affecting the accuracy of prediction inlow-frequency vibration analysis, an equivalent model for the FE analysis isproposed, based on which the natural frequencies corresponding to first threenon-rigid modes are analyzed. To quantify the inherent system-uncertaintyefficiently, Monte Carlo simulation is proposed in conjunction with themachine learning based FE computational framework for obtaining completeprobabilistic descriptions considering both individual and compound effect ofstochasticity. A variance based sensitivity analysis is carried out to enumeratethe relative significance of different material parameters corresponding tovarious constituting parts of the coronavirus structure. Using the modalcharacteristics like natural frequencies and mode shapes of the virus structureincluding their stochastic bounds, it is possible to readily identifycoronaviruses by comparing the experimentally measured dynamic responsesin terms of the peaks of frequency response function. Results from this first ofits kind study on coronaviruses along with the proposed generic machinelearning based approach will accelerate the detection of viruses and createefficient pathways toward future inventions leading to cure and containmentin the field of virology.
Keywords: Coronaviruses, Machine Learning
College: Faculty of Science and Engineering
Funders: UK-India Education and Research Initiative
Issue: 7
Start Page: 2000291