Prof.  Rashmi  Bhardwaj
Guru Gobind Singh Indraprastha University,  India

Title: Neuronal Wavelet conjuncted Modelling of COVID-19

Abstract:

Most widely and uncontrollably spreading unknown viral genome infecting people worldwide was announced to be 2019-2020 nCoV by WHO on January 30, 2020. Based on the seriousness of its spread and unavailability of vaccination or any form of treatment, it was an immediate health-emergency of concern of international-level. The specific virus-gene is believed to be evolved through 7-monthold infant having infected with bronchiolitis and conjunctivitis. Viral gene consists of distinctive features consisting of a distinctive N-terminal sliver within spike-protein. Corona-genomic viruses - the genus of Coronaviridae species encased viruses along with large plus-strand RNA-gene. Genomic RNA has size 27-32kb wrapped polyadenylated. Three serologically distinctive assemblies for coronaviruses description. This study analyses long-term effects of this virus. It is important to capture the essence of this pandemic affecting millions of the population daily ever since its spread began from January 22, 2020 - August 3, 2020 (approximately 195 days) in this case of India. From sample of each case taken distinctly, initial 4 data-points are input values. Rest of the 191 are to train and test designed forecast model. Further, values that are trained and validated into prototype as inputs. Wavelet Neuronal Network Fuzzified Inferences’ Layered (WNNFIL); Wavelet Neuronal Network Fuzzified Inferences’ Layered Least-Squares Support Vector Regression (WNNFIL-LSSVR); Wavelet Neuronal Network Fuzzified Inferences’ Layered Multivariate Adaptive Regression Spline (WNNFIL-MARS) techniques used to forecast the long term behaviour. WNNFIL-MARS perform better compared to WNNFIL & WNNFIL-LSSVR which is observed through Root Mean Square Error (RMSE), Mean Square Error (MSE), Mean Absolute Error (MAE) and Coefficient of Determination (R2 ) values. The goodness of fit, R2 value has been achieved to be closest to 1 i.e., 0.999 from WNNFIL-MARS It is observed that these proposed-models give enriched efficiency & diminishes error extremely sharply in contrast to existent classical models. 

Keywords: COVID-19; RNA genomic virus; Wavelet; Neuronal Network Fuzzified Inferences’ Layered (NNFIL); Least Square Support Vector Regression (LSSVR); Multivariate Adaptive Regression Spline (MARS); MAE; Goodness of fit (R2 )

Biography:

Prof. Rashmi Bhardwaj, Fellow of Institute of Mathematics & Applications (FIMA) (UK) working as Professor of Mathematics in Nonlinear Dynamics Research Lab, University School of Basic & Applied Sciences (USBAS), Guru Gobind Singh Indraprastha University (GGSIPU), New Delhi, India. Topper of University of Delhi with 100% marks in Integral equation & Boundary value problem. Recipient of Government of India, IMD 27th Biennial MAUSM Award. Visiting Associate of Inter University Center for Astronomy & Astrophysics (IUCAA), Young Scientist Award of All India Council for Technical Education (AICTE), Government of India., 3 patents, 170 research papers, 6 books 14 Ph.D. supervised, 4 presently working. Visited, attended and delivered 300 invited Lectures in International/National conferences. Subject Experts/Reviewer for many International/ National Journals. Life member of several International /National recognized Organizations in the sphere of Mathematical/ Physical/ Computational Sciences. Established Nonlinear Dynamics Research Lab & Mathematics Lab. Member of Sectional Committee of Section of Mathematical Sciences (including Statistics) for 2019-2020, 2020-2021 -107th & 108th Session of Indian Science Congress, Department of Science & Technology, Ministry of Science & Technology, Government of India. Field of Specialization|: Big data Analysis, Celestial Mechanics, Dynamical Astronomy, Nonlinear Dynamics, Applied & Computational Mathematics, Statistics, Optimization Techniques, Soft Computing, Machine Learning; Integral Equations & Boundary Value Problem,