On Artificial Neural Network to Analyze Discrete Fractional Order COVID-19 Mathematical Model

Abstract

A discrete type model for addressing the recent COVID-19 disease with vaccination class is considered in this research work. In this work, we integrate the harmonic mean type incidence rate into a new fractional-order discrete-time Susceptible-Vaccinated-Infected-Recovered (SVIR) epidemic model. For the considered model Disease Free Equilibrium(DFE) and Endemic Equilibrium (EE) are deduced and the basic reproductive number is also computed. Sensitivity analysis based on direct method is analyzed. The qualitative analysis and numerical investigations for the mentioned model are studied to understand the dynamical behavior. Stability analysis is deduced by using Ulam-Hyers (U-H) criteria. Further, we also investigate the concerned model through the Artificial Neural Networks (ANNs) technique which has recently attracted very well. Additionally, the simulated outcomes and ANNs are compared, and several metrics such as regression coefficient, Mean Square Error (MSE), and Root Mean Square Error (RMSE) are recorded and displayed graphically. We use the Levenberg-Marquardt algorithm to analyze the required computational results. Matlab 2023 software is used for computational purposes.