Numerical Assessments Employing Neural Networks for a Novel Drafted Anti-Virus Subcategory in a Nonlinear Fractional-Order SIR Differential System

Abstract

Whereas computer viruses (CVs) are a terrible threat to individual and corporate computer structures. A considerable attempt has been made to research ways to prevent their negative consequences, to develop anti-virus software that behave as vaccines in desktop computers or strategic network nodes. A further method for combating viral transmission is to develop preventative strategies associated with a given performance of a network that may be described using population models compared to the few employed with epidemiological analyses. An updated variation of such SIR (Susceptible-Infected-Removed) framework is offered here, along with an explanation of whether these parameters correspond to network properties. The novel formed SAIR model is then numerically treated, employing the qualities of stochastic procedure-based numerical computation approaches that use neural networks (NNs). In this research study, we suggest novel fractional-order SAIR (FO-SAIR) differential model that has not previously been published. This study's aim appeared to be to demonstrate the effects and applicability of such FO-SAIR differential scheme. An FO-SAIR problem is examined using stochastic solvers relyed upon Levenberg-Marquardt backpropagation approach (L-MB) and NNs, specifically L-MBNNs. For solve the FO-SAIR system, three examples with different values under the same fractional order are presented. The statistical methods used to generate numerical answers for the FO-SAIR system are categorised thus obeys: 75% for training, 13% for testing, and 12% for permission. By using Adams-Bashforth-Moulton, the numerical results were contrasted with the reference solutions to determine the accuracy of such L-MBNNs. To confirm overall capability, competence, validity, consistency, and exactness, the numerical performances of these L-MBNNs using error histograms (EHs), state transitions (STs), regression, correlation, and mean square error (MSE) are also shown.