A novel study of Morlet neural networks to solve the nonlinear HIV infection system of latently infected cells

The aim of this study is to provide the numerical outcomes of a nonlinear HIV infection system of latently infected CD4+ T cells exists in bioinformatics using Morlet wavelet (MW) artificial neural networks (ANNs) optimized initially with global search of genetic algorithms (GAs) hybridized for speedy local search of sequential quadratic programming (SQP), i.e., MW-ANN-GA-SQP. The design of an error function is presented by designing the MW-ANN models for the differential equations along with the initial conditions that represent the HIV infection system involving latently infected CD4+ T cells. The precision and persistence of the presented approach MW-ANN-GA-SQP are recognized through comparative studies from the results of the Runge-Kutta numerical scheme for solving the HIV infection spread system in case of single and multiple trails of the MW-ANN-GA-SQP. Statistical estimates with 'Theil's inequality coefficient' and 'root mean square error' based indices further validate the sustainability and applicability of proposed MW-ANN-GA-SQP solver.

Automated summary

This study aims to provide numerical outcomes of a nonlinear HIV infection system using Morlet wavelet artificial neural networks optimized with genetic algorithms and hybridized with sequential quadratic programming. The approach's precision and persistence are recognized through comparative studies with the Runge-Kutta numerical scheme, and statistical estimates further validate its sustainability and applicability.