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

作     者：Umar, Muhammad Sabir, Zulqurnain Raja, Muhammad Asif Zahoor Baskonus, Haci Mehmet Yao, Shao-Wen Ilhan, Esin 

作者机构：Hazara Univ Dept Math & Stat Mansehra Pakistan Natl Yunlin Univ Sci & Technol Future Technol Res Ctr 123 Univ RdSect 3 Touliu 64002 Yunlin Taiwan Harran Univ Dept Math & Sci Educ Sanliurfa Turkey Henan Polytech Univ Sch Math & Informat Sci Jiaozuo 454000 Henan Peoples R China Kirsehir Ahi Evran Univ Kirsehir Turkey 

出 版 物：《RESULTS IN PHYSICS》 (物理结果)

年 卷 期：2021年第25卷

页      面：104235-104235页

核心收录：

学科分类：07[理学] 0805[工学-材料科学与工程（可授工学、理学学位）] 0702[理学-物理学] 

基　　金：National Natural Science Foundation of China Key Scientific Research Project of Higher Education Institutions in Henan Province of China [20B110006] Fundamental Research Funds for the Universities of Henan Province [NSFRF210314] 

主　　题：Morlet wavelets HIV infection models Genetic algorithms Neural networks Sequential quadratic programming Bioinformatics 

摘      要：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.