A stochastic computing procedure to solve the dynamics of prevention in HIV system. (September 2022)

• Record Type: Journal Article
• Authors: Umar, Muhammad; Amin, Fazli; Al-Mdallal, Qasem; Ali, Mohamed R.
• Is Part Of: Biomedical signal processing and control. Volume 78(2022)
• Publication Date: 2022-09
• Subjects: Mayer wavelet -- Neural networks -- Interior-point -- Genetic algorithm, Prevention, HIV -- Numerical performances; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2022.103888
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: The numerical solutions of the HIPV mathematical model are successfully specified utilizing the MWNNs–GAIPA computational techniques. The overlapping of the MWNNs-GAIPA obtained results with precise or reference solutions can clearly be seen, demonstrating the reliability and validity of the computational MWNNs-GA-IPA. The MWNNs-GAIPA practically accurate performances are validated by statistical valuations in various figures and tables of merit. The suggested procedure is efficient for the HIPV mathematical model, and it is operated competently, with easy-to-understand topographies, as well as applicability and consistency. Abstract: The motive of this work is to find the numerical simulations of a dynamical HIV model along with the effects of prevention, i.e., HIPV nonlinear mathematical system. An advance computational framework using the procedures of Meyer neural networks (MNNs) together with the compotnecies of local/global search approaches is presented to solve the HIPV nonlinear mathematical system. The global and local operators will be used as genetic algorithm (GA) and interor-point algorithm (IPA), i.e., GAIPA. The dynamicis of HIPV mathematical system is classified into four categories, 'T-cells attentiveness', 'Infected from disease, 'Prevention actions' and 'Virus free particles. An error function is constructed using the differential system and its boundary conditions. The optimization of this function is presented through the hybridization computing paradigms of MWNNs-GAIPA. The correctness of the designed MWNNs-GAIPA is obtained by using the comparion of the obtained and reference solutions. The performance of this scheme is also acheived through the overlapping of the results with the accuracy of order 5 t 7 in the plots of absolute error. The reliability of the proposed MWNNs-GAIPA solver is observed by providing the statistical analysis by using different operators.