Designing a heuristic computing structure to solve the human balancing model

Abstract

The current study provides numerical solutions to the human balancing system using novel framework-based artificial neural networks and the hybrid competency of global heuristic genetic algorithm and local search sequential quadratic programming. These networks tend to handle complicated tasks and perform contemporary performance in different areas. The neural networks performances based on the hybridization schemes are presented using the discretization of the model to express the fitness function in the sense of mean square error. The numerical representations are presented for three cases of the delay terms-based human balancing model in order to validate the consistency and efficacy of the proposed stochastic scheme. The acceptability of the proposed solver is oppressed through the overlapping of obtained and reference results. The negligible values of absolute error also provide the accuracy of the scheme. Additionally, the graphs based on the statistical interpretations provide the precision, and convergence of stochastic computing solver.