A reliable stochastic computational procedure to solve the mathematical robotic model

摘要

The current work presents the numerical solutions of the robotic system in the process of coronavirus. The stochastic performances using the modeling of Gudermannian neural networks (GDMNNs) are provided along with the global search genetic algorithm (GA) and rapid interior-point scheme (IPS), i.e., GDMNNs-GAIPS. An error function using the differential form of the model is created and then optimized by applying the hybridization of GA-IPS. The correctness and accuracy of the stochastic procedure GDMNNs-GAIPS is examined by using the comparison of the proposed and reference results. The reliability and substantiation of the proposed GDMNNs-GAIPS is authenticated by using the statistical operators based on the mean square error, Theil inequality coefficient and variance account for. Forty numbers of independent trials along with ten numbers of hidden neurons have been used to solve the mathematical model of robotic system to detect the positive cases of COVID-19.