Numerical treatment of fractional order Buruli ulcer and cholera model by using neural network approach

Purpose

The purpose of these investigations is to design a neuro computing solver based on the Levenberg-Marquardt backpropagation neural network for the fractional order confection Buruli ulcer and cholera model, which is divided into ten different categories.

Method

The numerical solutions of the Buruli ulcer and cholera model are obtained through the reliable stochastic approach. A dataset based Adam scheme is designed that implemented to decrease the mean square error by splitting the data 12%, 12% for both endorsement and testing, while 76% is applied for training. Three cases based on the fractional order values 0.5, 0.7 and 0.9 are used to present the numerical performances of the model. The structure of neural network contains twelve neurons, single layer, and log-sigmoid transfer function for the Buruli ulcer and cholera model.

Results

The precision of the proposed scheme is checked using the comparison of the outputs, best validation performances around 10^–06 to 10^–07, and small absolute error as 10^–04 to 10^–06. Moreover, the some test performances based on taking different proportional indices are programmatic to validate the dependability of the solver.

Novelty

The proposed Levenberg-Marquardt backpropagation neural network approach together with twelve neurons, single layer, and log-sigmoid transfer function is applied first time for the fractional order Buruli ulcer and cholera model.