A stochastic neural network process for the fractional order lungs cancer operation system

Abstract The purpose of current research is to provide the solutions of the fractional lungs cancer operation system using one of the neural network approaches. The mathematical model is divided into immune/epithelial cells, tumor suppressor genetic factor, evolution factor oncogenes, and blood lung cancer vessels. The fractional derivatives are performed more competent as compared to integer order derivatives. A neural network approach based on the Levenberg-Marquardt Backpropagation is applied to solve the fractional kind of derivative to exist the solution of the system. Eighteen numbers of neurons along with sigmoid activation function in the hidden layer are used in the neural network process, while the data is created via Adam numerical solver with the selection of different percentages including testing, training and verification. The correctness of the designed neural network scheme is observed through the matching of the outcomes, best training performances and insignificant absolute error. Moreover, some tests based regression, state transition, and error histogram are also been used to check the validity of the proposed scheme.