Neural differential tracking control in cancer model

Abstract

Immunotherapy refers to the use of natural and synthetic substances to stimulate the immune response. This document provides the description on the identification process for a particular cancer mathematical model under the immunotherapy treatment by differential neural networks (DNN) and sliding mode type observer techniques. The combination of these both techniques make available a close enough following between the estimate states given by the neural network and the cancer model dynamics: these are the interleukin-2, the tumor cells and the effector cells concentrations. Besides, a feedback control design is shown using the DNN's estimated states and sliding mode control as a possible solution in the effective dose research for immunotherapy treatment. The numerical results derived by this method, implies the possibility to construct a real controller for cancer treatment using an IL-2 online sensor and an embedded system to implement the DNN scheme