Inverse Impulsive Optimal Neural Control for Complex Networks Applied to Epidemic Influenza Type A Model

Abstract

This paper proposes to mitigate the effects of the spread of influenza type A, employing a pinning neural impulsive optimal control for complex networks. The model and its dynamics of the network are unknown; therefore, it is necessary to design and train a neural identifier through extended Kalman filter algorithm to help provide the precise non-linear model for this complex network. The dynamics of the nodes are represented by a discrete version of the Susceptible-Infected-Recovered model.