Optimal Control of Infectious Diseases Using the Artificial Neural Networks

This paper presents a novel approach that uses artificial neural networks to solve the SEIR (Susceptible, Exposed, Infected, and Recovered) model of infectious diseases based on dynamical systems. Optimal control techniques are used to find a vaccination schedule for a standard SEIR epidemic model. The multilayer perceptron is applied to approximate the state and co-state functions of the SEIR model and to solve the optimal control problem using a nonlinear programming approach. By applying Pontryagin’s Minimum Principle (PMP) to the SEIR model and constructing a loss function, a minimization problem is defined, and the approximate solution of the Hamiltonian system is computed. This method is compared with the fourth-order Runge-Kutta method. Illustrative examples are used to demonstrate the usefulness of the proposed approach.