Estimations of Parameters of Delay Differential Equation Using Genetic Algorithm

Abstract

In this paper, the numerical problem of estimating unknown parameters in systems of delay differential equations from complete data is treated. The numerical method, based on the genetic algorithm method with a fitness function to minimize the difference between the complete data and the numerical solution, is presented. The method is implemented in the framework of an epidemic model. Several models from epidemic applications such as SIR, SI, SIS and SIRS with time delay are treated. The genetic algorithm performs very well in estimating some parameters but is quite poor in estimating time delay parameter.