Optimizing Chikungunya Epidemiology Control with Wolbachia Using Artificial Neural Network-Based Evolutionary Algorithms

The increasing incidence of Chikungunya virus (CHIKV) as an important public health issue led to the investigation of novel approaches to disease control. In this study, we analyze Chikungunya epidemic model in the presence of Wolbachia-infected mosquitoes, which is a promising biological approach for controlling vector-borne diseases. The basic reproduction number (R-0) of the proposed model is calculated using the next generation matrix approach. In this study, we utilize a hybrid methodology that combines the genetic algorithm (GA) and interior point algorithm (IPA) to numerically solve the proposed Chikungunya epidemic model. Our investigation examines the impact of key parameters, such as biting rate, reproduction rate, mortality rate, and transmission probability, on the complex dynamics of disease classes. This analysis provides valuable insights into the transmission dynamics of Chikungunya and highlights the potential effectiveness of interventions based on Wolbachia. We conclude that the numerical findings produced using the hybrid GA and IPA are in good agreement with those obtained using the traditional fourth-order Runge-Kutta (RK4) approach.