An improved SIRS model based on genetic algorithm

In order to solve the problem that the traditional propagation model (SIRS model) cannot accurately simulate the actual information dissemination problem. In this paper, genetic algorithm is combined with the mathematical model of propagation. The parameters in the SIRS model are optimized by genetic algorithm to obtain the best fit to the data set, and the final results are compared and visualized. After several experiments, our GA-SIRS model achieves the highest coefficient of determination (R2) of 97.54% for the data and outperforms the BP neural network and support vector machine in predicting information dissemination problems. Therefore, the proposed method can be a feasible solution to the problem of information dissemination prediction.