The chaotic time series prediction method based on sparrow search algorithm optimization
Weifeng Wang, Fang Liu, Wei Wang, Mowen Cheng · 2021
With the maturity of chaos theory and the rapid development of artificial intelligence, the establishment of chaotic time series prediction model based on neural network has become a hot issue. In order to further improve the prediction accuracy of neural network and solve the shortcomings of traditional BP neural network in convergence speed and stability, the chaotic time series prediction method based on the optimization of sparrow algorithm is proposed. The threshold and weight of neural network topology are optimized by using a new Sparrow Search Algorithm to improve the robustness of network prediction, so as to solve the prediction problem of chaotic time series. The experimental results show that the proposed optimization method has been significantly improved in prediction accuracy.