Chaotic Time Series Prediction Method Based on BP Neural Network and Extended Kalman Filter
For neural networks, there are local minimum problems and slow convergence speeds. In order to improve the prediction accuracy of the BP neural network prediction model for chaotic time series, the EKF algorithm with BP neural network is used in the field of chaotic time series prediction. Namely, the use of the weight of its output of BP neural network is suitable for the state equation and observation equation of the Kalman filter, which gives the evolution of the Kalman filter algorithm suitable for nonlinear systems. Extended Kalman filter (EKF) algorithmtypical and Mackey-Glass chaotic time series were simulated. The simulation results show that the method of chaotic time series with nonlinear fitting better and higher prediction accuracy.
KeywordsBP neural network Extended Kalman Filtering (EKF) Chaotic time series prediction
The authors would like to thank the anonymous reviewers for their valuable comments. This work was supported by Initial Scientific Research Fund of FJUT (GY-Z12079), Pre-research Fund of FJUT (GY-Z13018), Fujian Provincial Education Department Youth Fund (JAT170367, JAT170369), Natural Science Foundation of Fujian Province (2018J01640) and China Scholarship Council (201709360002).
- 1.Zhang, H., Li, R.: Bernstein neural network chaotic sequence prediction based on phase space reconstruction. J. Syst. Simul. 28(4), 880–889 (2016)Google Scholar
- 4.Ai, H., Shi, Y.: Study on prediction of haze based on BP neural network. Comput. Simul. 35(1), 402–405 (2015)Google Scholar
- 5.Zhang, J., Tan, Z.: Prediction of the chaotic time sevies using hybrid method. Syst. Eng. Theor. Pract. 33(3), 763–769 (2013)Google Scholar
- 7.Li, S., Luo, Y., Zhang, M.: Prediction method for chaotic time series of optimized BP neural network based on genetic algorithm. Comput. Eng. Appl. 47(29), 52–55 (2011)Google Scholar
- 8.Zhang, H., Li, R.: Chaotic time sevies prediction of full-parameters continued fraction based on quantum particle sarm optimization algorithm. Control Decis. 31(1), 52–58 (2016)Google Scholar