中国物理B ›› 2008, Vol. 17 ›› Issue (2): 536-542.doi: 10.1088/1674-1056/17/2/031
Multi-step-prediction of chaotic time series based on co-evolutionary recurrent neural network
马千里1, 郑启伦1, 彭 宏1, 覃姜维1, 钟谭卫2
- (1)College of Computer Science and Engineering, South China University of Technology, Guangzhou 510640, China; (2)College of Science, South China Agriculture University, Guangzhou 510640, China
Multi-step-prediction of chaotic time series based on co-evolutionary recurrent neural network
Ma Qian-Li(马千里)a)†, Zheng Qi-Lun(郑启伦)a), Peng Hong(彭宏)a), Zhong Tan-Wei(钟谭卫)b), and Qin Jiang-Wei(覃姜维)a)
- a College of Computer Science and Engineering, South China University of Technology, Guangzhou 510640, China; b College of Science, South China Agriculture University, Guangzhou 510640, China
摘要： This paper proposes a co-evolutionary recurrent neural network (CERNN) for the multi-step-prediction of chaotic time series, it estimates the proper parameters of phase space reconstruction and optimizes the structure of recurrent neural networks by co-evolutionary strategy. The searching space was separated into two subspaces and the individuals are trained in a parallel computational procedure. It can dynamically combine the embedding method with the capability of recurrent neural network to incorporate past experience due to internal recurrence. The effectiveness of CERNN is evaluated by using three benchmark chaotic time series data sets: the Lorenz series, Mackey--Glass series and real-world sun spot series. The simulation results show that CERNN improves the performances of multi-step-prediction of chaotic time series.
中图分类号: (Time series analysis)
- 05.45.Tp