Please wait a minute...
Chin. Phys. B, 2008, Vol. 17(2): 536-542    DOI: 10.1088/1674-1056/17/2/031
GENERAL Prev   Next  

Multi-step-prediction of chaotic time series based on co-evolutionary recurrent neural network

Ma Qian-Lia, Zheng Qi-Luna, Peng Honga, Qin Jiang-Weia, Zhong Tan-Weib
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
Abstract  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.
Keywords:  recurrent neural networks      chaotic time series      multi-step-prediction      co-evolutionary strategy  
Received:  04 June 2007      Revised:  07 July 2007      Published:  20 February 2008
PACS:  05.45.Tp (Time series analysis)  
  07.05.Mh (Neural networks, fuzzy logic, artificial intelligence)  
Fund: Project supported by the State Key Program of National Natural Science of China (Grant No 30230350) and the Natural Science Foundation of Guangdong Province, China (Grant No 07006474).

Cite this article: 

Ma Qian-Li, Zheng Qi-Lun, Peng Hong, Zhong Tan-Wei, Qin Jiang-Wei Multi-step-prediction of chaotic time series based on co-evolutionary recurrent neural network 2008 Chin. Phys. B 17 536

[1] New predication of chaotic time series based on local Lyapunov exponent
Zhang Yong. Chin. Phys. B, 2013, 22(5): 050502.
[2] Novel delay-distribution-dependent stability analysis for continuous-time recurrent neural networks with stochastic delay
Wang Shen-Quan, Feng Jian, Zhao Qing. Chin. Phys. B, 2012, 21(12): 120701.
[3] Robust stability analysis of Takagi–Sugeno uncertain stochastic fuzzy recurrent neural networks with mixed time-varying delays
M. Syed Ali. Chin. Phys. B, 2011, 20(8): 080201.
[4] Improved delay-dependent globally asymptotic stability of delayed uncertain recurrent neural networks with Markovian jumping parameters
Ji Yan, Cui Bao-Tong. Chin. Phys. B, 2010, 19(6): 060512.
[5] A method to improve the precision of chaotic time series prediction by using a non-trajectory
Yan Hua, Wei Ping, Xiao Xian-Ci. Chin. Phys. B, 2009, 18(8): 3287-3294.
[6] Chaotic time series prediction using fuzzy sigmoid kernel-based support vector machines
Liu Han, Liu Ding, Deng Ling-Feng. Chin. Phys. B, 2006, 15(6): 1196-1200.
[7] Chaotic time series prediction using mean-field theory for support vector machine    
Cui Wan-Zhao, Zhu Chang-Chun, Bao Wen-Xing, Liu Jun-Hua. Chin. Phys. B, 2005, 14(5): 922-929.
[8] Neural Volterra filter for chaotic time series prediction
Xiao Xian-Ci, Li Heng-Chao, Zhang Jia-Shu. Chin. Phys. B, 2005, 14(11): 2181-2188.
[9] Local discrete cosine transformation domain Volterra prediction of chaotic time series
Xiao Xian-Ci, Zhang Jia-Shu, Li Heng-Chao. Chin. Phys. B, 2005, 14(1): 49-54.
[10] Synchronization of an uncertain chaotic system via recurrent neural networks
Tan Wen, Wang Yao-Nan. Chin. Phys. B, 2005, 14(1): 72-76.
[11] Chaotic time series prediction using least squares support vector machines
Ye Mei-Ying, Wang Xiao-Dong. Chin. Phys. B, 2004, 13(4): 454-458.
[12] Improving the prediction of chaotic time series
Chen Tian-Lun, Li Ke-Ping, Gao Zi-You. Chin. Phys. B, 2003, 12(11): 1213-1217.
Zhang Jia-shu, Xiao Xian-ci. Chin. Phys. B, 2001, 10(5): 390-394.
No Suggested Reading articles found!