首页 | 本学科首页   官方微博 | 高级检索  
     检索      

Multi-step-prediction of chaotic time series based on co-evolutionary recurrent neural network
作者姓名:马千里  郑启伦  彭 宏  钟谭卫  覃姜维
作者单位:College of Computer Science and Engineering, South China University of Technology, Guangzhou 510640, China;College of Computer Science and Engineering, South China University of Technology, Guangzhou 510640, China;College of Computer Science and Engineering, South China University of Technology, Guangzhou 510640, China;College of Science, South China Agriculture University, Guangzhou 510640, China;College of Computer Science and Engineering, South China University of Technology, Guangzhou 510640, China
基金项目: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).
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 coevolutionary 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.

关 键 词:混沌时间组  多步预测  进化战略  循环时间网络
收稿时间:6/4/2007 12:00:00 AM
修稿时间:7/7/2007 12:00:00 AM

Multi-step-prediction of chaotic time series based on co-evolutionary recurrent neural network
Ma Qian-Li,Zheng Qi-Lun,Peng Hong,Zhong Tan-Wei and Qin Jiang-Wei.Multi-step-prediction of chaotic time series based on co-evolutionary recurrent neural network[J].Chinese Physics B,2008,17(2):536-542.
Authors:Ma Qian-Li  Zheng Qi-Lun  Peng Hong  Zhong Tan-Wei and Qin Jiang-Wei
Institution:College of Computer Science and Engineering, South China University of Technology, Guangzhou 510640, China; 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:chaotic time series  multi-step-prediction  co-evolutionary strategy  recurrent neural networks
本文献已被 维普 等数据库收录!
点击此处可从《中国物理 B》浏览原始摘要信息
点击此处可从《中国物理 B》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号