基于神经网络的联合混沌时间序列的预测研究(英文)  

Study of Predicting Combined Chaotic Time Series Using Neural Networks~

作　　者：王兆霞[1] 陈增强[1] 袁著祉[1] 郝庭柱[2] 杨保和[2] 

机构地区：[1]南开大学自动化系,天津300071 [2]天津理工大学光电子信息和电子工程系,天津300191

出　　处：《光电子．激光》2004年第10期1225-1228,1233,共5页Journal of Optoelectronics·Laser

基　　金：SupportedbyNationalNaturalScienceFoundationofChina(60 1 740 2 1 ) ;KeyProjectofTianjinNaturalScienceFoundation(0 1 380 0 71 1 )

摘　　要：提出了利用前馈神经网络预测联合混沌序列,通过引用著名的Henon和Lozi混沌系统作为仿真实验产生联合混沌信号序列。预测结果证明,用改进的BP算法训练的NN可以完全预测联合混沌信号序列。The combined chaotic time series is predicted by using the standard feed-forward neural networks (NN). Henon and Lozi systems are used to generate the combined chaotic time series. From the forecasting results, it can be concluded that the NN, which is trained by improved back-propagation (BP) algorithms, can be well applicable for combined chaotic time series prediction.

关 键 词：联合 预测 混沌序列 训练 改进 引用 利用 前馈神经网络 BP算法 混沌时间序列 

分 类 号：TN911[电子电信—通信与信息系统] TP183[电子电信—信息与通信工程]