基于条件熵扩维的多变量混沌时间序列相空间重构

Multivariate chaotic time series phase space reconstruction based on extending dimension by conditional entropy

提出一种多变量混沌时间序列相空间重构的条件熵扩维方法.首先使用互信息法求解每个变量的时间延迟,其次按条件熵最大原则逐步扩展相空间的嵌入维数,使得重构坐标从低维到高维的转换保持较强的独立性,最终的重构相空间具有较低的冗余度,为多变量时间序列的预测构造了有效的模型输入向量.通过对几个经典多变量混沌时间序列进行数值实验,结果表明该方法比单变量预测和已有多变量预测方法具有更好的预测效果,说明了该重构方法的有效性.

For multivariate chaotic time series, a method of conditional entropy extending dimension （ CEED ） in the reconstructed phase space is proposed. First,the delay time of any variable time series is selected by mutual information method,and then the embedding dimension of phase space is extended by the conditional entropy. This method can ensure the independence of reconstructed coordinates from low space to high space and eliminate the redundancy of phase space, because the largest condition entropy is choosen. The effective input vector for the prediction of multivariate time series is given. Simulations of the Lorenz system and Henon system show that the neural network predictions of multivariate time series are much better than the prediction of univariate and existing multivariate. Therefore,CEED is effective for multivariate chaotic systems.