研究一种基于组合进化算法优化相空间重构参数的混沌时间序列预测方法。该方法首先建立时间延迟τ和嵌入维数m在相空间中的信息熵优化模型,然后提出一种改进的组合进化算法同时求解2个重构参数τ和m,结合最小二乘向量机进行混沌时间序列预测。实验结果表明,该方法能够确定合适的相空间重构参数τ和m,提高预测精度。
A method of combinative evolutionary algorithm optimized parameters of phase space reconstruction is proposed for predicting chaotic time series. First, it establishes an information entropy optimum mathematical model in phase space for embedding dimension and delay time. It then solves these two parameters with an improved combinative evolutionary algorithm (CEA) simultaneously. The chaotic time series are predicted using least squares support vector machine. The results show that it not only determines two parameters at the same time, but also can improve the performance of chaotic time series prediction.