摘要
针对多变量混沌序列相关性分析中各分量幅值之间可能没有明显的相关性,但在其相空间邻域内会产生同步特性的问题,提出一种从相空间同步角度研究两个变量间相互依赖关系的非线性相关分析方法。首先按照对应的时间标记将原始变量相空间中的邻域点向另外一个变量中进行投影,分析映射前后邻域半径的变化,在此基础上定义一种度量变量间非线性相关性的评价指标。最后构建多变量局域预测模型,实现对多变量混沌序列的精确预测。仿真实例验证了结果的有效性。
Considering the characteristic of chaotic time series that may produce synchronization in the phase space although there is no obvious correlation between the amplitudes of various components,a nonlinear correlation analysis algorithm based on phase space synchronization is presented.Firstly,the nearest neighborhood of one time series is mapping into the phase space of another time series according to the time subscript,and the change of the neighborhood radius is calculated.Then,a criterion is defined to measure the nonlinear dependence between two time series.Finally,a local prediction model is constructed to implement the precise prediction of multivariate time series.Simulation results show the effectiveness of the designed method.
出处
《系统工程与电子技术》
EI
CSCD
北大核心
2010年第11期2426-2430,共5页
Systems Engineering and Electronics
基金
国家自然科学基金(60674073)
国家重点基础研究发展计划(973计划)项目(2006CB403405)
国家科技支撑计划项目(2006BAB14B05)资助课题
关键词
多变量混沌序列
邻域
相空间同步
相关分析
局域预测
multivariate chaotic time series
nearest neighborhood
phase space synchronization
correlation analysis
local prediction
