自回归模型的时变小波包分解  

TIME-VARYING WAVELET PACKETS DECOMPOSITION FOR AR MODEL

作　　者：方浩[1] 周冰[1] 薛培鼎[1] 冯祖仁[1] 

机构地区：[1]西安交通大学系统工程研究所,西安710049

出　　处：《电子与信息学报》2001年第11期1077-1082,共6页Journal of Electronics & Information Technology

摘　　要：该文提出了一种基于动态规划的时变小波包分解算法。利用此算法进行小波包分解可以解决以往分解算法如单树算法无法进行时频分解而双树算法只能进行二叉树分解的问题。通过对时变自回归模型的分解仿真实验,表明在处理时变信号方面,此分解算法比其它算法更具有灵活性。Based on dynamic programming, a time-varying wavelet packets decomposition algorithm is proposed. Using this algorithm, the problems, that the single tree algorithm cannot adapt to nonstationary signals and the double tree algorithm has strict binary restriction, are solved. Simulation results varify that this algorithm is more flexible than the others in time-varying signal processing.

关 键 词：小波包 动态规划 时频分解 自回归模型 

分 类 号：TN911.7[电子电信—通信与信息系统]