对数能量熵的最优小波包基搜寻算法  

Search Algorithm of Optimal Wavelet Packet Basis Based on Log Energy Entropy

作　　者：李姣军[1] 唐娜[1] 苏理云[2] 徐勤[1] 

机构地区：[1]重庆理工大学电子信息与自动化学院,重庆400054 [2]重庆理工大学数学与统计学院,重庆400054

出　　处：《重庆理工大学学报（自然科学）》2011年第11期51-55,共5页Journal of Chongqing University of Technology：Natural Science

基　　金：重庆市自然科学基金资助项目(CSTC2010BB2310);重庆市教委基金资助项目(KJ100810)

摘　　要：提出了一种新的最优小波包基搜寻算法,在BBS(best basis selection)基础上,选择对数能量熵作为信息花费代价函数,自上而下搜索,将父节点对数能量熵与子节点和的对数能量熵进行比较,标记最小熵节点,直至标记到根节点,按所标记的节点构成小波包树,则此结构即为最优小波包基,此算法打破了一直以来以香农熵为代价函数的惯例。This paper proposed a new kind of optimum wavelet packet basis search algorithm.Based on the BBS（Best Basis Selection）,the paper chose long energy entropy as the information cost function to search from bottom to top,and compared father node log energy entropy with son node,and marked min-entropy node until root node.According to mark-node,it constituted the wavelet packet tree,and then the structure would be the optimal wavelet packet basis.This algorithm has broken that Shannon as information cost function.This paper also simply introduced application field of this algorithm in the last.

关 键 词：小波包 最优基 对数能量熵 代价函数 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]