加权熵最大优化分带分析方法及在模式分类中的应用  

Sub-Band Optimization with Criterion of Maximum Weighting Entropy and Its Application in Pattern Classification

作　　者：鲍明[1] 管鲁阳[1] 李晓东[1] 田静[1] 

机构地区：[1]中国科学院声学研究所通信声学实验室,北京100080

出　　处：《模式识别与人工智能》2008年第1期42-48,共7页Pattern Recognition and Artificial Intelligence

摘　　要：针对信号分带优化的问题,提出功率谱加权熵最大分带分析方法.该方法在限定分带数目的条件下.以加权熵最大为优化标准,获得信号在频域的信息量最大的分带边界.在此基础上.建立功率谱加权熵最大分析模型,同时给出其实现算法.进而,依据功率谱加权熵最大的原则,提出功率谱加权熵最大分带倒谱系数分类特征,设计以线性分类距离为优化标准的权系数学习算法.并在地面目标识别的应用中取得较好效果.Power spectral sub-band analysis with the criterion of maximum weighting entropy is derived as a new signal analysis method in this paper. The maximum information is obtained by optimizing the sub-bands allocated in frequency. Based on this method, a algorithm of feature extraction for classification, maximum weighting entropy cepstrum coefficients （MECC）, is proposed and applied to ground vehicle recognition system. Experimental results show that MECC has better classification performance than the traditional methods.

关 键 词：加权熵最大 分带分析 遗传算法 

分 类 号：TP391.42[自动化与计算机技术—计算机应用技术]