结合小波变换的独立元心电信号增强  

ECG Enhancement of Combining Wavelet Transform and Independent Component Analysis

作　　者：杜德洁[1] 张乐平[1] 王刚[1] 龚华礼[1] 

机构地区：[1]第二军医大学计算机教研室,上海200433

出　　处：《计算机工程与应用》2006年第9期219-220,227,共3页Computer Engineering and Applications

摘　　要：论文应用小波变换的Mallat算法从一路带噪心电信号构造了另两路观察信号,从而满足独立元分析要求的观测信号向量维数不小于独立信号向量维数的条件;在此基础上,采用FastICA算法对三路心电信号进行独立元分解,分离效果理想。Independent Component Analysis requires that the number of observations should be no less than that of independent sources.In order to satisfy the assumption,in this paper,the Mallat algorithm in wavelet transform is applied to generate two other channels from one single channel noisy ECG signal.The experiment result shows that the performance of FastICA algorithm on the three channel noisy ECG signals is satisfactory.

关 键 词：心电信号 小波变换 独立元分析 MALLAT算法 FASTICA算法 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]