基于独立元分析和联合小波熵检测多导联ECG信号的QRS  

Detecting QRS Complexes of Multi-lead ECG Signals by Using Independent Component Analysis and Combined Wavelet Entropy

作　　者：黄博强[1] 汪源源[1] 

机构地区：[1]复旦大学电子工程系,上海200433

出　　处：《生物医学工程学进展》2010年第1期1-6,共6页Progress in Biomedical Engineering

基　　金：国家重点基础研究项目(2006CB705707);自然科学基金项目(10974035);上海市优秀学科带头人项目(10XD1400600)

摘　　要：QRS波群的准确定位是ECG信号自动分析的基础。为提高QRS检测率,提出一种基于独立元分析(ICA)和联合小波熵(CWS)检测多导联ECG信号QRS的算法。ICA算法从滤波后的多导联ECG信号中分离出对应心室活动的独立元;然后对各独立元进行连续小波变换(CWT),重构小波系数的相空间,结合相空间中的QRS信息对独立元排序;最后检测排序后独立元的CWS得到QRS信息。实验对St.Petersburg12导联心率失常数据库及64导联犬心外膜数据库测试,比较本文算法与单导联QRS检测算法和双导联QRS检测算法的性能。结果表明,该文算法的性能最好,检测准确率分别为99.98%和100%。The accurate QRS detection provides fundamentals for the automated ECG analysis.To improve the QRS detection accuracy,a QRS detection method based on the independent component analysis（ICA）and combined wavelet entropy（CWS）is proposed for multi-lead ECG signals.The ICA method is employed to extract independent components（ICs）corresponding to the ventricular activity from filtered multi-lead ECG signals.Each IC is transformed by the continuous wavelet transform（CWT）and the phase space of the CWT coefficient is reconstructed.The IC has been reordered based on the QRS information in the phase space.Finally,the CWS based method is employed to detect the QRS of multi-lead ECG signals.The proposed method is evaluated against the standard St.Petersburg 12-lead arrhythmia database and the 64-lead canine epicardial database with other two different QRS detection methods.Experimental results show that the proposed method achieves the detection rate of 99.97% and 100% respectively,which gives the best overall performance.

关 键 词：多导联ECG QRS检测 独立元分析 连续小波变换 相空间重构 联合小波熵 

分 类 号：R318.0[医药卫生—生物医学工程]