小波包分析和形态学滤波相结合的心电图QRS波群定位  

Location of QRS waves in ECG based on wavelet packet analysis and morphological filter

作　　者：刘金江[1] 王春光[2] 孙即祥[2] 

机构地区：[1]南阳师范学院计算机系,河南南阳473061 [2]国防科技大学电子科学与工程学院,湖南长沙410073

出　　处：《计算机工程与设计》2007年第11期2726-2729,共4页Computer Engineering and Design

摘　　要：心电图波形特征提取是针对一维心电信号的弱信号特征提取。如何排除各种干扰,提取出心电波形特征,并准确定位心电信号中P波、QRS波群,T波,一直是心脏病智能诊断的难点和热点问题,其中QRS波群的定位又是其它波定位的重要依据,利用形态学和小波包理论相结合的方法对这一问题进行了探讨,提出了QRS波群定位和滤除基线漂移的方法。实验证明提出的方法速度较快,能较准确的定位QRS波群、有效的去除基线漂移。The feature extraction ofECG waveform is a kind of weak signal characteristic extraction aiming at one dimension ECG signal. It is a difficulty and focused problem during diagnosing intellectively cardiopathy that how to exclude all kinds of interference and to extract the ECG waveform feature and to locate accurately P wave, QRS waves, T wave of ECG signals. Moreover, the location of QRS waves is the important foundation of other wave locations. This problem is discussed using a combined method based on morphology and wavelet packet theory and a method of wave location and filtering baseline excursion is posed. The experimental result prove to be faster and to locate accurately the QRS waves and to takeoff effectively baseline excursion.

关 键 词：心电图 小波包 一维形态学 特征提取 基线漂移 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]