小波变换在心电信号特征提取中的应用  

The Application of Wavelet Transform in ECG Feature Extraction

作　　者：万相奎[1] 秦树人[1] 梁小容[1] 叶顺流[1] 

机构地区：[1]重庆大学机械工程学院测试中心

出　　处：《北京生物医学工程》2005年第6期410-413,共4页Beijing Biomedical Engineering

基　　金：重庆市科技攻关项目(7238)资助

摘　　要：采用分段阈值和模极大值对斜率判据相结合的补偿策略,提出了一种精确提取QRS波群特征值的算法。经过对MIT/BIH心电数据库和临床实测的心电信号的大量实验,结果显示即使在有严重噪声干扰的情况下,运用本算法也很容易实现对QRS波群特征的有效提取,特别是对R波峰具有相当高的定位精度(其误差不超过一个采样点)和分析精度(没有累积误差)。It is an essential and vital function for ECG analysis instrument to exactly extract the information of QRS complexes. A dyadic spline wavelet is chosen as mother wavelet, and multi-scale wavelet decomposition is applied to the ECG signals. According to the characteristics of transformed signal, it is found that the signal at 3^rd （ S = 2^3 ） scale is suitable for extracting the QRS characteristic waves of ECG signals. There exists the corresponding relationship between a characteristic point （R peak point） of the ECG signals and a zero - crossing point of the modulus maximum pair. Combining with some compensation tactics （e. g. sectional threshold values and slope criterion for the modulus maximum pair） we present an algorithm for accurate extracting QRS complex. The algorithm is applied to massive data from MIT/BIH arrhythmia database and clinic, and the experimental results indicate that even for the data contaminated by serious noise it is easy to extract the feature information of QRS complexes. The locating precision （no more than one sampling points error） and analyzing accuracy for R peaks （no accumulative error） are high.

关 键 词：心电图 小波变换 阈值 特征提取 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]