基于子波多尺度分辨的心电QRS波分类方法的研究  

An Approach to Achieve Classification of QRS Waves with Wavelet Multiresolution Analysis and Fractal Dimension

作　　者：李海云[1] 郝冬梅[1] 段元民 

机构地区：[1]首都医科大学医学工程系医学仪器教研室,北京100054

出　　处：《生物医学工程学杂志》2000年第4期451-453,共3页Journal of Biomedical Engineering

摘　　要：本文分析了心电QRS波的子波多尺度分辨特征 ,探讨了曲线非线性分形维数的计算方法 ,提出了一种新的QRS波的分类方法 :对心电QRS复合波进行子波多尺度分解 ,在尺度为 4的情况下 ,根据局部正负极大值对检测出它们前后两个零点ZP1,ZP2 ,计算出局部正负极大值对位于 |ZP1,ZP2 |之间的曲线段的分形维数。根据局部正负极大值对的幅度和分形维数能很好地检出正常心电信号的QRS波及早搏信号 ;该方法具有很强的抗噪能力 ,提高了QRS波的正确检出率。This paper discussed the theoretical analysis of multiresolution ECGs decomposition and expounds the calculation of the fractal dimension. Based on Mallat's multiresolution analysis and fractal dimension of the series, a new approach to classify the QRS complex was provided:the QRS complex was decomposed with a quadratic spline wavelet. At scale 4, the fractal dimension of the decomposed series was calculated, the values of modulus maxima of wavelet transform and the fractal dimension were used as discriminatory criteria to classify QRS. The method was simple and had high anti noise ability.

关 键 词：QRS分类 子波变换 分形维数 

分 类 号：R540.4[医药卫生—心血管疾病]