EMD近似熵结合支持向量机的心音信号识别研究

PDF(1075 KB)

振动与冲击 ›› 2012, Vol. 31 ›› Issue (19) : 21-25.

论文

EMD近似熵结合支持向量机的心音信号识别研究

黄林洲，郭兴明，丁晓蓉

作者信息 +

Heart sound recognition based on EMD Approximate Entropy and SVM

HUANG Lin-zhou, GUO Xing-ming, DING Xiao-rong

Author information +

文章历史 +

摘要

针对心音信号的非线性、非平稳特征和心音识别准确率不高且分类速度较慢的实际情况，提出一种经验模式分解(Empirical Mode Decomposition，EMD)近似熵(Approximate Entropy，ApEn)结合支持向量机(Support Vector Machine，SVM)的心音分类识别方法。首先通过EMD方法将非平稳的心音振动信号分解成若干个平稳的固有模态函数(Intrinsic Mode Function，IMF)；然后利用互相关系数准则对IMF进行筛选，计算所筛选IMF的近似熵构成特征向量；最后将特征向量输入SVM分类器进行分类识别。对临床采集的心音样本按本文提出的方法进行测试，结果表明，该方法能有效地用于心音识别。

Abstract

Aiming at the non-stationary and non-linear characteristics of heart sound and the difficulty to gain high accuracy and classification speed, a new pathological diagnosis method based on Empirical Mode Decomposition (EMD) Approximate Entropy (ApEn) and Support Vector Machine (SVM) is proposed. Firstly, the heart sound signals are decomposed into a finite number of Intrinsic Mode Function (IMF). Then, the Approximate Entropy of five intrinsic mode functions can be quantitatively evaluated as the eigenvectors. Finally, the eigenvectors are put into support vector machine categorizer for automatic discrimination between normal and abnormal signals. The clinical data experimental diagnosis and contract test results showed that the approach proposed could identify the pathological heart sound effectively.

导出引用

黄林洲;郭兴明;丁晓蓉. EMD近似熵结合支持向量机的心音信号识别研究[J]. 振动与冲击, 2012, 31(19): 21-25

HUANG Lin-zhou;GUO Xing-ming;DING Xiao-rong. Heart sound recognition based on EMD Approximate Entropy and SVM[J]. Journal of Vibration and Shock, 2012, 31(19): 21-25