Classification of electrocardiogram signals with support vector machines and genetic algorithms using power spectral features
Classification of electrocardiogram signals with support vector machines and genetic algorithms using power spectral features
复制标题
DOI：
10.1016/j.bspc.2010.07.006
复制
发表时间：
2010-10-01
影响因子：
5.1
通讯作者：
Ebrahimzadeh, A.
中科院分区：
文献类型：
--
作者：
Khazaee, A.;Ebrahimzadeh, A.
本文提出了一种新的基于功率谱的混合遗传算法-支持向量机（SVMGA）技术来分类五种类型的心电图（ECG）搏动，即正常搏动和心律失常的四种表现。该方法包括三个模块：特征提取模块、分类模块和优化模块。特征提取模块提取心电图的频谱特征和三个时间间隔特征。非参数功率谱密度（PSD）估计方法被用来提取频谱特征。采用支持向量机（SVM）作为分类器对心电信号进行分类识别。我们调查和比较两个这样的分类方法。首先，它们是通过试错法实验性地确定的。在第二种技术中，该方法通过智能算法优化相关参数。这些参数是：高斯径向基函数（GRBF）核参数a和C惩罚参数的SVM分类器。然后针对从MIT-BIH心律失常数据库中获得的八个文件评估它们在心电图信号分类中的性能。SVMGA方法的分类精度证明上级的支持向量机，其中有常数和手动提取的参数。(C)2010爱思唯尔有限公司版权所有。
This paper proposes a new power spectral-based hybrid genetic algorithm-support vector machines (SVMGA) technique to classify five types of electrocardiogram (ECG) beats, namely normal beats and four manifestations of heart arrhythmia. This method employs three modules: a feature extraction module, a classification module and an optimization module. Feature extraction module extracts electrocardiogram's spectral and three timing interval features. Non-parametric power spectral density (PSD) estimation methods are used to extract spectral features. Support vector machine (SVM) is employed as a classifier to recognize the ECG beats. We investigate and compare two such classification approaches. First they are specified experimentally by the trial and error method. In the second technique the approach optimizes the relevant parameters through an intelligent algorithm. These parameters are: Gaussian radial basis function (GRBF) kernel parameter a and C penalty parameter of SVM classifier. Then their performances in classification of ECG signals are evaluated for eight files obtained from the MIT-BIH arrhythmia database. Classification accuracy of the SVMGA approach proves superior to that of the SVM which has constant and manually extracted parameter. (C) 2010 Elsevier Ltd. All rights reserved.