基于EMD和ApEn特征提取的心律失常分类研究

Arrhythmia classification algorithm based on EMD and ApEn feature extraction

心律失常分类是心电图自动分析领域的重要研究内容,其中精准的特征提取在分类中起着至关重要的作用。提出一种基于经验模式分解(empirical mode decomposition,EMD)和近似熵(approximate entropy,ApEn)相结合的心电信号特征提取的新方法。首先利用EMD将心电信号分解为不同的本征模函数(intrinsic mode function,IMF),计算前6个IMF分量的近似熵作为特征向量。然后利用粒子群优化算法(particle swarm optimization,PSO)优化后的支持向量机(support vector machine,SVM)分类器进行分类。经过美国麻省理工MIT-BIH心律失常数据库进行验证,该方法能够对心律失常进行有效分类,其分类精度可达98.57%。

Electrocardiogram(ECG) signal classification is an important diagnosis tool where in feature extraction plays a crucial function.This paper proposes a novel method for the nonlinear feature extraction of ECG signals by combining empirical mode decomposition(EMD) and approximate entropy(ApEn).The proposed method first uses EMD to decompose ECG signals into different frequency bands and then calculates the ApEn of each wavelet packet coefficient as a feature vector.A support vector machine(SVM)classifier is used for the classification.The particle swarm optimization(PSO) algorithm is used to optimize the SVM parameters.After MIT-BIH arrhythmia database was validated,the accuracy rate can reach 98.57%.