基于自适应多元多尺度熵的心电信号分类研究

Classification of ECG signal based on adaptive multivariate multiscale entropy

针对目前单通道心电信号识别精度不高、现存多元分解方法效果不佳、多元非线性心电信号分析复杂等问题,提出了一种基于自适应多元多尺度色散熵的心电信号分类方法。首先利用频谱分析,创新性地引入了正弦辅助多元经验模态分解方法,对心电信号进行分解得到多元模态分量;然后结合多模态分解和色散熵的优越性,通过累加多元本征模态分量代替粗粒化采样,提出了自适应多元多尺度色散熵的方法获取特征熵值;最后将特征输入到多个分类器上进行分类,通过实验对比分析,在模拟信号和MIT-BIH数据上验证该方案的有效性。

In order to solve the problems of low accuracy of single channel electrocardiogram signal identification and the complexity of multivariate nonlinear electrocardiogram signal analysis by existing multivariate decomposition methods,this paper proposed a classification method of ECG signals based on adaptive multiscale dispersion entropy.Firstly,it used spectrum analysis,innovatively introduced sinusoidal assisted multivariate empirical mode decomposition method to decompose ECG signals to obtain multivariate modal components.Then it combined the advantages of multi-mode decomposition and dispersion entropy,proposed an adaptive multi-scale dispersion entropy method to obtain the characteristic entropy value by adding multiple eigenmode components instead of coarse-grained sampling.Finally,the features were input to multiple classifiers for classification.The effectiveness of the proposed scheme is verified on analog signals and MIT-BIH data by experimental comparison and analysis.