基于混合时频域特征的卷积神经网络心律失常分类方法的研究  

Research on Arrhythmia Classification by Using Convolutional Neural Network with Mixed Time-Frequency Domain Features

作　　者：吕杭 蒋明峰[1] 李杨[1] 张鞠成 王志康[2] LÜHang;JIANG Ming-feng;LI Yang;ZHANG Ju-cheng;WANG Zhi-kang(School of Computer Science and Technology,Zhejiang Sci-Tech University,Hangzhou,Zhejiang 310018,China;The Second Affiliated Hospital,School of Medicine Zhejiang University,Hangzhou,Zhejiang 310009,China)

机构地区：[1]浙江理工大学计算机科学与技术学院,浙江杭州310018 [2]浙江大学医学院附属第二医院,浙江杭州310009

出　　处：《电子学报》2023年第3期701-711,共11页Acta Electronica Sinica

基　　金：浙江省科技厅重点研发项目(No.2020C03060);国家自然科学基金(No.62101497);浙江省自然科学基金-数理医学学会联合基金重点项目(No.LSZ19F010001)。

摘　　要：心律失常是常见的心血管疾病之一,目前很多方法通过计算机辅助系统对心电图进行分析以识别心律失常,但由于大多数心律失常数据样本较少,计算机辅助系统识别心律失常效果不佳.本文提出了一种基于混合时频域分析特征提取的卷积神经网络方法,该方法提取心电图的RR间期时域特征、希尔伯特-黄变换提取的频域特征和连续小波变换提取的时频域联合特征,经过特征融合后输入卷积神经网络训练分类模型,并采用Focal Loss作为网路的损失函数,实现对心律失常的分类.本文使用MIT-BIH(Massachusetts Institute of Technology-Boston’s Beth Israel Hospital)心律失常数据库验证本文提出方法对4类心电数据分类的结果,实验结果表明,与现有的分类算法相比,本文所提出的混合时频域特征方法能有效提升心律失常分类的准确性.Arrhythmia is one of cardiovascular diseases,and many methods are used to analyze electrocardiogram by computer-aided system to identify arrhythmia.However,most of the data samples of arrhythmia are small,and the computeraided system is not effective in identifying arrhythmia.In this paper,a mixed time-frequency domain feature extraction method is proposed for arrhythmia classification by using convolution neural network method.The fused features consist of the time domain characteristics from the RR interval,frequency domain characteristics from hilbert-huang transform,and joint time-fre⁃quency domain features extracted from continuous wavelet transform.Then the fused features are used as an input to the convo⁃lution neural network for training classification model,and the focal loss is used as the loss function of the training model,so as to realize the arrhythmias classification.In addition,the MIT-BIH(Massachusetts Institute of Technology-Boston's Beth Israel Hospital)arrhythmia database is used to verify the performances of the proposed method for arrhythmias classification of four types of ECG(Electrocardiograph)data.Experimental results show that compared with the existing classification algorithms,the proposed method improves the F1 of class obviously.

关 键 词：时频域分析 连续小波变换 希尔伯特-黄变换 心律失常分类 Focal Loss 卷积神经网络 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]