电子测量与仪器学报

梁盛德,王寻,梁金福.基于卷积神经网络和心电QRS波群的身份识别[J].电子测量与仪器学报,2020,34(4):1-10

基于卷积神经网络和心电QRS波群的身份识别

Human identification using convolutional neural network and QRS complex in ECG

DOI：

英文关键词:electrocardiograph QRS complex human identification convolutional neural network

基金项目:国家自然科学基金（11564006, 11864007）资助项目

作者	单位
梁盛德	1.甘肃民族师范学院物理与水电工程系
王寻	2.中国科学院声学研究所语言声学与内容理解重点实验室
梁金福	3.贵州师范大学物理与电子科学学院

Author	Institution
Liang Shengde	1. Department of Physics and Hydropower Engineering, Gansu Normal University for Nationalities
Wang Xun	2. Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics,Chinese Academy of Sciences
Liang Jinfu	3. School of Physics and Electronic Science, Guizhou Normal University

摘要点击次数: 473

全文下载次数: 463

中文摘要:

利用生物特征进行身份识别是目前模式识别领域的研究热点之一，由于人体的心电信号较为稳定且容易获取，因此利用心电进行身份识别得到了广泛的关注。传统基于心电的身份识别算法需要预先提取特征，然后进行模式识别，处理流程比较复杂，且容易受到噪声的影响。考虑心电QRS波群具有相对稳定的特点，利用QRS波群进行身份识别。首先对心电信号进行小波阈值降噪，然后提取QRS波群，将其转换为二值图，最后输入到卷积神经网络进行身份识别。通过几种不同超参数的卷积神经网络的计算比较，发现本文所述方法的最高准确率可达982%。此外，也对比了其他典型心电身份识别方法，结果表明，所述方法的识别准确率高于其他算法。

英文摘要:

Human identification based on biological features is one of the research hotspots nowadays. Considering electrocardio signals are relatively stable and they can be easily acquired, identification using electrocardio signals attracts the attention of many researchers. Traditional identification methods which are based on electrocardio signals usually extract the features artificially. The procedures are complicated and could be easily affected by noise. Because QRS complex is stable even though the duration of cardiac cycle changes, this research uses QRS complex to identify humans. The electrocardio signals are denoised by the wavelet threshold denoising method, and the QRS complexes are extracted to be transferred to binary images. These images are feed to convolutional neural networks to do the identification. This paper compares the performance of several neural networks of different hyper parameters, and finds the highest accuracy reaches 982%. Besides, this paper discusses some other human identification methods which are based on electrocardio signals. Results show that the method proposed in this paper is better than the others.

查看全文查看/发表评论下载PDF阅读器