基于深度学习技术的心律失常诊断与个体识别算法研究

doi:10.3969/j.issn.2095-2198.2023.06.011

摘要
参考文献
相关文章
推荐阅读
Metrics

下载:

PDF (2645KB)
输出: BibTeX | EndNote (RIS)

摘要

针对传统机器学习算法的弊端，提出一种基于深度学习的心率失常信号诊断和心电信号个体识别的改进算法.该方法通过加入改进的卷积注意力模块，将一维卷积神经网络和双向长短时网络结合，提出一种新的模型L-CNN对心律失常心电信号进行诊断识别.实验结果表明：L-CNN算法模型比现有研究的算法模型的识别精度最低提高了1.23%.与传统识别技术相比，基于心电信号的识别技术具有广阔的应用前景

	服务
	把本文推荐给朋友
	加入引用管理器
	E-mail Alert
	RSS
	（）
	作者相关文章

关键词: 心电识别深度学习卷积神经网络双向长短时网络卷积注意力模块

Abstract:

In view of the drawbacks of the traditional machine learning algorithm,an improved algorithm based on deep learning for diagnosing arrhythmia signal and individual recognition of ECG signal is proposed.By adding an improved CBAM module and combining one-dimensional convolutional neural network with bidirectional LSTM,a new model L-CNN is proposed to diagnose and recognize arrhythmia ECG signals.The experimental results show that the recognition accuracy is 1.23% higher than that of the existing research.Compared with the traditional recognition technology,the recognition technology based on ECG signal has broad application prospect.

Key words: ECG recognition')" href="#">

ECG recognition deep learning convolutional neural network bidirectional LSTM convolutional block attention module

出版日期: 2024-12-31 发布日期: 2024-09-23 整期出版日期: 2024-12-31

ZTFLH:

R318.6

通讯作者: 袁德成

作者简介: 诗雨桐（1995—），男，辽宁铁岭人，硕士研究生在读，主要从事深度学习图像识别的研究.

引用本文:

诗雨桐, 袁德成.

基于深度学习技术的心律失常诊断与个体识别算法研究 [J]. 沈阳化工大学学报, 2023, 37(6): 547-553.
SHI Yutong, YUAN Decheng.

Research on Arrhythmia Diagnosis and Individual Identification Algorithm Based on Deep Learning Technology . Journal of Shenyang University of Chemical Technology, 2023, 37(6): 547-553.

链接本文:

https://xuebao.syuct.edu.cn/CN/10.3969/j.issn.2095-2198.2023.06.011 或 https://xuebao.syuct.edu.cn/CN/Y2023/V37/I6/547

［1］吴从中,王浩宇,詹曙.融合曲面形状和纹理特征的三维人脸识别［J］.电子测量与仪器学报,2018,32(9):150-156.

［2］薛杉,朱虹,吴文欢.单样本的低分辨率单目标人脸识别算法［J］.仪器仪表学报,2019,40(3):196-202.

［3］GHAHABI O,HERNANDO J.Restricted Boltzmann Machines for Vector Representation of Speech in Speaker Recognition［J］.Computer Speech & Language,2018,47:16-29.

［4］顾陈磊,刘宇航,聂泽东,等.指纹识别技术发展现状［J］.中国生物医学工程学报,2017,36(4):470-482.

［5］AGARWAL A,KESHARI R,WADHWA M,et al.Iris Sensor Identification in Multi-Camera Environment［J］.Information Fusion,2019,45:333-345.

［6］刘笑楠,白雨辰,尹思璐,等.基于类卷积神经网络的可见光虹膜识别方法［J］.仪器仪表学报,2017,38(11):2651-2658.

［7］DAR M N,AKRAM M U,USMAN A,et al.ECG Biometric Identification for General Population Using Multiresolution Analysis of DWT Based Features［C］//2015 Second International Conference on Information Security and Cyber Forensics(InfoSec).Los Alamitos,CA:IEEE Computer Society,2015:5-10.

［8］ZHANG Q X,ZHOU D,ZENG X.HeartID:a Multiresolution Convolutional Neural Network for ECG-Based Biometric Human Identification in Smart Health Applications［J］.IEEE Access,2017,5:11805-11816.

［9］陈滨.基于深度学习的心电图类型识别和个体识别［D］.北京:北京交通大学,2019:51-55.

［10］杨朔,蒲宝明,李相泽,等.基于深度长短时记忆神经网络模型的心律失常检测算法［J］.计算机应用,2019,39(3):930-934.

［11］张建伟,王苗苗.基于小波包的撞击流反应器速度信号降噪分析［J］.沈阳化工大学学报,2015,29(2):159-163.

［12］WOO S,PARK J,LEE J Y,et al.CBAM:Convolutional Block Attention Module［C］//Computer Vision-ECCV 2018.Cham:Springer,2018:3-19.

［13］王晓,尹德升.机器学习方法的比较［J］.中国科技博览,2009(36):36.

［14］DERYA BEYLI E.Recurrent Neural Networks Employing Lyapunov Exponents for Analysis of ECG Signals［J］.Expert Systems with Application,2010,37(2):1192-1199.

［15］QU X,JIAN C W,FEI G D.ECG Signal Classification Based on BPNN［C］//2011 International Conference on Electric Information and Control Engineering.Los Alamitos,CA:IEEE Computer Society,2011:1362-1364.

［16］FAZILUDEEN S,SABIQ P V.ECG Beat Classification Using Wavelets and SVM［C］//2013 IEEE Conference on Information & Communication Technologies.Los Alamitos,CA:IEEE Computer Society,2013:815-818.

［17］KARPAGACHELVI S.Classification of ECG Signals Using Hybrid Particle Swarm Optimization in Extreme Learning Machine［J］.Internation Journal of Applied Science and Engineering Research，2014,3(6):1089-1098.

［18］ACHARYA U R,OH S L,HAGIWARA Y,et al.A Deep Convolutional Neural Network Model to Classify Heartbeats［J］.Computers in Biology and Medicine,2017,89:389-396.

［19］HE C G,LI W,CHIK D.Waveform Compensation of ECG Data Using Segment Fitting Functions for Individual Identification［C］//2017 13th International Conference on Computational Intelligence and Security(CIS).Los Alamitos,CA:IEEE Computer Society,2017:475-479.

[1]	宁泽惺1, 袁德成2. 基于条件约束下的自注意力生成对抗网络的图像修复 [J]. 沈阳化工大学学报, 2024, 38(1): 90-96.
[2]	韩煜, 张凯. 基于短时傅里叶变换的卷积神经网络复合故障诊断 [J]. 沈阳化工大学学报, 2023, 37(1): 68-73.
[3]	诗雨桐, 袁德成. 基于深度学习的面部微表情识别 [J]. 沈阳化工大学学报, 2021, 35(4): 380-384.
[4]	李元, 杨东昇, 李大舟. 基于二维卷积神经网络高层数据特征学习的过程故障检测[J]. 沈阳化工大学学报, 2021, 35(3): 256-264.

No Suggested Reading articles found!

Viewed

Full text

Abstract

Cited

Shared

Discussed