基于二维图像与迁移卷积神经网络的心律失常分类

doi:10.19678/j.issn.1000-3428.0055932

计算机工程 ›› 2020, Vol. 46 ›› Issue (10): 315-320. doi: 10.19678/j.issn.1000-3428.0055932

• 开发研究与工程应用 • 上一篇

基于二维图像与迁移卷积神经网络的心律失常分类

陈敏, 王娆芬

上海工程技术大学电子电气工程学院, 上海 201620

收稿日期:2019-09-05 修回日期:2019-10-09 发布日期:2019-11-04
作者简介:陈敏(1994-),女,硕士研究生,主研方向为生理信号处理、模式识别;王娆芬(通信作者),副教授、博士。
基金资助:
国家自然科学基金（71701124）；国家自然科学基金青年科学基金（61803255）；上海市自然科学基金（18ZR1416700）。

Arrhythmia Classification Based on Two-Dimensional Image and Tranfer Convolutional Neural Network

CHEN Min, WANG Raofen

School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620, China

Received:2019-09-05 Revised:2019-10-09 Published:2019-11-04

摘要/Abstract

摘要： 心律失常的自动分类对心血管疾病的诊断和预防具有重要意义。传统分类方法需要对心电信号进行人工特征提取，这对分类准确度有很大的影响。针对该问题，提出一种基于二维图像与迁移卷积神经网络（TCNN）的分类方法。通过对心电信号进行格拉姆角场变换将其转换为二维图像，在保证心电图像完整性的同时，保留原始信号的时间依赖性。在此基础上，结合迁移学习的思想，设计结构简单且参数量较少的TCNN模型对心电图像进行分类。实验结果表明，该方法网络训练用时较少，并且分类总准确率达到99.82%，可实现对心律失常的有效分类。

关键词: 心电信号, 格拉姆角场, 二维图像, 迁移学习, 迁移卷积神经网络

Abstract: The automatic classification of arrhythmia is very important for the diagnosis and prevention of cardiovascular diseases.Traditional classification methods require artificial feature extraction of ECG signals,which has a great impact on the accuracy of classification.To solve this problem,a classification method based on two dimensional image and Transfer Convolutional Neural Network(TCNN) is proposed.The ECG signal is transformed into a two-dimensional image by means of Gramian Angular Field.The integrity of the ECG image is guaranteed while the time dependence of the original signal is retained.On this basis,combined with the idea of transfer learning,a TCNN model with simple structure and fewer parameters is designed to classify the ECG images.The experimental results show that the network training time of this method is less,and the classification accuracy reaches 99.82%,which can realize the effective classification of arrhythmia.

Key words: ECG signal, Gramian Angular Field(GAF), two-dimensional image, transfer learning, Transfer Convolutional Neural Network(TCNN)

中图分类号:

TP391

陈敏, 王娆芬. 基于二维图像与迁移卷积神经网络的心律失常分类[J]. 计算机工程, 2020, 46(10): 315-320.

CHEN Min, WANG Raofen. Arrhythmia Classification Based on Two-Dimensional Image and Tranfer Convolutional Neural Network[J]. Computer Engineering, 2020, 46(10): 315-320.

http://www.ecice06.com/CN/Y2020/V46/I10/315

图/表 8

20201023094255

20201023094258

20201023094302

20201023094305

20201023094308

20201023094311

20201023094315

20201023094318

参考文献

[1] World Health Organization.Cardiovascular diseases[EB/OL].[2019-08-15].http://www.ho.int/mediacentre/factsheets/fs317/en/.
[2] MENG Yan,ZHENG Gang,DAI Min,et al.Design and implementation of wearable ECG signal acquisition and analysis system[J].Computer Science,2015,42(10):39-42.(in Chinese)孟妍,郑刚,戴敏,等.可穿戴心电信号采集与分析系统的设计与实现[J].计算机科学,2015,42(10):39-42.
[3] MONDÉJAR-GUERRA V,NOVO J,ROUCO J,et al.Heartbeat classification fusing temporal and morphological information of ECGs via ensemble of classifiers[J].Biomedical Signal Processing and Control,2019,47(1):41-48.
[4] SHI Haotian,WANG Haoren,HUANG Yixiang,et al.A hierarchical method based on weighted extreme gradient boosting in ECG heartbeat classification[J].Computer Methods and Programs in Biomedicine,2019,171:1-10.
[5] WANG Raofen,ZHANG Yu,ZHANG Liping.An adaptive neural network approach for operator functional state prediction using psychophysiological data[J].Integrated Computer-Aided Engineering,2016,23(1):81-97.
[6] RAJESH K,DHULI R.Classification of imbalanced ECG beats using re-sampling techniques and AdaBoost ensemble classifier[J].Biomedical Signal Processing and Control,2018,41(3):242-254.
[7] LU Wei,HOU Honghui,CHU Jinghui.Feature fusion for imbalanced ECG data analysis[J].Biomedical Signal Processing and Control,2018,41(3):152-160.
[8] SALEM M,TAHERI S,YUAN J.ECG arrhythmia classification using transfer learning from 2-dimensional deep CNN features[C]//Proceedings of IEEE Conference on Biomedical Circuits and Systems.Washington D.C.,USA:IEEE Press,2018:1-4.
[9] ZUBAIR M,KIM J,YOON C.An automated ECG beat classification system using convolutional neural networks[C]//Proceedings of the 6th International Conference on IT Convergence and Security.Washington D.C.,USA:IEEE Press,2016:1-5.
[10] YILDIRIM Ö,PŁAWIAK P,TAN R,et al.Arrhythmia detection using deep convolutional neural network with long duration ECG signals[J].Computers in Biology and Medicine,2018,102:411-420.
[11] WANG Z G,OATES T.Imaging time-series to improve classification and imputation[C]//Proceedings of the 24th International Joint Conference on Artificial Intelligence.Los Angeles,USA:[s.n.],2015:1-7.
[12] CHEN M C,BALL R L,YANG L,et al.Deep learning to classify radiology free-text reports[J].Radiology,2017,286(3):845-852.
[13] CHEN Bin,ZHOU Yong,LIU Bing.Event trigger word extraction based on convolutional bidirectional long short term memory network[J].Computer Engineering,2019,45(1):153-158.(in Chinese)陈斌,周勇,刘兵.基于卷积双向长短期记忆网络的事件触发词抽取[J].计算机工程,2019,45(1):153-158.
[14] SHI Jun,ZHENG Xiao,WU Jinjie,et al.Quaternion Grassmann average network for learning representation of histopathological image[J].Pattern Recognition,2018,89:67-76.
[15] ACHARYA U R,OH S L,HAGIWARA Y,et al.Automated EEG-based screening of depression using deep convolutional neural network[J].Computer Methods and Program in Biomedicine,2018,161:103-113.
[16] ZHU Ziqi,ZHUO Li,QU Panling,et al.Extreme weather recognition using convolutional neural networks[C]//Proceedings of the 18th IEEE International Symposium on Multimedia.Washington D.C.,USA:IEEE Press,2016:621-625.
[17] LI Xiaoyu,NIE Xiushan,CUI Chaoran,et al.Image retrieval algorithm based on transfer learning[J].Computer Science,2019,46(1):73-77.(in Chinese)李晓雨,聂秀山,崔超然,等.基于迁移学习的图像检索算法[J].计算机科学,2019,46(1):73-77.
[18] LIH O S,EDDIE Y K,RU S T,et al.Automated diagnosis of arrhythmia using combination of CNN and LSTM techniques with variable length heart beats[J].Computers in Biology and Medicine,2018,102:278-287.
[19] ZHA Xuefan,YANG Feng,WU Yu'nan,et al.ECG classification based on transfer learning and deep convolution neural network[J].Chinese Journal of Medical Physics,2018,35(11):1307-1312.(in Chinese)查雪帆,杨丰,吴俣南,等.结合迁移学习与深度卷积网络的心电分类研究[J].中国医学物理学杂志,2018,35(11):1307-1312.
[20] YILDIRIM Ö.A novel wavelet sequence based on deep bidirectional LSTM network model for ECG signal classification[J].Computers in Biology and Medicine,2018,96:189-202.

选择文件类型/文献管理软件名称

选择包含的内容

基于二维图像与迁移卷积神经网络的心律失常分类

Arrhythmia Classification Based on Two-Dimensional Image and Tranfer Convolutional Neural Network

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	王爱玲, 马文臻, 邹自明, 钟佳. 基于领域自适应的卫星工程参数异常检测[J]. 计算机工程, 2023, 49(5): 29-37,47.
[2]	白俊卿, 韩柏迅, 张丰侠. 基于深度学习的无人机图像语义分割算法研究[J]. 计算机工程, 2023, 49(4): 233-239.
[3]	郑云涛, 叶家炜. 基于茫然传输协议的FATE联邦迁移学习方案[J]. 计算机工程, 2023, 49(2): 24-30.
[4]	伍洲, 杨寒石, 邬俊俊, 张海军, 宋晴. 进化迁移优化算法综述[J]. 计算机工程, 2023, 49(1): 1-14.
[5]	邱鸿辉, 刘海林, 陈磊. 基于协方差矩阵调整的多目标多任务优化算法[J]. 计算机工程, 2022, 48(8): 306-312.
[6]	王丽娟, 张霖, 尹明, 郝志峰, 蔡瑞初, 温雯. 基于正交基的多视图迁移谱聚类[J]. 计算机工程, 2022, 48(10): 37-44,54.
[7]	梁正友, 刘德志, 孙宇. 结合迁移学习与可分离三维卷积的微表情识别方法[J]. 计算机工程, 2022, 48(1): 228-235.
[8]	顾亦然, 霍建霖, 杨海根, 卢逸飞, 郭玉雯. 基于BERT的电机领域中文命名实体识别方法[J]. 计算机工程, 2021, 47(8): 78-83,92.
[9]	李晶晶, 孟利超, 张可, 鲁珂, 申恒涛. 领域自适应研究综述[J]. 计算机工程, 2021, 47(6): 1-13.
[10]	王军, 赵凯, 程勇. 基于遮挡感知卷积神经网络的面部表情识别模型[J]. 计算机工程, 2021, 47(10): 242-251.
[11]	李庆忠, 徐相玉. 基于改进YOLOV3-Tiny的海面船舰目标快速检测[J]. 计算机工程, 2021, 47(10): 283-289,297.
[12]	谢瑞, 邵堃, 霍星, MITHUN Md Masud Parvej. 一种改进的DIQaM_FR/NR图像质量评价模型[J]. 计算机工程, 2020, 46(8): 258-263,270.
[13]	周胜, 刘三民. 基于动态策略的多源迁移学习数据流分类研究[J]. 计算机工程, 2020, 46(5): 139-143,149.
[14]	张强, 张勇, 刘芝国, 周文军, 刘佳慧. 基于改进YOLOv3的手势实时识别方法[J]. 计算机工程, 2020, 46(3): 237-245,253.
[15]	尚瑛杰, 董丽亚, 何虎. 基于脉冲神经网络的迁移学习算法与软件框架[J]. 计算机工程, 2020, 46(3): 53-59.

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

基于二维图像与迁移卷积神经网络的心律失常分类

Arrhythmia Classification Based on Two-Dimensional Image and Tranfer Convolutional Neural Network

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献

相关文章 15

编辑推荐

Metrics

本文评价