Study on ECG Signal Recognition and Classification Based on U-Net++
Computer Science

Computer Science ›› 2021, Vol. 48 ›› Issue (10): 121-126.doi: 10.11896/jsjkx.200700103

• Artificial Intelligence • Previous Articles     Next Articles

Study on ECG Signal Recognition and Classification Based on U-Net++

YANG Chun-de1,2, JIA Zhu1, LI Xin-wei2   

  1. 1 School of Computer Science and Technology,Chongqing University of Posts and Telecommunications,Chongqing 400065,China
    2 School of Biological Information,Chongqing University of Posts and Telecommunications,Chongqing 400065,China
  • Received:2020-07-16 Revised:2020-10-20 Online:2021-10-15 Published:2021-10-18
  • About author:YANG Chun-de,born in 1964,master,professor.His main research interests include digital image processing,information and computing theory.
    LI Xin-wei,born in 1990,Ph.D,lectu-rer.Her main research interests include biomedical image processing and so on.
  • Supported by:
    Science and Technology Research Project of Chongqing Education Commission(KJQN201800622).

PDF (PC)

1324

Abstract: It is difficult to explore efficient,fast and accurate ECG signal recognition and classification algorithm.The classification of ECG fragments is more suitable for clinical application.Based on this,the improved generation countermeasure network (DCGAN) is used for data expansion,and the optimized one-dimensional U-Net++ is used for fragment signal recognition of arrhythmia.ECG fragments from 1 200 sampling points in MIT-BIH database are continuously intercepted as the experimental data set,and the type that appears the most times of beats in each fragment recording center is used as the label of the whole record.Then the DCGAN,which uses optimized one-dimensional U-Net++ as generator,is used to realize partial data expansion to solve the problem of data imbalance.Under the condition that the original ECG signals are not preprocessed and the generated extended data are used to complete the wavelet threshold denoising,the accuracy of the optimized one-dimensional U-Net++ model for normal,ventricular premature beat,left bundle branch block,right bundle branch block four kind of different type can reach 98.10% for the training sets.The precision ratio,recall ratio and F1 score of the test set have good results.Under the same experimental data set,the accuracy of U-Net++ model is 1.05% higher than that of U-Net model.Under the same experimental parameters,compared with under sampling data,the accuracy of the experimental model of the data set expanded by DCGAN is improved by 0.85%.

Key words: DCGAN, ECG, MIT-BIH, Recognition and classification, U-Net++

CLC Number: 

  • TN911.7
[1]MA J W,LIU S P.Overview of ECG Signal Recognition andClassification Algorithms[J].Journal of Chongqing University of Technology (Natural Science),2018,32(12):122-128.
[2]JIN L P,DONG J.Study on Classification Algorithm of Clinical Electrocardiogram based on Integrated Learning[J].Journal of Biomedical Engineering,2016,33(5):825-833.
[3]MA R L,LIU X,ZHANG Y,et al.Deep learning based on ECG Signal anomaly Recognition Method[J].Transducer andMicro-system Technologies,2020,39(1):29-32.
[4]CHEN M,WANG R F.Arrhythmia Classification Based onTwo-Dimensional Image and Tranfer Convolutional Neural Network[J].Computer Engineering,2020,46(10):315-320.
[5]FENG Y R,CHEN W,CAI G Y.Biometric Extraction and Re-cognition based on ECG Signals[J].Computer & Digital Engineering,2016,46(6):1099-1103.
[6]VENKATESAN C,KARTHIGAIKUMAR P,VARATHARAJAN R.A novel LMS Algorithm for ECG Signal Preprocessing and KNN Classifier-based Abnormality Detection[J].Multi-media Tools and Applications,2018,77(8):10365-10374.
[7]ZHANG K,LI X,XIE X J,et al.Study on Arrhythmia Detection Algorithm based on Deep Learning[J].Chinese Medical Equipment Journal,2008,39(12):6-9,31.
[8]LI D,ZHANG H X,LIU Z Q,et al.Recognition of Arrhythmia in ECG based on Deep Residual Convolution Neural Network[J].Journal of Biomedical Engineering,2019,36(2):189-198.
[9]HESAR H D,MOHEBBI M.An Adaptive Kalman Filter Bank for ECG Denoising[J].IEEE Journal of Biomedical and Health Informatics,2021,25(1):13-21.
[10]GAO N H,WANG H,FENG X H.Classification Method ofElectrocardiogram Signals Based on Dynamic Fuzzy Decision Tree[J].Computer Engineering,2020,46(1):80-86.
[11]RONNEBERGER O,FISCHER P,BROX T.U-Net:ConvolutionalNetworks for Biomedical Image Segmentation[C]//Internatio-nal Conference on Medical Image Computing & Computer-assisted Intervention.Cham:Springer,2015:234-241.
[12]LONG J,SHELHAMER E,DARRELL T.Fully Convolutional Networks for Semantic Segmentation[C]//IEEE Conference on Computer Vision and Pattern Recognition.2015:3431-3440.
[13]ZHOU Z,SIDDIQUEE M M R,TAJBAKHSH N,et al. U-Net++:A Nested U-Net Architecture for Medical Image Segmentation[C]//Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support.Cham:Springer,2018:3-11.
[14]HUANG G,LIU Z,MAATEN L V D,et al.Densely Connected Convolutional Networks[C]//IEEE Conference on Computer Vision and Pattern Recognition.2017:2261-2269.
[15]LIN M,CHEN Q,YAN S.Network in network[J].arXiv:1312.4400,2013.
[16]KRIZHEVSKY A,SUTSKEVER I,HINTON G E.Image-net Classification with Deep Convolutional Neural Networks[C]//Advances in Neural Information Processing Systems.2012:1097-1105.
[17]LIANG J J,WEI J J,JIANG Z F.Overview of GAN Generation Adversarial Network[J].Journal of Frontiers of Computer Scien-ce and Technology,2020,14(1):1-17.
[18]GOODFELLOW I,POUGET-ABADIE J,MIRZA M,et al.Gene-rative Adversarial Nets[C]//Advances in Neural Information Processing Systems.2014:2672-2680.
[19]CHEN G D,ZENG Y L,LI Z.Adaptive Double Threshold ECG Signal Detection Algorithm Research[J].Journal of Jinan University (Natural Science & Medicine Edition),2008,39(3):262-268.
[20]LUO B.Research on the solution of interference signal removal in electrocardiograph [J].Quality & Market,2020(14):88-90.
[21]LI F,XIE S H.Abnormal Diagnosis of Mobile ECG based on Unsupervised Learning[J].Computer Science,2017,44(S2):68-71,109.
[22]FAN M,WANG X F,MENG X F.Research on Wearable ECG Adaptive Classification Algorithm [J].Computer Science,2019,46(12):292-297.
[23]GAO H J,QIU T S,CHOU Y T,et al.Fundus Image Vascular Segmentation based on Improved U-Net Network[J].Chinese Journal of Biomedical Engineering,2019,38(1):1-8.
[24]OH S L,NG E Y K,TAN R S,et al.Automated Beat-wiseArrhythmia Diagnosis using Modified U-Net on Extended Electrocardiographic Recordings with Heterogeneous Arrhythmia Types[J].Computers in Biology and Medicine,2019,105:92-101.
[1] ZHANG Xiao-yu, WANG Bin, AN Wei-chao, YAN Ting, XIANG Jie. Glioma Segmentation Network Based on 3D U-Net＋+ with Fusion Loss Function [J]. Computer Science, 2021, 48(9): 187-193.
[2] ZHANG Man, LI Jie, ZHU Xin-zhong, SHEN Ji, CHENG Hao-tian. Augmentation Technology of Remote Sensing Dataset Based on Improved DCGAN Algorithm [J]. Computer Science, 2021, 48(6A): 80-84.
[3] LI Hua-ji, CHENG Jiang-hua, LIU Tong, CHENG Bang, ZHAO Kang-cheng. Low-light Image Enhancement Method Based on U-net++ Network [J]. Computer Science, 2021, 48(11A): 278-282.
[4] FAN Min, WANG Xiao-feng, MENG Xiao-feng. Study on Patient-adaptive Algorithm for ECG Classification Based on Wearable Devices [J]. Computer Science, 2019, 46(12): 292-297.
[5] LI Feng and XIE Si-hong. Study on Abnormal Diagnosis of Moving ECG Signals Based on Unsupervised Learning [J]. Computer Science, 2017, 44(Z11): 68-71.
[6] LENG Li-hua and ZHENG Zhi-jie. Visualization Research of ECG Sequence in Sinus Arrhythmia [J]. Computer Science, 2016, 43(Z11): 183-185.
[7] PENG Zi-ran and WANG Gou-jun. Research and Improvement of ECG Compression Algorithm Based on EZW [J]. Computer Science, 2016, 43(11): 142-147.
[8] TANG Xiao, SHU Lan and ZHENG Wei. Premature Beat Signal Recognition Algorithm Based on Wavelet Transform and Rough Set [J]. Computer Science, 2015, 42(Z11): 32-35.
[9] WANG Wei-ping and YANG Miao. USDZQ Optimization Based on Ant Colony Algorithm and Application in ECG Compression [J]. Computer Science, 2015, 42(Z11): 550-553.
[10] MENG Yan, ZHENG Gang, DAI Min and ZHAO Rui. Design and Implementation of Wearable ECG Signal Acquisition and Analysis System [J]. Computer Science, 2015, 42(10): 39-42.
[11] LI Nan,YANG Zhao-chun,SUN Le-jun and WEI Rong-guo. Extraction Method Based on Q Wavelet Transform of ECG Signal Characteristic [J]. Computer Science, 2014, 41(Z11): 61-64.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
Add:18# Honghu West Rd., Yubei ,Chongqing,China    Post Code: 401121
Tel: 023-63500828/023-67039612/023-67039623
E-mail: jsjkx12@163.com
Powered by Beijing Magtech Co., Ltd.