Education, Science, Technology, Innovation and Life
Open Access
Sign In
  1. Home
  2. Journals
  3. Advances in Computer, Signals and Systems
  4. Vol 6, Issue 5, 2022

A Classification Scheme for ECG Signals Based on Bidirectional LSTM Model

Download as PDF

DOI: 10.23977/acss.2022.060506 | Downloads: 9 | Views: 576

Author(s)

Shuoxuan Zhang 1, Xinmi Zhang 1, Yuanyuan Huang 1, Zhenlin Dai 1, Jianhua Wang 1

Affiliation(s)

1 Sydney Smart Technology College, Northeastern University at Qinhuangdao, Tangshan, 066004, China

Corresponding Author

Shuoxuan Zhang

ABSTRACT

The application of ECG to diagnose cardiovascular diseases is a common method in clinical medicine, so the use of deep learning tools to achieve automatic analysis and classification of ECG has been a research direction for a wide range of researchers. This paper proposes a classification model for ECG signals based on a bidirectional LSTM model which is trained and tested using the dataset used for the PhysioNet 2017 computational cardiology challenge. The data are normalized and then processed by feature extraction. After passing a bidirectional LSTM layer, a fully connected layer, a softmax layer, and a classification layer in the model, and finally achieve the binary classification of normal signals and atrial fibrillation signals. In this process, the feature of bidirectional LSTM that can integrate contextual information is fully utilized. The experiments show that the classification accuracy of the model reaches 94.1%, demonstrating a good classification result.

KEYWORDS

Bidirectional LSTM, ECG signal, Deep learning, ECG, Feature extraction

CITE THIS PAPER

Shuoxuan Zhang, Xinmi Zhang, Yuanyuan Huang, Zhenlin Dai, Jianhua Wang, A Classification Scheme for ECG Signals Based on Bidirectional LSTM Model. Advances in Computer, Signals and Systems (2022) Vol. 6: 36-44. DOI: http://dx.doi.org/10.23977/acss.2022.060506.

REFERENCES

[1] Chen, Xie, Yuan, et al. Research on a Real-Time Monitoring Method for the Wear State of a Tool Based on a Convolutional Bidirectional LSTM Model[J]. Symmetry, 2019, 11(10):1233.
[2] Pahar M ,  Miranda I ,  Diacon A , et al. Automatic non-invasive Cough Detection based on Accelerometer and Audio Signals[J].  2021.
[3] Qian Kun. Dynamic electrocardiogram in diagnosis of arrhythmia in patients with coronary heart disease Comparative analysis with conventional ECG [J]. Journal of Clinical Medicine in Practice, 2017, 21(09): 191-192.
[4] Zhang Aiai, ZHANG Pengxiang, WANG Xiaoyuan, LI Feixing, LI Fangjiang. Assessment on efficacy of remote monitoring with artificial intelligence electrocatdiogram in ECG critical value processing [J]. Chin J Evid Based Cardiovasc Med, 2022, 14(04): 431-433.
[5] Wang Guanjun, WU Ting, WANG Long, TANG Zusheng. Research of ECG diagnosis based on machine learning [J]. Journal of Practical Electrocardiology, 2020, 29(04): 262-268+297. DOI: 10.13308/j.issn.2095-9354.2020.04.007.
[6] Sun Bo, Yang Lei, Guo Xiumei et al. A Novel Method for ECG Signal Recognition Based on CNN and SVM Hybrid Mode [J]. Journal of Shandong Agricultural University (Natural Science Edition), 2020, 51(02): 283-288.
[7] Liu Shouhua, Wang Xiaosong, LIU Yu. Clinical Electrocardiogram Classification Algorithm Based on Deep Learning [J]. Computer and modernization, 2021(08): 52-57.
[8] Xie Shenglong, Zhang Weimin, LU Yujun Et Al. Research on Intelligent Diagnosis of Atrial Fibrillation Based on One-dimensional Convolution Neural Network [J]. Journal of Metrology, 2020, 41(05): 620-626.
[9] Wei Xiaoling, Liu Ming, Yuan Xin et al. Atrial fibrillation detection based on multi-feature fusion and convolution neural network [J]. Laser Journal, 2017, 38(05): 176-179. DOI: 10.14016/j.cnki.jgzz.2017.05.176.
[10] Ma Zhiyi, Yang Xiaodong, He Aidong et al. Complex network recognition of ECG signals in healthy and myocardial infarction patients based on multi view [J]. Acta Phys. Sin., 2022, 71(05): 48-57.
[11] Liu W, Wang F, Huang Q Et Al. MFB-CBRNN: A hybrid network for MI detection using 12-leadECGs [J]. IEEE journal of biomedical and health informatics, 2019, 24(2): 503-514
[12] Cheng Shi, Luo Xiaoning, Li Dongcheng, Yao Chenhong. A speech emotion recognition model based on BLSTM [J]. Changjiang information communication, 2022, 35(07): 19-22.
[13] Gao Jie, Yu Yali, Yu Zijie, Cao Zilong. Research on multiple exchange rate forecasting based on Bi LSTM and transfer learning [J]. Computer programming skills and maintenance, 2022(07): 39-41+45. DOI: 10.16184/j.cnki. comprg.2022.07.006.
[14] Fang Xiaofan, Xv Zeyu, Zhang Ying. Aeronautical Engine Life Prediction Based on Bi- LSTM [J]. Agricultural equipment & vehicle engineering, 2022, 60(07): 130-133.

Subscription
E-Mail Alert
Most popular papers
Call for Special Issue
Publication Ethics & OA Statement
Plagiarism Policy
Contact Us
Downloads: 19343
Visits: 294514

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.