ECG Heartbeat Classification Detection Based on WaveNet-LSTM

被引:0
作者
Qu, Yuanyuan [1 ]
Zhang, Nina [2 ]
Meng, Yue [1 ]
Qin, Zhiliang [1 ]
Lu, Qidong [1 ]
Liu, Xiaowei [1 ]
机构
[1] Weihai Beiyang Elect Grp Co Ltd, Weihai, Shandong, Peoples R China
[2] Weihai Beiyang Opt Elect Info Tech Co Ltd, Weihai, Shandong, Peoples R China
来源
2020 IEEE THE 4TH INTERNATIONAL CONFERENCE ON FRONTIERS OF SENSORS TECHNOLOGIES (ICFST 2020) | 2020年
关键词
ECG analysis; heartbeat classification; deep learning; WaveNet model; confusion matrix; NEURAL-NETWORK; MODEL;
D O I
10.1109/icfst51577.2020.9294765
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Electrocardiogram (ECG) can effectively record the potential difference of the body surface generated during the physiological function of the heart, and analyze and accurately discriminate the potential difference signal generated by the electrocardiogram, which can effectively prevent sudden diseases and reduce suddenness. ECG heartbeat is a powerful tool to diagnose several abnormal arrhythmias. Although the classification methods of arrhythmia improved significantly, but when detecting different types of cardiac abnormalities, especially when dealing with unbalanced data sets, it still does not provide acceptable performance. In this paper, we propose a method of data processing combined with the deep WaveNet-LSTM convolution model to solve this limitation of the current classification method. Furthermore, to prove the effectiveness of proposed method, using the MIT-Bill arrhythmia database, which considers intra- and inter-patient paradigms, and the AAMI EC57 standard. The evaluation results show that our method has achieved very good performance, and its accuracy of ECG abnormal signal detection reaches 96.8%.
引用
收藏
页码:54 / 58
页数:5
相关论文
共 50 条
[21]   ECG heartbeat classification in compressive domain for wearable devices [J].
Hua, Jing ;
Xu, Yilu ;
Tang, Jianjun ;
Liu, Jizhong ;
Zhang, Jihao .
JOURNAL OF SYSTEMS ARCHITECTURE, 2020, 104
[22]   ECG-based heartbeat classification using exponential-political optimizer trained deep learning for arrhythmia detection [J].
Choudhury, Avishek ;
Vuppu, Shankar ;
Singh, Suryabhan Pratap ;
Kumar, Manoj ;
Kumar, Sanjay Nakharu Prasad .
BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2023, 84
[23]   Explainable AI-based ECG Heartbeat Classification Using Deep Learning Models [J].
Moningi, Rohit ;
Mahakur, Shreya ;
Mundada, Shradha ;
Tripathy, Asis Kumar .
2024 4TH INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND SIGNAL PROCESSING, AISP, 2024,
[24]   Inter-patient ECG arrhythmia heartbeat classification based on unsupervised domain adaptation [J].
Wang, Guijin ;
Chen, Ming ;
Ding, Zijian ;
Li, Jiawei ;
Yang, Huazhong ;
Zhang, Ping .
NEUROCOMPUTING, 2021, 454 :339-349
[25]   A granular resampling method based energy-efficient architecture for heartbeat classification in ECG [J].
Xu, Yin ;
Chen, Zhijian ;
Xiang, Xiaoyan ;
Meng, Jianyi .
IEICE ELECTRONICS EXPRESS, 2017, 14 (22)
[26]   Fusing Transformer Model with Temporal Features for ECG Heartbeat Classification [J].
Yan, Genshen ;
Liang, Shen ;
Zhang, Yanchun ;
Liu, Fan .
2019 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE (BIBM), 2019, :898-905
[27]   Heartbeat Classification of ECG Signals Using Rational Function Systems [J].
Bognar, Gergo ;
Fridli, Sandor .
COMPUTER AIDED SYSTEMS THEORY - EUROCAST 2017, PT II, 2018, 10672 :187-195
[28]   Heartbeat classification using projected and dynamic features of ECG signal [J].
Chen, Shanshan ;
Hua, Wei ;
Li, Zhi ;
Li, Jian ;
Gao, Xingjiao .
BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2017, 31 :165-173
[29]   Enhancing dynamic ECG heartbeat classification with lightweight transformer model [J].
Meng, Lingxiao ;
Tan, Wenjun ;
Ma, Jiangang ;
Wang, Ruofei ;
Yin, Xiaoxia ;
Zhang, Yanchun .
ARTIFICIAL INTELLIGENCE IN MEDICINE, 2022, 124
[30]   Heartbeat Classification Using Morphological and Dynamic Features of ECG Signals [J].
Ye, Can ;
Kumar, B. V. K. Vijaya ;
Coimbra, Miguel Tavares .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2012, 59 (10) :2930-2941