Arrhythmia Disease Diagnosis Based on ECG Time–Frequency Domain Fusion and Convolutional Neural Network

Electrocardiogram (ECG) signals are often used to diagnose cardiac status. However, most of the existing ECG diagnostic methods only use the time-domain information, resulting in some obviously lesion information in frequency-domain of ECG signals are not being fully utilized. Therefore, we propose...

Full description

Saved in:
Bibliographic Details
Main Authors: Bocheng Wang, Guorong Chen, Lu Rong, Yuchuan Liu, Anning Yu, Xiaohui He, Tingting Wen, Yixuan Zhang, Biaobiao Hu
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Journal of Translational Engineering in Health and Medicine
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10002348/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850271652018913280
author Bocheng Wang
Guorong Chen
Lu Rong
Yuchuan Liu
Anning Yu
Xiaohui He
Tingting Wen
Yixuan Zhang
Biaobiao Hu
author_facet Bocheng Wang
Guorong Chen
Lu Rong
Yuchuan Liu
Anning Yu
Xiaohui He
Tingting Wen
Yixuan Zhang
Biaobiao Hu
author_sort Bocheng Wang
collection DOAJ
description Electrocardiogram (ECG) signals are often used to diagnose cardiac status. However, most of the existing ECG diagnostic methods only use the time-domain information, resulting in some obviously lesion information in frequency-domain of ECG signals are not being fully utilized. Therefore, we propose a method to fuse the time and frequency domain information in ECG signals by convolutional neural network (CNN). First, we adapt multi-scale wavelet decomposition to filter the ECG signal; Then, R-wave localization is used to segment each individual heartbeat cycle; And then, the frequency domain information of this heartbeat cycle is extracted via fast Fourier transform. Finally, the temporal information is spliced with the frequency domain information and input to the neural network for classification. The experimental results show that the proposed method has the highest recognition accuracy (99.43%) of ECG singles compared with state-of-the-art methods. Clinical and Translational Impact Statement— The proposed ECG classification method provides an effective solution for ECG interrogation to quickly diagnose the presence of arrhythmia in a patient from the ECG signal. It can increase the efficiency of the interrogating physician by aiding diagnosis.
format Article
id doaj-art-77f8dba0ffa24a1688e488f1a4386f57
institution OA Journals
issn 2168-2372
language English
publishDate 2023-01-01
publisher IEEE
record_format Article
series IEEE Journal of Translational Engineering in Health and Medicine
spelling doaj-art-77f8dba0ffa24a1688e488f1a4386f572025-08-20T01:52:10ZengIEEEIEEE Journal of Translational Engineering in Health and Medicine2168-23722023-01-011111612510.1109/JTEHM.2022.323279110002348Arrhythmia Disease Diagnosis Based on ECG Time–Frequency Domain Fusion and Convolutional Neural NetworkBocheng Wang0https://orcid.org/0000-0003-3757-6452Guorong Chen1https://orcid.org/0000-0003-2553-014XLu Rong2Yuchuan Liu3https://orcid.org/0000-0003-3010-7653Anning Yu4https://orcid.org/0000-0003-2017-2355Xiaohui He5Tingting Wen6Yixuan Zhang7Biaobiao Hu8School of Intelligent Technology and Engineering, Chongqing University of Science and Technology, Chongqing, ChinaSchool of Intelligent Technology and Engineering, Chongqing University of Science and Technology, Chongqing, ChinaSchool of Intelligent Technology and Engineering, Chongqing University of Science and Technology, Chongqing, ChinaSchool of Intelligent Technology and Engineering, Chongqing University of Science and Technology, Chongqing, ChinaSchool of Intelligent Technology and Engineering, Chongqing University of Science and Technology, Chongqing, ChinaChongqing Vocational Institute of Engineering, Chongqing, ChinaSchool of Intelligent Technology and Engineering, Chongqing University of Science and Technology, Chongqing, ChinaSchool of Intelligent Technology and Engineering, Chongqing University of Science and Technology, Chongqing, ChinaSchool of Intelligent Technology and Engineering, Chongqing University of Science and Technology, Chongqing, ChinaElectrocardiogram (ECG) signals are often used to diagnose cardiac status. However, most of the existing ECG diagnostic methods only use the time-domain information, resulting in some obviously lesion information in frequency-domain of ECG signals are not being fully utilized. Therefore, we propose a method to fuse the time and frequency domain information in ECG signals by convolutional neural network (CNN). First, we adapt multi-scale wavelet decomposition to filter the ECG signal; Then, R-wave localization is used to segment each individual heartbeat cycle; And then, the frequency domain information of this heartbeat cycle is extracted via fast Fourier transform. Finally, the temporal information is spliced with the frequency domain information and input to the neural network for classification. The experimental results show that the proposed method has the highest recognition accuracy (99.43%) of ECG singles compared with state-of-the-art methods. Clinical and Translational Impact Statement— The proposed ECG classification method provides an effective solution for ECG interrogation to quickly diagnose the presence of arrhythmia in a patient from the ECG signal. It can increase the efficiency of the interrogating physician by aiding diagnosis.https://ieeexplore.ieee.org/document/10002348/Time–frequency domain fusionconvolutional neural networksECG diagnosis
spellingShingle Bocheng Wang
Guorong Chen
Lu Rong
Yuchuan Liu
Anning Yu
Xiaohui He
Tingting Wen
Yixuan Zhang
Biaobiao Hu
Arrhythmia Disease Diagnosis Based on ECG Time–Frequency Domain Fusion and Convolutional Neural Network
IEEE Journal of Translational Engineering in Health and Medicine
Time–frequency domain fusion
convolutional neural networks
ECG diagnosis
title Arrhythmia Disease Diagnosis Based on ECG Time–Frequency Domain Fusion and Convolutional Neural Network
title_full Arrhythmia Disease Diagnosis Based on ECG Time–Frequency Domain Fusion and Convolutional Neural Network
title_fullStr Arrhythmia Disease Diagnosis Based on ECG Time–Frequency Domain Fusion and Convolutional Neural Network
title_full_unstemmed Arrhythmia Disease Diagnosis Based on ECG Time–Frequency Domain Fusion and Convolutional Neural Network
title_short Arrhythmia Disease Diagnosis Based on ECG Time–Frequency Domain Fusion and Convolutional Neural Network
title_sort arrhythmia disease diagnosis based on ecg time x2013 frequency domain fusion and convolutional neural network
topic Time–frequency domain fusion
convolutional neural networks
ECG diagnosis
url https://ieeexplore.ieee.org/document/10002348/
work_keys_str_mv AT bochengwang arrhythmiadiseasediagnosisbasedonecgtimex2013frequencydomainfusionandconvolutionalneuralnetwork
AT guorongchen arrhythmiadiseasediagnosisbasedonecgtimex2013frequencydomainfusionandconvolutionalneuralnetwork
AT lurong arrhythmiadiseasediagnosisbasedonecgtimex2013frequencydomainfusionandconvolutionalneuralnetwork
AT yuchuanliu arrhythmiadiseasediagnosisbasedonecgtimex2013frequencydomainfusionandconvolutionalneuralnetwork
AT anningyu arrhythmiadiseasediagnosisbasedonecgtimex2013frequencydomainfusionandconvolutionalneuralnetwork
AT xiaohuihe arrhythmiadiseasediagnosisbasedonecgtimex2013frequencydomainfusionandconvolutionalneuralnetwork
AT tingtingwen arrhythmiadiseasediagnosisbasedonecgtimex2013frequencydomainfusionandconvolutionalneuralnetwork
AT yixuanzhang arrhythmiadiseasediagnosisbasedonecgtimex2013frequencydomainfusionandconvolutionalneuralnetwork
AT biaobiaohu arrhythmiadiseasediagnosisbasedonecgtimex2013frequencydomainfusionandconvolutionalneuralnetwork