Research on arrhythmia classification algorithm based on adaptive multi-feature fusion network_Journal of Biomedical Engineering

Authors：

HUANG Mengmeng ¹ ,  JIANG Mingfeng ² , LI Yang ² , HE Xiaoyu ² , WANG Zefeng ³ , WU Yongquan ³ , KE Wei ⁴

1. School of Information Science and Engineering, Zhejiang Sci-Tech University, Hangzhou 310018, P. R. China;
2. School of Computer Science and Technology (School of Artificial Intelligence), Zhejiang Sci-Tech University, Hangzhou 310018, P. R. China;
3. Department of Cardiology, Beijing Anzhen Hospital Affiliated to Capital Medical University, Beijing 100029, P. R. China;
4. Faculty of Applied Sciences, Macao Polytechnic University, Macao SAR 999078, P. R. China;

Corresponding author：

JIANG Mingfeng, Email: m.jiang@zstu.edu.cn

Keywords：

Electrocardiogram classification; Arrhythmia; Multi-feature; Convolutional neural network; Feature fusion

DOI：

10.7507/1001-5515.202406069

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Deep learning method can be used to automatically analyze electrocardiogram (ECG) data and rapidly implement arrhythmia classification, which provides significant clinical value for the early screening of arrhythmias. How to select arrhythmia features effectively under limited abnormal sample supervision is an urgent issue to address. This paper proposed an arrhythmia classification algorithm based on an adaptive multi-feature fusion network. The algorithm extracted RR interval features from ECG signals, employed one-dimensional convolutional neural network (1D-CNN) to extract time-domain deep features, employed Mel frequency cepstral coefficients (MFCC) and two-dimensional convolutional neural network (2D-CNN) to extract frequency-domain deep features. The features were fused using adaptive weighting strategy for arrhythmia classification. The paper used the arrhythmia database jointly developed by the Massachusetts Institute of Technology and Beth Israel Hospital (MIT-BIH) and evaluated the algorithm under the inter-patient paradigm. Experimental results demonstrated that the proposed algorithm achieved an average precision of 75.2%, an average recall of 70.1% and an average F₁-score of 71.3%, demonstrating high classification accuracy and being able to provide algorithmic support for arrhythmia classification in wearable devices.

Citation： HUANG Mengmeng, JIANG Mingfeng, LI Yang, HE Xiaoyu, WANG Zefeng, WU Yongquan, KE Wei. Research on arrhythmia classification algorithm based on adaptive multi-feature fusion network. Journal of Biomedical Engineering, 2025, 42(1): 49-56. doi: 10.7507/1001-5515.202406069 Copy

1.	Islam M R, Qaraqe M, Qaraqe K, et al. Cat-net: convolution, attention, and transformer based network for single-lead ECG arrhythmia classification. Biomedical Signal Processing and Control, 2024, 93: 106211.
2.	Li X, Zhang J, Chen W, et al. Inter-patient automated arrhythmia classification: a new approach of weight capsule and sequence to sequence combination. Comput Methods Programs Biomed, 2022, 214: 106533.
3.	Hao S, Xu H, Ji H, et al. G2-ResNeXt: a novel model for ECG signal classification. IEEE Access, 2023, 11: 34808-34820.
4.	Singh A K, Krishnan S. ECG signal feature extraction trends in methods and applications. Biomed Eng Online, 2023, 22(1): 22.
5.	Jeong D U, Lim K M. Convolutional neural network for classification of eight types of arrhythmia using 2D time-frequency feature map from standard 12-lead electrocardiogram. Sci Rep, 2021, 11(1): 20396.
6.	Oliveira A T, Nobrega E G O. A novel arrhythmia classification method based on convolutional neural networks interpretation of electrocardiogram images//2019 IEEE International Conference on Industrial Technology (ICIT), Melbourne: IEEE, 2019: 841-846.
7.	Lai D, Fan X, Zhang Y, et al. Intelligent and efficient detection of life-threatening ventricular arrhythmias in short segments of surface ECG signals. IEEE Sensors Journal, 2020, 21(13): 14110-14120.
8.	Ozaltin O, Yeniay O. A novel proposed CNN–SVM architecture for ECG scalograms classification. Soft Computing, 2023, 27(8): 4639-4658.
9.	Mohonta S C, Motin M A, Kumar D K. Electrocardiogram based arrhythmia classification using wavelet transform with deep learning model. Sensing and Bio-Sensing Research, 2022, 37: 100502.
10.	Nojavanasghari B, Gopinath D, Koushik J, et al. Deep multimodal fusion for persuasiveness prediction//Proceedings of the 18th ACM International Conference on Multimodal Interaction (ICMI), Tokyo: ACM, 2016: 284-288.
11.	Ilse M, Tomczak J, Welling M. Attention-based deep multiple instance learning//Proceedings of the 35th International Conference on Machine Learning (ICML), Stockholm: PMLR, 2018: 2127-2136.
12.	Zhang F, Wang J, Li M, et al. Multi-scale and multi-channel information fusion for exercise electrocardiogram feature extraction and classification. IEEE Access, 2024, 12: 36670-36679.
13.	Hashimoto N, Fukushima D, Koga R, et al. Multi-scale domain-adversarial multiple-instance CNN for cancer subtype classification with unannotated histopathological images//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle: IEEE, 2020: 3852-3861.
14.	Wang T, Lu C, Sun Y, et al. Automatic ECG classification using continuous wavelet transform and convolutional neural network. Entropy (Basel), 2021, 23(1): 119.
15.	Liu Q, Gao C, Zhao Y, et al. ECG abnormality detection based on multi-domain combination features and LSTM//2023 4th International Conference on Computer Engineering and Application (ICCEA), Hangzhou: IEEE, 2023: 565-569.
16.	Ahmad Z, Tabassum A, Guan L, et al. ECG heartbeat classification using multimodal fusion. IEEE Access, 2021, 9: 100615-100626.
17.	Feng P, Fu J, Ge Z, et al. Unsupervised semantic-aware adaptive feature fusion network for arrhythmia detection. Information Sciences, 2022, 582: 509-528.
18.	Waswani A, Shazeer N, Parmar N, et al. Attention is all you need//Proceedings of the 31st Neural Information Processing Systems (NIPS), Long Beach: NIPS, 2017: 5998-6008.
19.	Zhou F, Sun Y, Wang Y. Inter-patient ECG arrhythmia heartbeat classification network based on multiscale convolution and FCBA. Biomedical Signal Processing and Control, 2024, 90: 105789.
20.	Yi P, Si Y, Fan W, et al. ECG biometrics based on attention enhanced domain adaptive feature fusion network. IEEE Access, 2023, 12: 1291-1307.
21.	袁成成, 刘自结, 王常青, 等. 融合残差网络与自注意力机制的心律失常分类. 生物医学工程学杂志, 2023, 40(3): 474-481.
22.	Mondéjar-Guerra V, Novo J, Rouco J, et al. Heartbeat classification fusing temporal and morphological information of ECGs via ensemble of classifiers. Biomedical Signal Processing and Control, 2019, 47: 41-48.
23.	Zhang Z, Dong J, Luo X, et al. Heartbeat classification using disease-specific feature selection. Computers in Biology and Medicine, 2014, 46: 79-89.
24.	韩闯, 阙文戈, 王治忠, 等. 基于心电图的心肌梗死智能辅助诊断方法研究综述. 生物医学工程学杂志, 2023, 40(5): 1019-1026.
25.	Sraitih M, Jabrane Y, Atlas A. An overview on intra-and inter-patient paradigm for ECG heartbeat arrhythmia classification//2021 International Conference on Digital Age & Technological Advances for Sustainable Development (ICDATA), Marrakech: IEEE, 2021: 1-7.
26.	de Chazal P, O'Dwyer M, Reilly R B. Automatic classification of heartbeats using ECG morphology and heartbeat interval features. IEEE Transactions on Biomedical Engineering, 2004, 51(7): 1196-1206.
27.	吕杭, 蒋明峰, 李杨, 等. 基于混合时频域特征的卷积神经网络心律失常分类方法的研究. 电子学报, 2023, 51(3): 701-711.
28.	Xia Y, Xu Y, Chen P, et al. Generative adversarial network with transformer generator for boosting ECG classification. Biomedical Signal Processing and Control, 2023, 80: 104276.
29.	Wang T, Lu C, Yang M, et al. A hybrid method for heartbeat classification via convolutional neural networks, multilayer perceptrons and focal loss. PeerJ Computer Sci, 2020, 6: e324.
30.	Wang T, Lu C, Ju W, et al. Imbalanced heartbeat classification using EasyEnsemble technique and global heartbeat information. Biomedical Signal Processing and Control, 2022, 71(PA): 103105.
31.	Wang H, Shi H, Lin K, et al. A high-precision arrhythmia classification method based on dual fully connected neural network. Biomedical Signal Processing and Control, 2020, 58: 101874.
32.	Liu J, Liu Y, Jin Y, et al. A novel diagnosis method combined dual-channel SE-ResNet with expert features for inter-patient heartbeat classification. Medical Engineering & Physics, 2024, 130: 104209.

1. Islam M R, Qaraqe M, Qaraqe K, et al. Cat-net: convolution, attention, and transformer based network for single-lead ECG arrhythmia classification. Biomedical Signal Processing and Control, 2024, 93: 106211.
2. Li X, Zhang J, Chen W, et al. Inter-patient automated arrhythmia classification: a new approach of weight capsule and sequence to sequence combination. Comput Methods Programs Biomed, 2022, 214: 106533.
3. Hao S, Xu H, Ji H, et al. G2-ResNeXt: a novel model for ECG signal classification. IEEE Access, 2023, 11: 34808-34820.
4. Singh A K, Krishnan S. ECG signal feature extraction trends in methods and applications. Biomed Eng Online, 2023, 22(1): 22.
5. Jeong D U, Lim K M. Convolutional neural network for classification of eight types of arrhythmia using 2D time-frequency feature map from standard 12-lead electrocardiogram. Sci Rep, 2021, 11(1): 20396.
6. Oliveira A T, Nobrega E G O. A novel arrhythmia classification method based on convolutional neural networks interpretation of electrocardiogram images//2019 IEEE International Conference on Industrial Technology (ICIT), Melbourne: IEEE, 2019: 841-846.
7. Lai D, Fan X, Zhang Y, et al. Intelligent and efficient detection of life-threatening ventricular arrhythmias in short segments of surface ECG signals. IEEE Sensors Journal, 2020, 21(13): 14110-14120.
8. Ozaltin O, Yeniay O. A novel proposed CNN–SVM architecture for ECG scalograms classification. Soft Computing, 2023, 27(8): 4639-4658.
9. Mohonta S C, Motin M A, Kumar D K. Electrocardiogram based arrhythmia classification using wavelet transform with deep learning model. Sensing and Bio-Sensing Research, 2022, 37: 100502.
10. Nojavanasghari B, Gopinath D, Koushik J, et al. Deep multimodal fusion for persuasiveness prediction//Proceedings of the 18th ACM International Conference on Multimodal Interaction (ICMI), Tokyo: ACM, 2016: 284-288.
11. Ilse M, Tomczak J, Welling M. Attention-based deep multiple instance learning//Proceedings of the 35th International Conference on Machine Learning (ICML), Stockholm: PMLR, 2018: 2127-2136.
12. Zhang F, Wang J, Li M, et al. Multi-scale and multi-channel information fusion for exercise electrocardiogram feature extraction and classification. IEEE Access, 2024, 12: 36670-36679.
13. Hashimoto N, Fukushima D, Koga R, et al. Multi-scale domain-adversarial multiple-instance CNN for cancer subtype classification with unannotated histopathological images//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle: IEEE, 2020: 3852-3861.
14. Wang T, Lu C, Sun Y, et al. Automatic ECG classification using continuous wavelet transform and convolutional neural network. Entropy (Basel), 2021, 23(1): 119.
15. Liu Q, Gao C, Zhao Y, et al. ECG abnormality detection based on multi-domain combination features and LSTM//2023 4th International Conference on Computer Engineering and Application (ICCEA), Hangzhou: IEEE, 2023: 565-569.
16. Ahmad Z, Tabassum A, Guan L, et al. ECG heartbeat classification using multimodal fusion. IEEE Access, 2021, 9: 100615-100626.
17. Feng P, Fu J, Ge Z, et al. Unsupervised semantic-aware adaptive feature fusion network for arrhythmia detection. Information Sciences, 2022, 582: 509-528.
18. Waswani A, Shazeer N, Parmar N, et al. Attention is all you need//Proceedings of the 31st Neural Information Processing Systems (NIPS), Long Beach: NIPS, 2017: 5998-6008.
19. Zhou F, Sun Y, Wang Y. Inter-patient ECG arrhythmia heartbeat classification network based on multiscale convolution and FCBA. Biomedical Signal Processing and Control, 2024, 90: 105789.
20. Yi P, Si Y, Fan W, et al. ECG biometrics based on attention enhanced domain adaptive feature fusion network. IEEE Access, 2023, 12: 1291-1307.
21. 袁成成, 刘自结, 王常青, 等. 融合残差网络与自注意力机制的心律失常分类. 生物医学工程学杂志, 2023, 40(3): 474-481.
22. Mondéjar-Guerra V, Novo J, Rouco J, et al. Heartbeat classification fusing temporal and morphological information of ECGs via ensemble of classifiers. Biomedical Signal Processing and Control, 2019, 47: 41-48.
23. Zhang Z, Dong J, Luo X, et al. Heartbeat classification using disease-specific feature selection. Computers in Biology and Medicine, 2014, 46: 79-89.
24. 韩闯, 阙文戈, 王治忠, 等. 基于心电图的心肌梗死智能辅助诊断方法研究综述. 生物医学工程学杂志, 2023, 40(5): 1019-1026.
25. Sraitih M, Jabrane Y, Atlas A. An overview on intra-and inter-patient paradigm for ECG heartbeat arrhythmia classification//2021 International Conference on Digital Age & Technological Advances for Sustainable Development (ICDATA), Marrakech: IEEE, 2021: 1-7.
26. de Chazal P, O'Dwyer M, Reilly R B. Automatic classification of heartbeats using ECG morphology and heartbeat interval features. IEEE Transactions on Biomedical Engineering, 2004, 51(7): 1196-1206.
27. 吕杭, 蒋明峰, 李杨, 等. 基于混合时频域特征的卷积神经网络心律失常分类方法的研究. 电子学报, 2023, 51(3): 701-711.
28. Xia Y, Xu Y, Chen P, et al. Generative adversarial network with transformer generator for boosting ECG classification. Biomedical Signal Processing and Control, 2023, 80: 104276.
29. Wang T, Lu C, Yang M, et al. A hybrid method for heartbeat classification via convolutional neural networks, multilayer perceptrons and focal loss. PeerJ Computer Sci, 2020, 6: e324.
30. Wang T, Lu C, Ju W, et al. Imbalanced heartbeat classification using EasyEnsemble technique and global heartbeat information. Biomedical Signal Processing and Control, 2022, 71(PA): 103105.
31. Wang H, Shi H, Lin K, et al. A high-precision arrhythmia classification method based on dual fully connected neural network. Biomedical Signal Processing and Control, 2020, 58: 101874.
32. Liu J, Liu Y, Jin Y, et al. A novel diagnosis method combined dual-channel SE-ResNet with expert features for inter-patient heartbeat classification. Medical Engineering & Physics, 2024, 130: 104209.

Previous Article
Prediction method of paroxysmal atrial fibrillation based on multimodal feature fusion
Next Article
Research on intelligent fetal heart monitoring model based on deep active learning

Journal of Biomedical Engineering

Research on arrhythmia classification algorithm based on adaptive multi-feature fusion network

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content