Electrocardiogram signal classification algorithm of nested long short-term memory network based on focal loss function_Journal of Biomedical Engineering

Authors：

XU Shiyu ¹ ,  MO Site ¹ , YAN Huijun ¹ , HUANG Hua ¹ , WU Jinhui ² , ZHANG Shaomin ² , YANG Lin ¹

1. School of Electrical Engineering, Sichuan University, Chengdu 610065, P. R. China;
2. Department of Geriatrics, West China Hospital of Sichuan University, Chengdu 610041, P. R. China;

Corresponding author：

MO Site, Email: scumosite@163.com

Keywords：

Arrhythmia; Nested long short-term memory network; Focal loss; Residual attention; Synthetic minority over-sampling technique

DOI：

10.7507/1001-5515.202110002

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Electrocardiogram (ECG) can visually reflect the physiological electrical activity of human heart, which is important in the field of arrhythmia detection and classification. To address the negative effect of label imbalance in ECG data on arrhythmia classification, this paper proposes a nested long short-term memory network (NLSTM) model for unbalanced ECG signal classification. The NLSTM is built to learn and memorize the temporal characteristics in complex signals, and the focal loss function is used to reduce the weights of easily identifiable samples. Then the residual attention mechanism is used to modify the assigned weights according to the importance of sample characteristic to solve the sample imbalance problem. Then the synthetic minority over-sampling technique is used to perform a simple manual oversampling process on the Massachusetts institute of technology and Beth Israel hospital arrhythmia (MIT-BIH-AR) database to further increase the classification accuracy of the model. Finally, the MIT-BIH arrhythmia database is applied to experimentally verify the above algorithms. The experimental results show that the proposed method can effectively solve the issues of imbalanced samples and unremarkable features in ECG signals, and the overall accuracy of the model reaches 98.34%. It also significantly improves the recognition and classification of minority samples and has provided a new feasible method for ECG-assisted diagnosis, which has practical application significance.

Citation： XU Shiyu, MO Site, YAN Huijun, HUANG Hua, WU Jinhui, ZHANG Shaomin, YANG Lin. Electrocardiogram signal classification algorithm of nested long short-term memory network based on focal loss function. Journal of Biomedical Engineering, 2022, 39(2): 301-310. doi: 10.7507/1001-5515.202110002 Copy

1.	Sannino G, De Pietro G. A deep learning approach for ECG-based heartbeat classification for arrhythmia detection. Future Generation Computer Systems, 2018, 86: 446-455.
2.	Kumar A, Komaragiri R, Kumar M. From pacemaker to wearable: techniques for ECG detection systems. J Med Syst, 2018, 42(2): 34.
3.	Rajpurkar P, Hannun A Y, Haghpanahi M, et al. Cardiologist-level arrhythmia detection with convolutional neural networks. arXiv: Computer Vision and Pattern Recognition, 2017, arXiv: 1707.01836.
4.	Sangaiah A K, Arumugam M, Bian G B. An intelligent learning approach for improving ECG signal classification and arrhythmia analysis. Artif Intell Med, 2020, 103: 101788.
5.	Wu Q, Sun Y F, Yan H, et al. ECG signal classification with binarized convolutional neural network. Comput Biol Med, 2020, 121: 103800.
6.	Dutta S, Chatterjee A, Munshi S. Correlation technique and least square support vector machine combine for frequency domain based ECG beat classification. Med Eng Phys, 2010, 32(10): 1161-1169.
7.	Li T, Min Z. ECG classification using wavelet packet entropy and random forests. Entropy, 2016, 18(8): 285.
8.	Moody G A, Mark R G. The impact of the MIT-BIH arrhythmia database. IEEE Engineering in Medicine and Biology Magazine, 2001, 20(3): 45-50.
9.	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.
10.	行鸿彦, 黄敏松. 心电信号特征点提取的算法研究. 仪器仪表学报, 2008, 29(11): 2362-2366.
11.	陈志博, 李健, 李智, 等. 基于RR间期和多特征值的房颤自动检测分类. 生物医学工程学杂志, 2018, 35(4): 550-556.
12.	Khatibi T, Rabinezhadsadatmahaleh N. Proposing feature engineering method based on deep learning and K-NNs for ECG beat classification and arrhythmia detection. Phys Eng Sci Med, 2020, 43(1): 49-68.
13.	李端, 张洪欣, 刘知青, 等. 基于深度残差卷积神经网络的心电信号心律不齐识别. 生物医学工程学杂志, 2019, 36(2): 189-198.
14.	Mathews S M, Kambhamettu C, Barner K. A novel application of deep learning for single-lead ECG classification. Comput Biol Med, 2018, 99: 53-62.
15.	刘光达, 周葛, 董梦坤, 等. 基于FFNN和1D-CNN的实时心律失常诊断系统与算法. 电子测量与仪器学报, 2021, 35(3): 35-42.
16.	Xiao Q, Cai W J, Ge D F. ECG signal classification based on BPNN//2011 International Conference on Electric Information and Control Engineering. 2011, 2011: 1362-1364.
17.	Li H, Yuan D, Ma X, et al. Genetic algorithm for the optimization of features and neural networks in ECG signals classification. Sci Rep, 2017, 7: 41011.
18.	Moniz J R A, Krueger D. Nested LSTMs. arXiv: Computation and Language, 2018, arXiv: 1801.10308.
19.	Lin T Y, Goyal P, Girshick R, et al. Focal loss for dense object detection. IEEE Trans Pattern Anal Mach Intell, 2020, 42(2): 318-327.
20.	Chawla N V, Bowyer K W, Hall L O, et al. SMOTE: synthetic minority over-sampling technique. Journal of Artificial Intelligence Research, 2002, 16(1): 321-357.
21.	Balachandran A, Ganesan M, Sumesh E P. Daubechies algorithm for highly accurate ECG feature extraction//2014 International Conference on Green Computing Communication and Electrical Engineering (ICGCCEE), IEEE, 2014: 1-5.
22.	Acharya U R, Suri J S, Spaan J, et al. Wavelets and its application in cardiology. Springer Berlin Heidelberg, 2007, 2007(Chapter 18): 407-422.
23.	Rai H M, Trivedi A, Shukla S, et al. ECG arrhythmia classification using daubechies wavelet and radial basis function neural network//2012 Nirma University International Conference on Engineering (NUiCONE), IEEE, 2012: 1-6.
24.	Pan J, Tompkins W J. A real-time QRS detection algorithm. IEEE Trans Biomed Eng, 1985(3): 230-236.
25.	Wang Yequan, Huang Minlie, Zhao Li, et al. Attention-based LSTM for aspect-level sentiment classification// Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 2016: 606-615.
26.	Laina I, Rupprecht C, Belagiannis V, et al. Deeper depth prediction with fully convolutional residual networks//2016 Fourth International Conference on 3D Vision (3DV), IEEE, 2016: 239-248.
27.	Srivastava N, Hinton G, Krizhevsky A, et al. Dropout: a simple way to prevent neural networks from overfitting. Journal of Machine Learning Research, 2014, 15(1): 1929-1958.
28.	Acharya U R, Oh S L, Hagiwara Y, et al. A deep convolutional neural network model to classify heartbeats. Comput Biol Med, 2017, 89: 389-396.

1. Sannino G, De Pietro G. A deep learning approach for ECG-based heartbeat classification for arrhythmia detection. Future Generation Computer Systems, 2018, 86: 446-455.
2. Kumar A, Komaragiri R, Kumar M. From pacemaker to wearable: techniques for ECG detection systems. J Med Syst, 2018, 42(2): 34.
3. Rajpurkar P, Hannun A Y, Haghpanahi M, et al. Cardiologist-level arrhythmia detection with convolutional neural networks. arXiv: Computer Vision and Pattern Recognition, 2017, arXiv: 1707.01836.
4. Sangaiah A K, Arumugam M, Bian G B. An intelligent learning approach for improving ECG signal classification and arrhythmia analysis. Artif Intell Med, 2020, 103: 101788.
5. Wu Q, Sun Y F, Yan H, et al. ECG signal classification with binarized convolutional neural network. Comput Biol Med, 2020, 121: 103800.
6. Dutta S, Chatterjee A, Munshi S. Correlation technique and least square support vector machine combine for frequency domain based ECG beat classification. Med Eng Phys, 2010, 32(10): 1161-1169.
7. Li T, Min Z. ECG classification using wavelet packet entropy and random forests. Entropy, 2016, 18(8): 285.
8. Moody G A, Mark R G. The impact of the MIT-BIH arrhythmia database. IEEE Engineering in Medicine and Biology Magazine, 2001, 20(3): 45-50.
9. 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.
10. 行鸿彦, 黄敏松. 心电信号特征点提取的算法研究. 仪器仪表学报, 2008, 29(11): 2362-2366.
11. 陈志博, 李健, 李智, 等. 基于RR间期和多特征值的房颤自动检测分类. 生物医学工程学杂志, 2018, 35(4): 550-556.
12. Khatibi T, Rabinezhadsadatmahaleh N. Proposing feature engineering method based on deep learning and K-NNs for ECG beat classification and arrhythmia detection. Phys Eng Sci Med, 2020, 43(1): 49-68.
13. 李端, 张洪欣, 刘知青, 等. 基于深度残差卷积神经网络的心电信号心律不齐识别. 生物医学工程学杂志, 2019, 36(2): 189-198.
14. Mathews S M, Kambhamettu C, Barner K. A novel application of deep learning for single-lead ECG classification. Comput Biol Med, 2018, 99: 53-62.
15. 刘光达, 周葛, 董梦坤, 等. 基于FFNN和1D-CNN的实时心律失常诊断系统与算法. 电子测量与仪器学报, 2021, 35(3): 35-42.
16. Xiao Q, Cai W J, Ge D F. ECG signal classification based on BPNN//2011 International Conference on Electric Information and Control Engineering. 2011, 2011: 1362-1364.
17. Li H, Yuan D, Ma X, et al. Genetic algorithm for the optimization of features and neural networks in ECG signals classification. Sci Rep, 2017, 7: 41011.
18. Moniz J R A, Krueger D. Nested LSTMs. arXiv: Computation and Language, 2018, arXiv: 1801.10308.
19. Lin T Y, Goyal P, Girshick R, et al. Focal loss for dense object detection. IEEE Trans Pattern Anal Mach Intell, 2020, 42(2): 318-327.
20. Chawla N V, Bowyer K W, Hall L O, et al. SMOTE: synthetic minority over-sampling technique. Journal of Artificial Intelligence Research, 2002, 16(1): 321-357.
21. Balachandran A, Ganesan M, Sumesh E P. Daubechies algorithm for highly accurate ECG feature extraction//2014 International Conference on Green Computing Communication and Electrical Engineering (ICGCCEE), IEEE, 2014: 1-5.
22. Acharya U R, Suri J S, Spaan J, et al. Wavelets and its application in cardiology. Springer Berlin Heidelberg, 2007, 2007(Chapter 18): 407-422.
23. Rai H M, Trivedi A, Shukla S, et al. ECG arrhythmia classification using daubechies wavelet and radial basis function neural network//2012 Nirma University International Conference on Engineering (NUiCONE), IEEE, 2012: 1-6.
24. Pan J, Tompkins W J. A real-time QRS detection algorithm. IEEE Trans Biomed Eng, 1985(3): 230-236.
25. Wang Yequan, Huang Minlie, Zhao Li, et al. Attention-based LSTM for aspect-level sentiment classification// Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 2016: 606-615.
26. Laina I, Rupprecht C, Belagiannis V, et al. Deeper depth prediction with fully convolutional residual networks//2016 Fourth International Conference on 3D Vision (3DV), IEEE, 2016: 239-248.
27. Srivastava N, Hinton G, Krizhevsky A, et al. Dropout: a simple way to prevent neural networks from overfitting. Journal of Machine Learning Research, 2014, 15(1): 1929-1958.
28. Acharya U R, Oh S L, Hagiwara Y, et al. A deep convolutional neural network model to classify heartbeats. Comput Biol Med, 2017, 89: 389-396.

Journal of Biomedical Engineering

Electrocardiogram signal classification algorithm of nested long short-term memory network based on focal loss function

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content