Classification of ECG Signals Using GAN, SMOTE, and VAE Data Augmentation Methods: Synthetic vs. Real

Year 2024, , 1158 - 1168, 31.12.2024

Turgut Özseven

https://doi.org/10.17798/bitlisfen.1523524

Abstract

Classification is separating data into predefined categories by obtaining descriptive features. In the classification process, machine and deep learning algorithms assume that the class samples are evenly distributed. In particular, the dataset size used in deep learning is significant for classification success. However, obtaining balanced data distribution in real-life problems is very difficult. This negatively affects class-based accuracy. Various methods are used in the literature to overcome the unbalanced data problem. This study investigated the effects of GAN, SMOTE, and VAE methods on ECG data. For this purpose, the heartbeat signals in the MIT-BIH dataset were used. To test the performance of the methods, a performance comparison was made using real and synthetic data, and finally, the model trained with synthetic data was tested with real data. According to the results, 96.5% accuracy was obtained with the real data. The highest classification accuracy of 100.0% was obtained in VAE when using only synthetic data. In training with synthetic data and test results with real data, the highest classification success was 86.4% with SMOTE. When synthetic and real data sets are used together, the highest success rate is 98.6% with VAE. In addition, the accuracy of all classes is evenly distributed after data augmentation.

Keywords

Synthetic data, Data augmentation, GAN, SMOTE, VAE, Heartbeat classification, Deep learning

Ethical Statement

The study is complied with research and publication ethics.

References

• [1] H. Yang, J. Liu, L. Zhang, Y. Li, and H. Zhang, ‘Proegan-ms: A progressive growing generative adversarial networks for electrocardiogram generation’, IEEE Access, vol. 9, pp. 52089–52100, 2021.
• [2] Z. Zhou, X. Zhai, and C. Tin, ‘Fully automatic electrocardiogram classification system based on generative adversarial network with auxiliary classifier’, Expert Systems with Applications, vol. 174, p. 114809, 2021.
• [3] A. M. Shaker, M. Tantawi, H. A. Shedeed, and M. F. Tolba, ‘Generalization of convolutional neural networks for ECG classification using generative adversarial networks’, IEEE Access, vol. 8, pp. 35592–35605, 2020.
• [4] W. Li, Y. M. Tang, K. M. Yu, and S. To, ‘SLC-GAN: An automated myocardial infarction detection model based on generative adversarial networks and convolutional neural networks with single-lead electrocardiogram synthesis’, Information Sciences, vol. 589, pp. 738–750, 2022.
• [5] H. M. Rai, K. Chatterjee, and S. Dashkevych, ‘The prediction of cardiac abnormality and enhancement in minority class accuracy from imbalanced ECG signals using modified deep neural network models’, Computers in Biology and Medicine, vol. 150, p. 106142, 2022.
• [6] A. Salazar, L. Vergara, and G. Safont, ‘Generative Adversarial Networks and Markov Random Fields for oversampling very small training sets’, Expert Systems with Applications, vol. 163, p. 113819, 2021.
• [7] S. S. Aphale, E. John, and T. Banerjee, ‘ArrhyNet: a high accuracy arrhythmia classification convolutional neural network’, in 2021 IEEE International Midwest Symposium on Circuits and Systems (MWSCAS), IEEE, 2021, pp. 453–457.
• [8] S. K. Pandey and R. R. Janghel, ‘Automatic detection of arrhythmia from imbalanced ECG database using CNN model with SMOTE’, Australasian physical & engineering sciences in medicine, vol. 42, no. 4, pp. 1129–1139, 2019.
• [9] H. Ge, K. Sun, L. Sun, M. Zhao, and C. Wu, ‘A selective ensemble learning framework for ECG-based heartbeat classification with imbalanced data’, in 2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), IEEE, 2018, pp. 2753–2755.
• [10] C. Du, P. X. Liu, and M. Zheng, ‘Classification of imbalanced electrocardiosignal data using convolutional neural network’, Computer Methods and Programs in Biomedicine, vol. 214, p. 106483, 2022.
• [11] M. Frid-Adar, E. Klang, M. Amitai, J. Goldberger, and H. Greenspan, ‘Synthetic data augmentation using GAN for improved liver lesion classification’, in 2018 IEEE 15th international symposium on biomedical imaging (ISBI 2018), IEEE, 2018, pp. 289–293.
• [12] Z. Qin, Z. Liu, P. Zhu, and Y. Xue, ‘A GAN-based image synthesis method for skin lesion classification’, Computer Methods and Programs in Biomedicine, vol. 195, p. 105568, 2020.
• [13] T. Golany, G. Lavee, S. T. Yarden, and K. Radinsky, ‘Improving ECG classification using generative adversarial networks’, in Proceedings of the AAAI Conference on Artificial Intelligence, 2020, pp. 13280–13285.
• [14] T. D. Tran, T. T. K. Dang, and N. Q. Tran, ‘An Innovative Approach for Long ECG Synthesis with Wasserstein GAN Model’, in Computational Science and Its Applications – ICCSA 2024, O. Gervasi, B. Murgante, C. Garau, D. Taniar, A. M. A. C. Rocha, and M. N. Faginas Lago, Eds., Cham: Springer Nature Switzerland, 2024, pp. 339–351. doi: 10.1007/978-3-031-64608-9_22.
• [15] F. Zhou and J. Li, ‘ECG data enhancement method using generate adversarial networks based on Bi-LSTM and CBAM’, Physiol. Meas., vol. 45, no. 2, p. 025003, Feb. 2024, doi: 10.1088/1361-6579/ad2218.
• [16] C. Esteban, S. L. Hyland, and G. Rätsch, ‘Real-valued (medical) time series generation with recurrent conditional gans’, arXiv preprint arXiv:1706.02633, 2017.
• [17] N. Wulan, W. Wang, P. Sun, K. Wang, Y. Xia, and H. Zhang, ‘Generating electrocardiogram signals by deep learning’, Neurocomputing, vol. 404, pp. 122–136, 2020.
• [18] D. Hazra and Y.-C. Byun, ‘SynSigGAN: Generative adversarial networks for synthetic biomedical signal generation’, Biology, vol. 9, no. 12, p. 441, 2020.
• [19] E. Piacentino, A. Guarner, and C. Angulo, ‘Generating synthetic ecgs using gans for anonymizing healthcare data’, Electronics, vol. 10, no. 4, p. 389, 2021.
• [20] F. Zhu, F. Ye, Y. Fu, Q. Liu, and B. Shen, ‘Electrocardiogram generation with a bidirectional LSTM-CNN generative adversarial network’, Scientific reports, vol. 9, no. 1, pp. 1–11, 2019.
• [21] Y. Xia, Y. Xu, P. Chen, J. Zhang, and Y. Zhang, ‘Generative adversarial network with transformer generator for boosting ECG classification’, Biomedical Signal Processing and Control, vol. 80, p. 104276, 2023.
• [22] R. R. Sarra, A. M. Dinar, M. A. Mohammed, M. K. A. Ghani, and M. A. Albahar, ‘A Robust Framework for Data Generative and Heart Disease Prediction Based on Efficient Deep Learning Models’, Diagnostics, vol. 12, no. 12, p. 2899, 2022.
• [23] S. Ma, J. Cui, W. Xiao, and L. Liu, ‘Deep Learning-Based Data Augmentation and Model Fusion for Automatic Arrhythmia Identification and Classification Algorithms’, Computational Intelligence and Neuroscience, vol. 2022, 2022.
• [24] S. Huang, P. Wang, and R. Li, ‘Noise ECG generation method based on generative adversarial network’, Biomedical Signal Processing and Control, vol. 81, p. 104444, 2023.
• [25] N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, ‘SMOTE: synthetic minority over-sampling technique’, Journal of artificial intelligence research, vol. 16, pp. 321–357, 2002.
• [26] G. B. Moody and R. G. Mark, ‘The impact of the MIT-BIH Arrhythmia Database’, IEEE Engineering in Medicine and Biology Magazine, vol. 20, no. 3, pp. 45–50, May 2001, doi: 10.1109/51.932724.
• [27] Ö. Yakut, S. Solak, and E. Bolat, ‘IIR Based Digital Filter Design for Denoising the ECG Signal’, Journal Of Polytechnic, vol. 21, no. 1, 2018, doi: 10.2339/politeknik.386970.
• [28] M. A. Kızrak and B. Bolat, ‘Derin öğrenme ile kalabalık analizi üzerine detaylı bir araştırma’, Bilişim Teknolojileri Dergisi, vol. 11, no. 3, pp. 263–286, 2018.
• [29] A. Courville and Y. Bengio, ‘Generative adversarial nets’, Advanc in Neural, 2014.
• [30] Y. Xiong, L. Wang, Q. Wang, S. Liu, and B. Kou, ‘Improved convolutional neural network with feature selection for imbalanced ECG Multi-Factor classification’, Measurement, vol. 189, p. 110471, 2022.
• [31] C. Güzel Turhan and H. Bilge, ‘Scalable image generation and super resolution using generative adversarial networks’, Journal of the Faculty of Engineering and Architecture of Gazi University, vol. 35, no. 2, 2020.