Semi-Supervised Domain Adaptation for Individual Identification from Electrocardiogram Signals
Abstract
:1. Introduction
2. Methods
2.1. Signal to Image via Continuous Wavelet Transform
2.2. CycleGAN (Cycle Generative Adversarial Network)
2.3. Convolutional Neural Network for Image Classification
3. Proposed Domain Adaptation Method for Individual Identification Using ECG Signals
3.1. First Module for Individual Identification Using ECG
3.2. Second Module for Individual Identification Using ECG
3.3. Third Module for Individual Identification Using ECG
4. Experiments and Results
4.1. ECG Datasets for Individual Identification
4.2. Experiments and Results
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Gahi, Y.; Lamrani, M.; Zoglat, A.; Guennoun, M.; Kapralos, B.; El-Khatib, K. Biometric Identification System Based on Electrocardiogram Data. In Proceedings of the New Technologies, Mobility and Security, Tangier, Morocco, 5–7 November 2008; pp. 1–4. [Google Scholar]
- Nguyen, B.P.; Tay, W.L.; Chui, C.K. Robust biometric recognition from palm depth images for gloved hands. IEEE Trans. Hum.-Mach. Syst. 2015, 45, 799–804. [Google Scholar] [CrossRef]
- Zhang, Y.; Juhola, M. On biometrics with eye movements. IEEE J. Biomed. Health Inform. 2017, 21, 1360–1366. [Google Scholar] [CrossRef]
- Pokhriyal, N.; Tayal, K.; Nwogu, I.; Govindaraju, V. Cognitive-biometric recognition from language usage: A feasibility study. IEEE Trans. Inf. Forensics Secur. 2017, 12, 134–143. [Google Scholar] [CrossRef]
- Wang, H.; Hu, J.; Deng, W. Compressing fisher vector for robust face recognition. IEEE Access 2017, 5, 23157–23165. [Google Scholar] [CrossRef]
- Mobarakeh, A.K.; Carrillo, J.A.C.; Aguilar, J.J.C. Robust face recognition based on a new supervised kernel subspace learning method. Symmetry 2019, 19, 1643. [Google Scholar] [CrossRef]
- Jain, A.K.; Arora, S.S.; Cao, K.; Best-Rowden, L.; Bhatnagar, A. Fingerprint recognition of young children. IEEE Trans. Inf. Forensics Secur. 2017, 12, 1505–1514. [Google Scholar] [CrossRef]
- Boles, W.W. A Security System Based on Human Iris Identification Using Wavelet Transform. In Proceedings of the First International Conference on Conventional and Knowledge Based Intelligent Electronics Systems, Adelaide, Australia, 21–23 May 1997; pp. 533–541. [Google Scholar]
- Yin, W.; Yang, X.; Li, L.; Zhang, L.; Kitsuwan, N.; Shinkuma, R.; Oki, E. Self-adjustable domain adaptation in personalized ECG monitoring integrated with ir-uwb radar. Biomed. Signal Process. Control 2018, 47, 75–87. [Google Scholar] [CrossRef]
- Lee, E.; Ho, A.; Wang, Y.-T.; Huang, C.-H.; Lee, C.-Y. Cross-Domain Adaptation for Biometric Identification Using Photoplethysmogram. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Barcelona, Spain, 4–8 May 2020; pp. 1289–1293. [Google Scholar]
- Patwary, A.B.; Chowdhury, M.T.I.; Mamun, N. Comparison among ECG filtering methods for non-linear noise. In Proceedings of the International Conference on Advancement in Electrical and Electronic Engineering, Gazipur, Bangladesh, 22–24 November 2018; p. 141. [Google Scholar]
- Satija, U.; Ramkumar, B.; Manikandan, M.S. Automated ECG noise detection and classification system for unsupervised healthcare monitoring. IEEE J. Biomed. Health Inform. 2018, 22, 722–732. [Google Scholar] [CrossRef]
- Chang, C.-H.; Wang, T.-M.; Hsu, H.L. Denoising of mixed noises in ecg with separate noise estimators based on discrete wavelet transform. In Proceedings of the IEEE International Conference on Advanced Materials for Science and Engineering, Tainan, Taiwan, 12–13 November 2016; pp. 562–564. [Google Scholar]
- Xu, X.; Cai, Q.; Wang, H.; Suo, Y.; Zhao, Y.; Tianwei, W.; Wang, G.; Lian, Y. A 12-Lead ECG Delineation Algorithm Based on a Quantized CNN-BiLSTM Auto-Encoder with 1–12 mapping. In Proceedings of the International Conference on Artificial Intelligence Circuits and Systems, Hangzhou, China, 11–13 June 2023; pp. 1–5. [Google Scholar]
- Nazi, Z.A.; Biswas, A.; Rayhan, M.A.; Abir, T.A. Classification of ECG signals by dot residual LSTM network with data augmentation for anomaly detection. In Proceedings of the International Conference on Computer and Information Technology, Dhaka, Bangladesh, 18–20 December 2019; pp. 1–5. [Google Scholar]
- Cayce, G.I.; Depoian, A.C., II; Bailey, C.P.; Guturu, P. Improved neural network arrhythmia classification through integrated data augmentation. In Proceedings of the IEEE MetroCon, Hurst, TX, USA, 3 November 2022; pp. 1–3. [Google Scholar]
- Anwar, T.; Zakir, S. Effect of image augmentation on ECG image classification using deep learning. In Proceedings of the International Conference on Aritificial Intelligence, Islamabad, Pakstan, 5–7 April 2021; pp. 182–186. [Google Scholar]
- Yang, H.; Liu, J.; Zhang, L.; Li, Y.; Zhang, H. ProEGAN-MS: A progressive growing generative adversarial networks for electrocardiogram generation. IEEE Access 2021, 9, 52089–52100. [Google Scholar] [CrossRef]
- Choi, S.; Seo, H.-C.; Cho, M.S.; Joo, S.; Nam, G.-B. Performace improvement of deep learning based multi-class ECG classification model using limited medical dataset. IEEE Access 2023, 11, 53185–53194. [Google Scholar]
- Li, J.; Wang, G.; Chen, M.; Ding, Z.; Yang, H. Mixup asymmetric tri-training for heartbeat classification under domain shift. IEEE Signal Process. Lett. 2021, 28, 718–722. [Google Scholar] [CrossRef]
- Alawad, M.; Wang, L. Learning domain shift in simulated and clinical data: Localizing the origin of ventiricular activation from 12-lead electrocardiograms. IEEE Trans. Med. Imaging 2019, 38, 1172–1184. [Google Scholar] [CrossRef]
- Rafi, T.H.; Ko, Y.W. Heartnet: Self multihead attention mechanism via convolutional network with adversarial data synthesis for ECG-based arrhythmia classification. IEEE Access 2022, 10, 100501–100512. [Google Scholar] [CrossRef]
- Bazi, Y.; Alajlan, N.; AlHichri, H.; Malek, S. Domain adaptation methods for ECG classification. In Proceedings of the International Conference on Computer Medical Applications, Sousse, Tunisia, 22 April 2013; pp. 1–4. [Google Scholar]
- Niu, L.; Chen, C.; Liu, H.; Zhou, S.; Shu, M. A deep-learning approach to ecg classification based on adversarial domain adaptation. Healthcare 2020, 8, 437. [Google Scholar] [CrossRef]
- Wang, G.; Chen, M.; Ding, Z.; Li, J.; Yang, H.; Zhang, P. Inter-patient ECG arrhythmia hearbeat classification based on unsupervised domain adaptation. Neurocomputing 2021, 454, 339–349. [Google Scholar] [CrossRef]
- Carrera, D.; Rossi, B.; Fragneto, P.; Boracchi, G. Domain adaptation for online ECG monitoring. In Proceedings of the International Conference on Data Mining, Los Angeles, CA, USA, 18 December 2017; pp. 1–6. [Google Scholar]
- Chen, M.; Wang, W.; Chen, H.; Ding, Z. Adaptive region aggregation network: Unsupervised domain adaptation with adversarial traning for ECG delineation. In Proceedings of the International Conference on Acoustics, Speech and Signal Processing, Barcelona, Spain, 4–8 May 2020; pp. 1274–1278. [Google Scholar]
- Shang, Z.; Zhao, Z.; Fang, H.; Relton, S.; Murphy, D.; Hancox, Z.; Yan, R.; Wong, D. Deep discriminative domain generalization with adversarial feature learning for classifying ECG signals. In Proceedings of the Computing in Cardiology, Brno, Czech Republic, 13–15 September 2021; pp. 1–4. [Google Scholar]
- Rafi, T.H.; Ko, Y.-W. SF-ECG: Source-free intersubject domain adaptation for electrocardiography-based arrhythmia classification. Appl. Sci. 2023, 13, 8551. [Google Scholar] [CrossRef]
- Deng, F.; Tu, S.; Xu, L. Multi-source unsupervised domain adaptation for ECG classification. In Proceedings of the International Conference on Bioinformatics and Biomedicine, Houston, TX, USA, 9–12 December 2021; pp. 854–859. [Google Scholar]
- Natarajan, A.; Angarita, G.; Gaiser, E.; Malison, R.; Ganesan, D.; Marlin, B.M. Domain adaptation methods for improving lab-to-field generalization of cocaine detection using wearable ECG. In Proceedings of the ACM International Joint Conference on Pervasive and Ubiquitous Computing, Heidelberg, Germany, 12–16 September 2016; pp. 875–885. [Google Scholar]
- He, Z. ECG heartbeat classification under dataset shift. J. Intell. Med. Healthc. 2022, 1, 79–89. [Google Scholar] [CrossRef]
- Lilly, J.M.; Olhede, S.C. On the analytic wavelet transform. IEEE Trans. Inf. Theory 2010, 56, 4135–4156. [Google Scholar] [CrossRef]
- Lilly, J.M.; Olhede, S.C. Generalized Morse wavelets as a superfamily of analytic wavelets. IEEE Trans. Signal Process. 2012, 60, 6036–6041. [Google Scholar] [CrossRef]
- Olhede, S.C.; Walden, A.T. Generalized morse wavelets. IEEE Trans. Signal Process. 2002, 50, 2661–2670. [Google Scholar] [CrossRef]
- Lilly, J.M.; Olhede, S.C. Higher-order properties of analytic wavelets. IEEE Trans. Signal Process. 2009, 57, 146–160. [Google Scholar] [CrossRef]
- Zhu, J.-Y.; Park, T.; Isola, P.; Efros, A.A. Unpaired image-to-image translation using cycle-consistent adversarial networks. In Proceedings of the International Conference on Computer Vision, Venice, Italy, 22–29 October 2017; pp. 2223–2232. [Google Scholar]
- Szegedy, C.; Liu, W.; Jia, Y.; Sermanet, P.; Reed, S.; Anguelov, D.; Erhan, D.; Vanhoucke, V.; Rabinovich, A. Going deeper with convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA, 7–12 June 2015; pp. 1–9. [Google Scholar]
- He, K.; Zhang, X.; Ren, S.; Sun, J. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27–30 June 2016; pp. 770–778. [Google Scholar]
- Simonyan, K.; Zisserman, A. Very deep convolutional neural networks for large-scale image recognition. In Proceedings of the International Conference on Learning Representations, San Diego, CA, USA, 7–9 May 2015; pp. 1–14. [Google Scholar]
- Goldberger, A.L.; Amaral, L.N.; Glass, L.; Hausdorff, J.M.; Ivanov, P.C.; Mark, R.G.; Mietus, J.E.; Moody, G.B.; Peng, C.K.; Stanley, H.E. PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. Circulation 2000, 101, e215–e220. [Google Scholar] [CrossRef]
- Wubbeler, G.; Stavridis, M.; Kreiseler, D.; Bousseljot, R.D.; Elster, C. Verification of humans using the electrocardiogram. Pattern Recognit. Lett. 2007, 28, 1172–1175. [Google Scholar] [CrossRef]
Diagnostic Categories |
---|
Myocardial infarction |
Cardiomyopathy/Heart failure |
Bundle branch block |
Dysrhythmia |
Myocardial hypertrophy |
Valvular heart disease |
Myocarditis |
Miscellaneous |
Healthy controls |
Epochs of CycleGAN | Test Accuracy |
---|---|
100 | 90.92 |
200 | 88.42 |
300 | 88.87 |
400 | 85.77 |
500 | 90.67 |
600 | 91.61 |
Method | Test Accuracy |
---|---|
ResNet-101 only with original data | 94.52 |
ResNet-101 with original and generated data | 91.61 |
Epochs of CycleGAN | Ratio Of Weighted Average (Original: Generated) | Test Accuracy |
---|---|---|
100 | 1:1 | 77.15 |
2:1 | 88.30 | |
3:1 | 94.06 | |
4:1 | 89.83 | |
200 | 1:1 | 71.24 |
2:1 | 91.20 | |
3:1 | 91.94 | |
4:1 | 94.97 | |
300 | 1:1 | 80.28 |
2:1 | 92.78 | |
3:1 | 93.22 | |
4:1 | 92.37 | |
400 | 1:1 | 79.76 |
2:1 | 88.87 | |
3:1 | 92.40 | |
4:1 | 93.08 | |
500 | 1:1 | 91.39 |
2:1 | 93.79 | |
3:1 | 95.40 | |
4:1 | 93.47 | |
600 | 1:1 | 91.92 |
2:1 | 95.27 | |
3:1 | 97.06 | |
4:1 | 94.76 |
Method | Epochs of CycleGAN | Accuracy | Precision | Recall | F1-Score |
---|---|---|---|---|---|
CycleGAN-based MobileNet-V2 [10] | 100 | 94.11 | 95.63 | 94.11 | 93.78 |
200 | 92.62 | 94.35 | 92.62 | 92.18 | |
300 | 90.06 | 93.06 | 90.06 | 89.30 | |
400 | 91.70 | 94.24 | 91.70 | 91.56 | |
500 | 93.25 | 94.96 | 93.25 | 92.69 | |
600 | 93.43 | 95.14 | 93.43 | 93.03 | |
Ours | 600 | 97.06 | 97.32 | 97.06 | 96.82 |
Method | Gender | Epochs of CycleGAN | Accuracy |
---|---|---|---|
Without generated data | Men | - | 99.33 |
Women | 97.83 | ||
With generated data | Men | 600 | 99.17 |
Women | 98.67 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Byeon, Y.-H.; Kwak, K.-C. Semi-Supervised Domain Adaptation for Individual Identification from Electrocardiogram Signals. Appl. Sci. 2023, 13, 13259. https://doi.org/10.3390/app132413259
Byeon Y-H, Kwak K-C. Semi-Supervised Domain Adaptation for Individual Identification from Electrocardiogram Signals. Applied Sciences. 2023; 13(24):13259. https://doi.org/10.3390/app132413259
Chicago/Turabian StyleByeon, Yeong-Hyeon, and Keun-Chang Kwak. 2023. "Semi-Supervised Domain Adaptation for Individual Identification from Electrocardiogram Signals" Applied Sciences 13, no. 24: 13259. https://doi.org/10.3390/app132413259