Deep Contrastive Learning-Based Model for ECG Biometrics
Source abstract
Abstract
The electrocardiogram (ECG) signal is shown to be promising as a biometric. To this end, it has been demonstrated that the analysis of ECG signals can be considered as a good solution for increasing the biometric security levels. This can be mainly due to its inherent robustness against presentation attacks. In this work, we present a deep contrastive learning-based system for ECG biometric identification. The proposed system consists of three blocks: a feature extraction backbone based on short time Fourier transform (STFT), a contrastive learning network, and a classification network. We evaluated the proposed system on the Heartprint dataset, a new ECG biometrics multi-session dataset. The experimental analysis shows promising capabilities of the proposed method. In particular, it yields an average top1 accuracy of 98.02% on a new dataset built by gathering 1539 ECG records from 199 subjects collected in multiple sessions with an average interval between sessions of 47 days.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: ECG Monitoring and Analysis · EEG and Brain-Computer Interfaces · Advanced Computing and Algorithms
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Computer Engineering Department, College of Computer and Information Sciences, King Saud University, Riyadh 11543, Saudi Arabia
Computer Science Department, College of Computer and Information Sciences, King Saud University, Riyadh 11543, Saudi Arabia
Funding
National Science, Technology and Innovation Plan, King Abdulaziz City for Science and Technology, Saudi Arabia
References (36)
Show source-provided references
1. ECG Biometric Recognition: A Comparative Analysis10.1109/TIFS.2012.2215324 ↗
2. Jomaa, R.M., Mathkour, H., Bazi, Y., and Islam, M.S. (2020). End-to-End Deep Learning Fusion of Fingerprint and Electrocardiogram Signals for Presentation Attack Detection. Sensors, 20.10.3390/s20072085 ↗
3. Kim, B.-H., and Pyun, J.-Y. (2020). ECG Identification for Personal Authentication Using LSTM-Based Deep Recurrent Neural Networks. Sensors, 20.10.3390/s20113069 ↗
4. EDITH: ECG Biometrics Aided by Deep Learning for Reliable Individual AuTHentication10.1109/TETCI.2021.3131374 ↗
5. Liveness Detection and Automatic Template Updating Using Fusion of ECG and Fingerprint10.1109/TIFS.2018.2804890 ↗
6. ECG Analysis: A New Approach in Human Identification10.1109/19.930458 ↗
7. A Comprehensive Survey on ECG Signals as New Biometric Modality for Human Authentication: Recent Advances and Future Challenges10.1109/ACCESS.2021.3095248 ↗
8. Opportunities and Challenges of Deep Learning Methods for Electrocardiogram Data: A Systematic Review10.1016/j.compbiomed.2020.103801 ↗
9. and M. Review of Fiducial and Non-Fiducial Techniques of Feature Extraction in ECG Based Biometric Systems10.17485/ijst/2016/v9i21/94841 ↗
10. Belo, D., Bento, N., Silva, H., Fred, A., and Gamboa, H. (2020). ECG Biometrics Using Deep Learning and Relative Score Threshold Classification. Sensors, 20.10.3390/s20154078 ↗
11. Jomaa, R.M., Islam, M.S., and Mathkour, H. (2015, January 19–21). Enhancing the Information Content of Fingerprint Biometrics with Heartbeat Signal. Proceedings of the 2015 World Symposium on Computer Networks and Information Security (WSCNIS), Hammamet, Tunisia.10.1109/WSCNIS.2015.7368284 ↗
12. A Multilayer System to Boost the Robustness of Fingerprint Authentication against Presentation Attacks by Fusion with Heart-Signal
13. Multimodal Biometric System for ECG, Ear and Iris Recognition Based on Local Descriptors10.1007/s11042-019-7467-x ↗
14. Israel, S.A., Scruggs, W.T., Worek, W.J., and Irvine, J.M. (2003, January 15–17). Fusing Face and ECG for Personal Identification. Proceedings of the 32nd Applied Imagery Pattern Recognition Workshop, Washington, DC, USA.
15. Multimodal Biometric System Combining ECG and Sound Signals10.1016/j.patrec.2013.11.014 ↗
16. Deep-ECG: Convolutional Neural Networks for ECG Biometric Recognition10.1016/j.patrec.2018.03.028 ↗
17. ECG Authentication Method Based on Parallel Multi-Scale One-Dimensional Residual Network with Center and Margin Loss10.1109/ACCESS.2019.2912519 ↗
18. HeartID: A Multiresolution Convolutional Neural Network for ECG-Based Biometric Human Identification in Smart Health Applications10.1109/ACCESS.2017.2707460 ↗
19. Ihsanto, E., Ramli, K., Sudiana, D., and Gunawan, T.S. (2020). Fast and Accurate Algorithm for ECG Authentication Using Residual Depthwise Separable Convolutional Neural Networks. Appl. Sci., 10.10.3390/app10093304 ↗
20. Salloum, R., and Kuo, C.-C.J. (2017, January 5–9). ECG-Based Biometrics Using Recurrent Neural Networks. Proceedings of the 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), New Orleans, LA, USA.10.1109/ICASSP.2017.7952519 ↗
21. An LSTM-Based Model for Person Identification Using ECG Signal10.1109/LSENS.2020.3012653 ↗
22. A Deep Bidirectional GRU Network Model for Biometric Electrocardiogram Classification Based on Recurrent Neural Networks10.1109/ACCESS.2019.2939947 ↗
23. Quantitative Investigation of QRS Detection Rules Using the MIT/BIH Arrhythmia Database10.1109/TBME.1986.325695 ↗
24. Hamilton, P. (2002, January 22–25). Open Source ECG Analysis. Proceedings of the Computers in Cardiology, Memphis, TN, USA.
25. Tirado-Martin, P., and Sanchez-Reillo, R. (2021). BioECG: Improving ECG Biometrics with Deep Learning and Enhanced Datasets. Appl. Sci., 11.10.3390/app11135880 ↗
26. An ECG-Based Authentication System Using Siamese Neural Networks10.1007/s40846-021-00637-9 ↗
27. Evolution, Current Challenges, and Future Possibilities in ECG Biometrics10.1109/ACCESS.2018.2849870 ↗
28. Islam, M.S., Alhichri, H., Bazi, Y., Ammour, N., Alajlan, N., and Jomaa, R.M. (2022). Heartprint: A Dataset of Multisession ECG Signal with Long Interval Captured from Fingers for Biometric Recognition. Data, 7.10.3390/data7100141 ↗
29. Islam, M.S., and Alajlan, N. (2013, January 15–19). An Efficient QRS Detection Method for ECG Signal Captured from Fingers. Proceedings of the 2013 IEEE International Conference on Multimedia and Expo Workshops (ICMEW), San Jose, CA, USA.10.1109/ICMEW.2013.6618388 ↗
30. Islam, M.S., and Alajlan, N. (2014, January 8–10). Augmented-Hilbert Transform for Detecting Peaks of a Finger-ECG Signal. Proceedings of the 2014 IEEE Conference on Biomedical Engineering and Sciences (IECBES), Kuala Lumpur, Malaysia.10.1109/IECBES.2014.7047634 ↗
31. AlDuwaile, D.A., and Islam, M.S. (2021). Using Convolutional Neural Network and a Single Heartbeat for ECG Biometric Recognition. Entropy, 23.10.3390/e23060733 ↗
32. Alduwaile, D., and Islam, M.S. (2020, January 23–24). Single Heartbeat ECG Biometric Recognition Using Convolutional Neural Network. Proceedings of the 2020 International Conference on Advanced Science and Engineering (ICOASE), Duhok, Iraq.10.1109/ICOASE51841.2020.9436592 ↗
33. Dense Convolutional Networks with Focal Loss and Image Generation for Electrocardiogram Classification10.1109/ACCESS.2019.2960116 ↗
34. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
35. A Simple Framework for Contrastive Learning of Visual Representations 2020
36. Hadsell, R., Chopra, S., and LeCun, Y. (2006, January 17–22). Dimensionality Reduction by Learning an Invariant Mapping. Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’06), New York, NY, USA.