graduate student from 01.01.2024 until now
Sankt-Peterburg, St. Petersburg, Russian Federation
UDK 004 Информационные технологии. Компьютерные технологии. Теория вычислительных машин и систем
UDK 62 Инженерное дело. Техника в целом. Транспорт
Electrocardiogram (ECG)-based biometrics offer a promising solution for secure and reliable authentication, leveraging the unique and intrinsic characteristics of ECG signals. Unlike external traits such as fingerprints or facial recognition, ECG signals are internal to the body, making them highly resistant to spoofing and ensuring that only live persons can be verified and authenticated. While existing research has largely focused on closed-set recognition environments, where systems operate within predefined datasets, real-world applications demand open-set recognition capabilities. Open-set recognition means that the systems must recognize the enrolled users and at the same time reject the unknown individuals, which poses the following challenges: variability of signals, limited generalization of classifiers, and lack of rich datasets. This review examines the design considerations, challenges, and solutions for implementing ECG biometrics in open-set environments. Advanced classification methodologies that include deep learning models, classification techniques, and new open-set specific models including OpenMax and EVMs are discussed. Additionally, the role of feature extraction, data augmentation, and evaluation metrics in improving system performance is analyzed. By addressing these challenges, ECG biometrics can become the basis for secure authentication in health care, IoT and financial systems. This paper aims to guide future research toward developing robust and scalable ECG-based biometric systems.
ECG Biometrics, Open-Set Recognition, Closed-Set Recognition, Authentication Systems, Signal Variability, Classification Models, Deep Learning, OpenMax, Extreme Value Machines (EVMs).
1. M. J. Ahmed et al., “CardioGuard: AI-driven ECG authentication hybrid neural network for predictive health monitoring in telehealth systems,” SLAS Technology, vol. 29, no. 5, p. 100193, Sep. 2024, doi:https://doi.org/10.1016/j.slast.2024.100193.
2. C. Lupu, V. Lupu, and V.-G. Gaitan, “Security enhancement of internet banking applications by using multimodal biometrics,” Jan. 2015, pp. 47–52. doi:https://doi.org/10.1109/sami.2015.7061904.
3. M. Abuhamad, D. Nyang, D. Mohaisen, and A. Abusnaina, “Sensor-Based Continuous Authentication of Smartphones’ Users Using Behavioral Biometrics: A Contemporary Survey,” IEEE Internet of Things Journal, vol. 8, no. 1, pp. 65–84, Sep. 2020, doi:https://doi.org/10.1109/jiot.2020.3020076.
4. W. A. Hammood, S. Mohamad Asmara, M. A. Al-Sharafi, O. A. Hammood, R. Abdullah, and A. Muttaleb Hasan, “A Review of User Authentication Model for Online Banking System based on Mobile IMEI Number,” IOP Conference Series: Materials Science and Engineering, vol. 769, no. 1, p. 012061, Feb. 2020, doi:https://doi.org/10.1088/1757-899x/769/1/012061.
5. A. Pal, A. K. Gautam, and Y. N. Singh, “Evaluation of Bioelectric Signals for Human Recognition,” Procedia Computer Science, vol. 48, pp. 746–752, Jan. 2015, doi:https://doi.org/10.1016/j.procs.2015.04.211.
6. J.-A. Lee and K.-C. Kwak, “Personal Identification Using an Ensemble Approach of 1D-LSTM and 2D-CNN with Electrocardiogram Signals,” Applied Sciences, vol. 12, no. 5, p. 2692, Mar. 2022, doi:https://doi.org/10.3390/app12052692.
7. S. Lin, W. Yang, C. Chiang, C. Lin, and C. Chen, “Individual identification based on chaotic electrocardiogram signals during muscular exercise,” IET Biometrics, vol. 3, no. 4, pp. 257–266, Dec. 2014, doi:https://doi.org/10.1049/iet-bmt.2013.0014.
8. A. Al-Jibreen, S. Al-Ahmadi, S. Islam, and A. M. Artoli, “Person identification with arrhythmic ECG signals using deep convolution neural network,” Scientific Reports, vol. 14, no. 1, Feb. 2024, doi:https://doi.org/10.1038/s41598-024-55066-w.
9. W. Zhang, J. Lin, X. Wang, M. Zhou, and D. Huang, “Open-Set Signal Recognition Based on Transformer and Wasserstein Distance,” Applied Sciences, vol. 13, no. 4, p. 2151, Feb. 2023, doi:https://doi.org/10.3390/app13042151.
10. S. C. Eastwood, D. O. Gorodnichy, V. P. Shmerko, S. N. Yanushkevich, and M. Drahansky, “Biometric-Enabled Authentication Machines: A Survey of Open-Set Real-World Applications,” IEEE Transactions on Human-Machine Systems, vol. 46, no. 2, pp. 231–242, Apr. 2016, doi:https://doi.org/10.1109/thms.2015.2412944.
11. D. Wang, G. Zhang, Y. Si, T. Liu, and W. Yang, “A Novel Heart Rate Robust Method for Short-Term Electrocardiogram Biometric Identification,” Applied Sciences, vol. 9, no. 1, p. 201, Jan. 2019, doi:https://doi.org/10.3390/app9010201.
12. Y. Yang, N. Jiang, D.-C. Zhan, and Y. Xu, “Robust Semi-Supervised Learning by Wisely Leveraging Open-Set Data.,” IEEE transactions on pattern analysis and machine intelligence, vol. 46, no. 12, pp. 8334–8347, Dec. 2024, doi:https://doi.org/10.1109/tpami.2024.3403994.
13. C. Geng and S. Chen, “Collective Decision for Open Set Recognition,” IEEE Transactions on Knowledge and Data Engineering, vol. 34, no. 1, pp. 192–204, Mar. 2020, doi:https://doi.org/10.1109/tkde.2020.2978199.
14. N. Ammour, R. M. Jomaa, N. Alajlan, M. S. Islam, H. Alhichri, and Y. Bazi, “Deep Contrastive Learning-Based Model for ECG Biometrics,” Applied Sciences, vol. 13, no. 5, p. 3070, Feb. 2023, doi:https://doi.org/10.3390/app13053070.
15. J. Ribeiro Pinto, A. Lourenco, and J. S. Cardoso, “Evolution, Current Challenges, and Future Possibilities in ECG Biometrics,” IEEE Access, vol. 6, pp. 34746–34776, Jan. 2018, doi:https://doi.org/10.1109/access.2018.2849870.
16. M. Abo-Zahhad, S. N. Abbas, and S. M. Ahmed, “Biometric authentication based on PCG and ECG signals: present status and future directions,” Signal, Image and Video Processing, vol. 8, no. 4, pp. 739–751, Dec. 2013, doi:https://doi.org/10.1007/s11760-013-0593-4.
17. S. Shand and R. Rahul, “Importance of Human Gait Analysis in Biometric Recognition using Machine Learning: A Review,” Apr. 2022, pp. 1431–1436. doi:https://doi.org/10.1109/icoei53556.2022.9776760.
18. N. Tasneem, K. Namuduri, G. Mehta, A. Cedars, D. Kota, and I. Mahbub, “A Dry Electrode-Based ECG Sensor with Motion Artifacts Cancellation and Signal Analysis for Heart Irregularity Detection,” Oct. 2020, pp. 1–4. doi:https://doi.org/10.1109/sensors47125.2020.9278739.
19. P. Dilaveris, C.-K. Antoniou, K. Gatzoulis, and D. Tousoulis, “T wave axis deviation and QRS-T angle – Controversial indicators of incident coronary heart events,” Journal of Electrocardiology, vol. 50, no. 4, pp. 466–475, Feb. 2017, doi:https://doi.org/10.1016/j.jelectrocard.2017.02.008.
20. M. Sepahvand and F. Abdali-Mohammadi, “A novel multi-lead ECG personal recognition based on signals functional and structural dependencies using time-frequency representation and evolutionary morphological CNN,” Biomedical Signal Processing and Control, vol. 68, p. 102766, May 2021, doi:https://doi.org/10.1016/j.bspc.2021.102766.
21. S.-C. Wu, P.-L. Hung, and A. L. Swindlehurst, “ECG Biometric Recognition: Unlinkability, Irreversibility, and Security,” IEEE Internet of Things Journal, vol. 8, no. 1, pp. 487–500, Jun. 2020, doi:https://doi.org/10.1109/jiot.2020.3004362.
22. A. Eduardo, H. Aidos, and A. Fred, “ECG-based Biometrics using a Deep Autoencoder for Feature Learning - An Empirical Study on Transferability,” Jan. 2017, pp. 463–470. doi:https://doi.org/10.5220/0006195404630470.
23. A. R. Yuniarti, S. Rizal, and F. A. Manurung, “Application of Neural Network for ECG-based Biometrics System Using QRS Features,” Journal of Computer Engineering, Electronics and Information Technology, vol. 1, no. 2, pp. 91–102, Oct. 2022, doi:https://doi.org/10.17509/coelite.v1i2.43823.
24. C. Geng, S.-J. Huang, and S. Chen, “Recent Advances in Open Set Recognition: A Survey.,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 43, no. 10, pp. 3614–3631, Mar. 2020, doi:https://doi.org/10.1109/tpami.2020.2981604.
25. S. Mukherjee, “t-SNE based feature extraction technique for multi-layer perceptron neural network classifier,” Jul. 2017, vol. 15, pp. 660–664. doi:https://doi.org/10.1109/icicict1.2017.8342641.
26. S. Chen, S.-J. Huang, and C. Geng, “Recent Advances in Open Set Recognition: A Survey.” Nov. 21, 2018. doi:https://doi.org/10.48550/arxiv.1811.08581.
27. U. Panizza, “Financial Development and Economic Growth: Known Knowns, Known Unknowns, and Unknown Unknowns,” Revue d’économie du développement, vol. Vol. 22, no. HS02, pp. 35–65, Nov. 2014, doi:https://doi.org/10.3917/edd.hs02.0035.
28. R. Yoshihashi, T. Naemura, S. You, W. Shao, M. Iida, and R. Kawakami, “Classification-Reconstruction Learning for Open-Set Recognition,” Jun. 2019, pp. 4011–4020. doi:https://doi.org/10.1109/cvpr.2019.00414.
29. F. Elahee, K. A. Kalpoma, F. Mim, S. Tabassom, F. B. Naquib, and T. Hossain, “Comparative Study of Deep Learning based Finger Vein Biometric Authentication Systems,” Nov. 2020, vol. 11, pp. 444–448. doi:https://doi.org/10.1109/icaict51780.2020.9333515.
30. Y. Huang, G. Yang, K. Wang, and Y. Yin, “Multi-view discriminant analysis with sample diversity for ECG biometric recognition,” Pattern Recognition Letters, vol. 145, pp. 110–117, Feb. 2021, doi:https://doi.org/10.1016/j.patrec.2021.01.027.
31. S. Dargan, M. Kumar, A. Garg, and K. Thakur, “Writer identification system for pre-segmented offline handwritten Devanagari characters using k-NN and SVM,” Soft Computing, vol. 24, no. 13, pp. 10111–10122, Nov. 2019, doi:https://doi.org/10.1007/s00500-019-04525-y.
32. R. Faleh and A. Kachouri, “A hybrid deep convolutional neural network-based electronic nose for pollution detection purposes,” Chemometrics and Intelligent Laboratory Systems, vol. 237, p. 104825, Apr. 2023, doi:https://doi.org/10.1016/j.chemolab.2023.104825.
33. J. Lu, Z. Cheng, Y. Niu, H. Li, and Y. Xu, “PMAL: Open Set Recognition via Robust Prototype Mining,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, no. 2, pp. 1872–1880, Jun. 2022, doi:https://doi.org/10.1609/aaai.v36i2.20081.
34. G. Chen et al., “Learning Open Set Network with Discriminative Reciprocal Points,” springer, 2020, pp. 507–522. doi:https://doi.org/10.1007/978-3-030-58580-8_30.
35. D.-W. Zhou, D.-C. Zhan, and H.-J. Ye, “Learning Placeholders for Open-Set Recognition,” Jun. 2021, pp. 4399–4408. doi:https://doi.org/10.1109/cvpr46437.2021.00438.
36. R. D. Labati, R. Sassi, and F. Scotti, “ECG biometric recognition: Permanence analysis of QRS signals for 24 hours continuous authentication,” Nov. 2013, vol. 7667, pp. 31–36. doi:https://doi.org/10.1109/wifs.2013.6707790.
37. D. Belo, N. Bento, H. Gamboa, A. Fred, and H. Silva, “ECG Biometrics Using Deep Learning and Relative Score Threshold Classification.,” Sensors, vol. 20, no. 15, p. 4078, Jul. 2020, doi:https://doi.org/10.3390/s20154078.
38. L. Cernuzzi and J. Pane, “Toward Open Government in Paraguay,” IT Professional, vol. 16, no. 5, pp. 62–64, Sep. 2014, doi:https://doi.org/10.1109/mitp.2014.71.
39. N. D. Binh, “Online multiple tasks one-shot learning of object categories and vision,” Dec. 2011, pp. 131–138. doi:https://doi.org/10.1145/2095697.2095722.
40. L. Fei-Fei, P. Perona, and R. Fergus, “One-shot learning of object categories,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28, no. 4, pp. 594–611, Apr. 2006, doi:https://doi.org/10.1109/tpami.2006.79.
41. A. Bendale and T. E. Boult, “Towards Open Set Deep Networks,” Jun. 2016. doi:https://doi.org/10.1109/cvpr.2016.173.
42. A. Rozsa, T. Boult, and M. Gunther, “Adversarial Robustness: Softmax versus Openmax,” Jan. 2017. doi:https://doi.org/10.5244/c.31.156.
43. G. Chen, Y. Tian, X. Wang, and P. Peng, “Adversarial Reciprocal Points Learning for Open Set Recognition.,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 11, p. 1, Jan. 2021, doi:https://doi.org/10.1109/tpami.2021.3106743.
44. Y. Liu, X. Gao, J. Han, L. Liu, and L. Shao, “Zero-shot learning via a specific rank-controlled semantic autoencoder,” Pattern Recognition, vol. 122, p. 108237, Aug. 2021, doi:https://doi.org/10.1016/j.patcog.2021.108237.
45. P. Ma and X. Hu, “A Variational Autoencoder with Deep Embedding Model for Generalized Zero-Shot Learning,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 07, pp. 11733–11740, Apr. 2020, doi:https://doi.org/10.1609/aaai.v34i07.6844.
46. A. Maas and C. Kemp, “One-Shot Learning with Bayesian Networks,” vol. 31, no. 31, Jun. 2018, doi:https://doi.org/10.1184/r1/6617375.v1.
47. Y. Zhang, Z. Xiao, Z. Guo, and Z. Wang, “ECG-based personal recognition using a convolutional neural network,” Pattern Recognition Letters, vol. 125, pp. 668–676, Jul. 2019, doi:https://doi.org/10.1016/j.patrec.2019.07.009.
48. M. J. Page et al., “The PRISMA 2020 statement: An updated guideline for reporting systematic reviews.,” International Journal of Surgery, vol. 88, p. 105906, Apr. 2021, doi:https://doi.org/10.1016/j.ijsu.202
49. J. Helbach, F. Hoffmann, D. Pieper, and K. Allers, “Reporting according to the preferred reporting items for systematic reviews and meta-analyses for abstracts (PRISMA-A) depends on abstract length,” Journal of Clinical Epidemiology, vol. 154, pp. 167–177, Dec. 2022, doi:https://doi.org/10.1016/j.jclinepi.2022.12.019.
50. S.-C. Wu, A. L. Swindlehurst, S.-Y. Wei, J.-K. Chiu, and C.-S. Chang, “A Scalable Open-Set ECG Identification System Based on Compressed CNNs.,” IEEE transactions on neural networks and learning systems, vol. 34, no. 8, pp. 4966–4980, Aug. 2023, doi:https://doi.org/10.1109/tnnls.2021.3127497.
51. K. Su et al., “Human identification using finger vein and ECG signals,” Neurocomputing, vol. 332, pp. 111–118, Dec. 2018, doi:https://doi.org/10.1016/j.neucom.2018.12.015.
52. S. S. Tabrizi and N. Cavus, “A Hybrid KNN-SVM Model for Iranian License Plate Recognition,” Procedia Computer Science, vol. 102, pp. 588–594, Jan. 2016, doi:https://doi.org/10.1016/j.procs.2016.09.447.
53. E. Y. Boateng, D. A. Abaye, and J. Otoo, “Basic Tenets of Classification Algorithms K-Nearest-Neighbor, Support Vector Machine, Random Forest and Neural Network: A Review,” Journal of Data Analysis and Information Processing, vol. 08, no. 04, pp. 341–357, Jan. 2020, doi:https://doi.org/10.4236/jdaip.2020.84020.
54. E. M. Rudd, T. E. Boult, L. P. Jain, and W. J. Scheirer, “The Extreme Value Machine.,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 40, no. 3, pp. 762–768, May 2017, doi:https://doi.org/10.1109/tpami.2017.2707495.
55. F. Schornbaum and U. Rüde, “Extreme-Scale Block-Structured Adaptive Mesh Refinement,” SIAM Journal on Scientific Computing, vol. 40, no. 3, pp. C358–C387, Jan. 2018, doi:https://doi.org/10.1137/17m1128411.
56. W. Colomb, J. D. Sau, S. K. Sarkar, and J. Czerski, “Estimation of microscope drift using fluorescent nanodiamonds as fiducial markers.,” Journal of Microscopy, vol. 266, no. 3, pp. 298–306, Mar. 2017, doi:https://doi.org/10.1111/jmi.12539.
57. M. A. Elshahed, “Personal identity verification based ECG biometric using non-fiducial features,” International Journal of Electrical and Computer Engineering (IJECE), vol. 10, no. 3, p. 3007, Jun. 2020, doi:https://doi.org/10.11591/ijece.v10i3.pp3007-3013.
58. D. Wang, X. Zhang, M. Lin, Y. Zhu, and Y. Huang, “Automatic Modulation Classification Based on CNN-Transformer Graph Neural Network.,” Sensors, vol. 23, no. 16, p. 7281, Aug. 2023, doi:https://doi.org/10.3390/s23167281.
59. J. M. Shrein, “Fingerprint classification using convolutional neural networks and ridge orientation images,” Nov. 2017. doi:https://doi.org/10.1109/ssci.2017.8285375.
60. P. Dimitrakopoulos, G. Sfikas, and C. Nikou, “ISING-GAN: Annotated Data Augmentation with a Spatially Constrained Generative Adversarial Network,” Apr. 2020, pp. 1600–1603. doi:https://doi.org/10.1109/isbi45749.2020.9098618.
61. M. S. Meor Yahaya and J. Teo, “Data augmentation using generative adversarial networks for images and biomarkers in medicine and neuroscience,” Frontiers in Applied Mathematics and Statistics, vol. 9, May 2023, doi:https://doi.org/10.3389/fams.2023.1162760.
62. D. R. Bhuva and S. Kumar, “A novel continuous authentication method using biometrics for IOT devices,” Internet of Things, vol. 24, p. 100927, Sep. 2023, doi:https://doi.org/10.1016/j.iot.2023.100927.
63. N. Karimian, F. Tehranipoor, and P. A. Wortman, “Evolving authentication design considerations for the internet of biometric things (IoBT),” Oct. 2016, vol. 50, pp. 1–10. doi:https://doi.org/10.1145/2968456.2973748.
64. H. Kim and S. Y. Chun, “Cancelable ECG Biometrics Using Compressive Sensing-Generalized Likelihood Ratio Test,” IEEE Access, vol. 7, pp. 9232–9242, Jan. 2019, doi:https://doi.org/10.1109/access.2019.28918
