Journal of Artificial Intelligence and Metaheuristics
Journal DOI
2833-5597ISSN (Online)
Volume 5 , Issue 2 , PP: 31-40, 2023 | Cite this article as | XML | Html | PDF | Full Length Article
Ammar Kadi 1 * , Adel Oubelaid 2 , S. K. Towfek 3
Doi: https://doi.org/10.54216/JAIM.050203
The electrocardiogram (ECG) is a type of biometric data that has recently attracted a lot of attention as a potentially useful biometric trait due to its high discriminatory power. However, precise and consistent biometric identification systems are challenging to deploy because to ECG signals' vulnerability to a wide range of sounds, including baseline wander, powerline interference, and high/low frequency noises. That's why ECG signal denoising is such an important aspect of the preprocessing phase for ECG-based biometric person identification: it removes noise from the raw ECG data. Biometric recognition using ECG signals is a difficult problem involving phases of preprocessing, feature extraction, feature selection, feature modification, and classification. Biometric system analysis also relies heavily on the use of appropriate success measures and a well-organized library of ECG signals. This is especially crucial when considering the fact that researchers rely significantly on freely accessible resources to gauge the efficacy of the algorithms they propose. In this study, we examine most of the approaches that have been taken toward ECG-based biometric verification of humans.
ECG biometrics , Applications of biometric , Biometric traits , Feature extraction , Classification , feature fusion , Authentication , Machine learning.
[1] M M A Rahhal, Y Bazi, H AlHichri, N Alajlan, F Melgani, R R Yager, Deep learning approach for active classification of electrocardiogram signals. Inf. Sci., 345, 340–354, 2016.
[2] D D Testa, M Rossi, Lightweight lossy compression of biometric patterns via denoising autoencoders. IEEE Signal Process. Lett., 22(12), 2304–2308, 2015.
[3] C Shaojie, Z Meng, Q Zhao, Electrocardiogram recognization based on variational AutoEncoder. Machine Learning and Biometrics. IntechOpen, 2018.
[4] D Wang, Y Si, W Yang, G Zhang, J Li, A novel electrocardiogram biometric identification method based on temporal-frequency autoencoding. Electronics, 8(6), 667, 2019.
[5] R D Labati, E Muæoz, V Piuri, R Sassi, F Scotti, Deep-ECG: Convolutional neural networks for ECG biometric recognition. Pattern Recognit. Lett., 126, 78–85, 2019.
[6] D M Uliyan, S Sadeghi, H A Jalab, Anti-spoofing method for fingerprint recognition using patch based deep learning machine. Eng. Sci. Technol., Int. J., 23(2), 264–273, 2020.
[7] S C Wu, P T Chen, A L Swindlehurst, P L Hung, Cancelable biometric recognition with ECGs: Subspace-based approaches. IEEE Trans. Inf. Forensics Security, 14(5), 1323–1336, 2019.
[8] J Galbally-Herrero, J Fierrez-Aguilar, J Rodriguez-gonzalez, F Alonso-Fernandez, J Ortega-Garcia, M Tapiador, On the vulnerability of fingerprint verification systems to fake fingerprints attacks. in Proc. 40th Annu. Int. Carnahan Conf. Secur. Technol., 130–136, 2006.
[9] J Galbally, S Marcel, J Fierrez, Biometric antispoofing methods: A survey in face recognition. IEEE Access, 2, 1530–1552, 2014.
[10] R D Labati, R Sassi, F Scotti, ECG biometric recognition: Permanence analysis of QRS signals for 24 hours continuous authentication. in Proc. IEEE Int. Workshop Inf. Forensics Secur. (WIFS), 31–36, 2013.
[11] Q Zhang, D Zhou, X Zeng, HeartID: A multiresolution convolutional neural network for ECG-based biometric human identification in smart health applications. IEEE Access, 5, 11805–11816, 2017.
[12] I Odinaka, P H Lai, A Kaplan, J A O’Sullivan, E J Sirevaag, J W Rohrbaugh, ECG biometric recognition: A comparative analysis. IEEE Trans. Inf. Forensics Security, 7(6), 1812–1824, 2012.
[13] G Lenis, N Pilia, A Loewe, W H W Schulze, O Dössel, Comparison of baseline wander removal techniques considering the preservation of ST changes in the ischemic ECG: A simulation study, Comput. Math. Methods Med. 2017, 1–13, 2017.
[14] R Li, G Yang, K Wang, Y Huang, F Yuan, Y Y, Robust ECG biometrics using GNMF and sparse representation. Pattern Recognit. Lett., 129, 70–76, 2020.
[15] S Min, B Lee, S Yoon, Deep learning in bioinformatics. Brief Bioinform., 18(5), 851–869, 2016.
[16] Z Mao, W X Yao, Y Huang, EEG-based biometric identification with deep learning. in Proc. 8th Int. IEEE/EMBS Conf. Neural Eng. (NER), 609–612, 2017.
[17] S Hong, Y Zhou, J Shang, C Xiao, J Sun, Opportunities and challenges of deep learning methods for electrocardiogram data: A systematic review. Comput. Biol. Med., 122, 103801, 2020.
[18] P L Hong, J Y Hsiao, C H Chung, Y M Feng, S C Wu, ECG biometric recognition: Template-free approaches based on deep learning. in Proc. 41st Annu. Int. Conf. IEEE Eng. Med. Biol. Soc., 2633–2636, 2019.
[19] S M Mathews, C Kambhamettu, K E Barner, A novel application of deep learning for single-lead ECG classification. Comput. Biol. Med., 99, 53–62, 2018.
[20] Z Ebrahimi, M Loni, M Daneshtalab, A Gharehbaghi, A review on deep learning methods for ECG arrhythmia classification. Expert Syst. Appl., 7, 2020.
[21] L Biel, O Pettersson, L Philipson, P Wide, ECG analysis: A new approach in human identification. IEEE Trans. Instrum. Meas., 50(3), 808–812, 2001.
[22] J M Irvine, S A Israel, W T Scruggs, W J Worek, EigenPulse: Robust human identification from cardiovascular function. Pattern Recognit., 41(11), 3427–3435, 2008.
[23] O Boumbarov, Y Velchev, S Sokolov, ECG personal identification in subspaces using radial basis neural networks. in Proc. IEEE IDAACS, 446-451, 2009.
[24] S C Wu, P L Hung, A L Swindlehurst, ECG biometric recognition: Unlinkability, irreversibility, and security. IEEE Internet Things J., 8(1), 487–500, 2021.
[25] Z Hassan, S O Gilani, M Jamil, Review of fiducial and nonfiducial techniques of feature extraction in ECG based biometric systems. Indian J. Sci. Technol., 9(21), 850–855, 2016.
[26] A L Goldberger et al, PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. Circulation, 101(23),e215–e220, 2000.
[27] M K Das and S Ari, ECG beats classification using mixture of features. Int. Scholarly Res. Notices,1–12, 2014.
[28] J. Xu, G. Yang, K. Wang, Y. Huang, H. Liu, and Y. Yin, ‘‘Structural sparse representation with class-specific dictionary for ECG biometric recognition,’’ Pattern Recognit. Lett., vol. 135, pp. 44–49, Jul. 2020.
[29] S Lee, Y Jeong, D Park, B J Yun, K Park, Efficient fiducial point detection of ECG QRS complex based on polygonal approximation. Sensors, 18(12), 4502, 2018.
[30] K N Plataniotis, D Hatzinakos, J K M Lee, ECG biometric recognition without fiducial detection. in Proc. Biometrics Symp., Special Session Res. Biometric Consortium Conf., 1–6, 2006.
