Enhancing ECG-based authentication systems using VGG16 model and transfer learning

Eshaghi, Narges; Habibi, Mohammad; Bagheri, Nasour; Khatibi, Ali

doi:10.22061/jdma.2025.12571.1169

تعداد نشریات	15
تعداد شماره‌ها	246
تعداد مقالات	2,509
تعداد مشاهده مقاله	4,499,510
تعداد دریافت فایل اصل مقاله	3,316,522

	Enhancing ECG-based authentication systems using VGG16 model and transfer learning
Journal of Discrete Mathematics and Its Applications
دوره 11، شماره 1، خرداد 2026، صفحه 13-32 اصل مقاله (1.82 M)
نوع مقاله: Full Length Article
شناسه دیجیتال (DOI): 10.22061/jdma.2025.12571.1169
نویسندگان
Narges Eshaghi¹؛ Mohammad Habibi^* ¹؛ Nasour Bagheri²؛ Ali Khatibi³
¹Department of Mathematics, Tafresh University, Tafresh 39518-79611, Iran
²Electrical Engineering Department, Shahid Rajaee Teacher Training University, Tehran 16788-15811, Iran
³Department of Mechanical Engineering, Tafresh University, Tafresh 39518-79611, Iran
تاریخ دریافت: 06 مهر 1404، تاریخ بازنگری: 16 مهر 1404، تاریخ پذیرش: 22 مهر 1404
چکیده
This study explores a novel authentication algorithm leveraging ECG signals and deep learning models, specifically VGG16, enhanced with transfer learning. Authentication systems were evaluated based on preparation time, response time, and accuracy, with biometric data utilized to increase security. Traditional deep learning models face challenges in retraining time when data changes, prompting the proposed algorithm to incorporate new users or modify access efficiently using transfer learning. Key findings included training the VGG16 model on ECG data from 48 individuals (MITDB dataset) with a 99.45% accuracy and 120 seconds average training time. The transfer learning approach enabled adding or removing user data by adjusting SoftMax coefficients, reducing training time significantly to about 12 seconds per user with accuracy exceeding 99%. Removing a user followed a similar process with comparable results. Overall, the algorithm reduced retraining time by 72.89% while maintaining over 99.16% accuracy. Additionally, the system's response time for a new user was 37 milliseconds, demonstrating practicality for real-time applications. The study highlights the proposed algorithm's efficiency in managing user data changes while ensuring high accuracy and reduced retraining time, making it a robust solution for modern authentication systems.
کلیدواژه‌ها
Biometric Authentication System؛ ECG Signals؛ VGG16؛ Transfer Learning؛ Adding and Removing Users

مراجع
[1] M. M. A. Abuqadumah, M. A. M. Ali, R. R. O. Al-Nima, Personal authentication application using deep learning neural network, in: 2020 16th IEEE International Colloquium on Signal Processing and Its Applications (CSPA), 2020, pp. 186–190. https://doi.org/10.1109/CSPA48992.2020.9068706 [2] D. Belo, N. Bento, H. Silva, A. Fred, H. Gamboa, ECG biometrics using deep learning and relative score threshold classification, Sensors 20(15) (2020) 1–20. https://doi.org/10.3390/s20154078 [3] Y. Bengio, Y. LeCun, Scaling learning algorithms toward AI, in: Large-Scale Kernel Machines, MIT Press, 2007. https://doi.org/10.7551/mitpress/7496.003.0016 [4] C. Boncelet, Chapter 7 – Image noise models, in: The Essential Guide to Image Processing, Academic Press, 2009, pp. 143–167. https://doi.org/10.1016/B978-0-12-374457-9.00007-X [5] Y. Chu, H. Shen, K. Huang, ECG authentication method based on parallel multi-scale onedimensional residual network with center and margin loss, IEEE Access 7 (2019) 51598–51607. https://doi.org/10.1109/ACCESS.2019.2912519 [6] H. S. Desai, A. M. Gonsai, Hybrid CNN-VGG19 model for real-time face recognition system, Educ. Adm. Theory Pract. 30(6) (2024) 427–433. https://doi.org/10.53555/kuey.v30i6.6141 [7] A. L. Goldberger et al., PhysioBank, PhysioToolkit, and PhysioNet, Circulation 101(23) (2000) e215–e220. https://doi.org/10.1161/01.CIR.101.23.e215 [8] M. I. Hashem, K. Hasen Kuban, Key generation method from fingerprint image based on deep convolutional neural network model, Nexo Sci. J. 36(06) (2023) 906–925. https://doi.org/10.5377/nexo.v36i06.17447 [9] G. E. Hinton, R. R. Salakhutdinov, Reducing the dimensionality of data with neural networks, Science 313(5786) (2006) 504–507. https://doi.org/10.1126/science.1127647 [10] A. Hosna, E. Merry, J. Gyalmo, Z. Alom, Z. Aung, M. A. Azim, Transfer learning: a friendly introduction, J. Big Data 9(1) (2022) 102. https://doi.org/10.1186/s40537-022-00652-w [11] A. A. Kuznetsov, D. O. Zakharov, Deep learning-based models’ application to generating a cryptographic key from a face image, Radiotekhnika 2(213) (2023) 31–40. https://doi.org/10.30837/rt.2023.2.213.03 [12] T. Lam, S. Nilsson, Application of convolutional neural networks for fingerprint recognition, Master’s Thesis, Mathematical Sciences, 2018. http://lup.lub.lu.se/student-papers/record/8949667 [13] H. Li, N. A. Parikh, L. He, A novel transfer learning approach to enhance deep neural network classification of brain functional connectomes, Front. Neurosci. 12 (2018) 00491. https://doi.org/10.3389/fnins.2018.00491 [14] R. Li, G. Yang, K. Wang, Y. Huang, F. Yuan, Y. Yin, Robust ECG biometrics using GNMF and sparse representation, Pattern Recognit. Lett. 129 (2020) 70–76. https://doi.org/10.1016/j.patrec.2019.11.005 [15] H. M. Lynn, S. B. Pan, P. Kim, A deep bidirectional GRU network model for biometric electrocardiogram classification based on recurrent neural networks, IEEE Access 7 (2019) 145395–145405. https://doi.org/10.1109/ACCESS.2019.2939947 [16] J. Ma, S. Dang, G. Watkins, K. Morris, M. Beach, A high-performance transfer learning-based model for microwave structure behavior prediction, TechRxiv (2023). https://doi.org/10.36227/techrxiv.23700054.v1 [17] D. Makowski et al., NeuroKit2: a Python toolbox for neurophysiological signal processing, Behav. Res. Methods (2021) 1–8. https://doi.org/10.3758/s13428-020-01510-y [18] S. Maleki, Analysis and design bio-signals based access control schemes, M.Sc. thesis, Dept. of Electrical Engineering, Shahid Rajaee Teacher Training University, Tehran, Iran, 2020. [19] S. Minaee, A. Abdolrashidiy, Y. Wang, An experimental study of deep convolutional features for iris recognition, in: 2016 IEEE Signal Processing in Medicine and Biology Symposium (SPMB), 2016, pp. 1–6. https://doi.org/10.1109/SPMB.2016.7846859 [20] M. F. Moller, A scaled conjugate gradient algorithm for fast supervised learning, Neural Networks 6(4) (1993) 525–533. https://doi.org/10.1016/S0893-6080(05)80056-5 [21] A. Pantanowitz et al., Effective deep learning approach based on VGG-mini architecture for iris recognition, Informatics Med. Unlocked 26 (2021) 4718–4726. https://doi.org/10.1016/J.IMU.2021.100727 [22] M. Papez, A. Quinn, Transferring model structure in Bayesian transfer learning for Gaussian process regression, Knowledge-Based Syst. 251 (2022) 108875. https://doi.org/10.1016/j.knosys.2022.108875 [23] D. Sharma, A. Selwal, Biometrics: introduction and applications, in: Leveraging Computer Vision to Biometric Applications, 2024, pp. 1–18. https://doi.org/10.1201/9781032614663-1 [24] Y. Shi, Construction of the convolutional neural network based on the increase optimizers provided and atomic layers provided, in: 2022 2nd International Conference on Consumer Electronics and Computer Engineering (ICCECE), 2022, pp. 676–679. https://doi.org/10.1109/ICCECE54139.2022.9712718 [25] H.-C. Shin, M. R. Orton, D. J. Collins, S. J. Doran, M. O. Leach, Stacked autoencoders for unsupervised feature learning and multiple organ detection in a pilot study using 4D patient data, IEEE Trans. Pattern Anal. Mach. Intell. 35(8) (2013) 1930–1943. https://doi.org/10.1109/TPAMI.2012.277 [26] A. Singh, A. Nigam, RETRACTED ARTICLE: Effect of identity mapping, transfer learning and domain knowledge on the robustness and generalization ability of a network: a biometric based case study, J. Ambient Intell. Humaniz. Comput. 11(5) (2020) 1905–1922. https://doi.org/10.1007/s12652- 019-01297-z [27] R. Tan, M. Perkowski, Toward improving electrocardiogram (ECG) biometric verification using mobile sensors: a two-stage classifier approach, Sensors 17(2) (2017). https://doi.org/10.3390/s17020410 [28] J. Tao, Y. Gu, J. Sun, Y. Bie, H. Wang, Research on vgg16 convolutional neural network feature classification algorithm based on transfer learning, in: 2021 2nd China International SAR Symposium (CISS), 2021, pp. 1–3. https://doi.org/10.23919/CISS51089.2021.9652277 [29] S. D. Thepade, M. Dindorkar, P. Chaudhari, S. Bang, Face presentation attack identification optimization with adjusting convolution blocks in VGG networks, Intell. Syst. with Appl. 16 (2022) 200107. https://doi.org/10.1016/j.iswa.2022.200107 [30] K. Wang, G. Yang, Y. Huang, Y. Yin, Multi-scale differential feature for ECG biometrics with collective matrix factorization, Pattern Recognit. 102 (2020) 107211. https://doi.org/10.1016/j.patcog.2020.107211 [31] Z. Wen, S. Han, Y. Yu, X. Xiang, S. Lin, X. Xu, Empowering robust biometric authentication: the fusion of deep learning and security image analysis, Appl. Soft Comput. 154 (2024) 111286. https://doi.org/10.1016/j.asoc.2024.111286 [32] H. Yang, J. Ni, J. Gao, Z. Han, T. Luan, A novel method for peanut variety identification and classification by improved VGG16, Sci. Rep. 11(1) (2021) 15756. https://doi.org/10.1038/s41598- 021-95240-y [33] Z. Zhang, R. Tavenard, A. Bailly, X. Tang, P. Tang, T. Corpetti, Dynamic time warping under limited warping path length, Inf. Sci. 393 (2017) 91–107. https://doi.org/10.1016/j.ins.2017.02.018
آمار تعداد مشاهده مقاله: 257 تعداد دریافت فایل اصل مقاله: 217

سامانه مدیریت نشریات علمی. طراحی و پیاده سازی از سیناوب

پیوندهای مفید

آمار

Enhancing ECG-based authentication systems using VGG16 model and transfer learning