Article Detail

Yasin TAŞTEKİN

Keywords

ECG Biometric Identification Deep Learning CNN Chest Leads

Doi : 10.71350/hgtsci.2026162

Abstract

Electrocardiogram (ECG) signals can be used as an alternative method in biometric identification systems due to the unique cardiac structure of each individual. In this study, the person identification performances of six different chest leads (V1-V6) were compared. ECG recordings of 290 patients from the PTB Diagnostic ECG Database were used, and heartbeats were segmented after R-peak detection. A convolutional neural network (CNN)-based deep learning model was trained for each lead. According to the results obtained, the V3 lead showed the highest performance with 98.50% accuracy. The V2 lead ranked second with 98.43% accuracy, while the V1 lead exhibited the lowest performance with 97.69%. The AUC values of all leads were above 0.999, indicating excellent discrimination capacity. The findings demonstrate that biometric identification can be performed with high accuracy even using a single lead, and V2-V3 leads are the most suitable options for practical applications.

References

1. Altan, G., Kutlu, Y., & Yeniad, M. (2019). ECG based human identification using second order difference plots. Computer Methods and programs in Biomedicine, 170, 81-93.
2. Altan, G., & Kutlu, Y. (2015). ECG based human identification using logspace grid analysis of second order difference plot. In 2015 23nd Signal Processing and Communications Applications Conference (SIU) (pp. 1288-1291). IEEE.
3. Bel, M., Kutlu, Y., Gürsoy-Demır, H. (2025). Comparative Analysis of Wavelet Types for Feature Extraction in Arrhythmia Classification. Journal of Artificial Intelligence with Applications, 6(1), 8-13, doi : 10.5281/zenodo.18105152
4. Bousseljot, R., Kreiseler, D., & Schnabel, A. (1995). Nutzung der EKG-Signaldatenbank CARDIODAT der PTB über das Internet. Biomedizinische Technik/Biomedical Engineering, 40(s1), 317-318.
5. Fawcett, T. (2006). An introduction to ROC analysis. Pattern Recognition Letters, 27(8), 861-874.
6. Fratini, A., Sansone, M., Bifulco, P., & Cesarelli, M. (2015). Individual identification via electrocardiogram analysis. BioMedical Engineering OnLine, 14(1), 78.
7. Hejazi, M., Al-Haddad, S. A. R., Singh, Y. P., Hashim, S. J., & Abdul Aziz, A. F. (2019). ECG biometric authentication based on non-fiducial approach using kernel methods. Digital Signal Processing, 52, 72-86.
8. Kim, J., Kim, Y., & Jung, H. (2020). ECG identification for personal authentication using LSTM-based deep recurrent neural networks. Sensors, 20(11), 3069.
9. Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. Proceedings of the 3rd International Conference on Learning Representations (ICLR).
10. LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278-2324.
11. Luz, E. J. S., Schwartz, W. R., Cámara-Chávez, G., & Menotti, D. (2018). ECG-based heartbeat classification for arrhythmia detection: A survey. Computer Methods and Programs in Biomedicine, 127, 144-164.
12. Pan, J., & Tompkins, W. J. (1985). A real-time QRS detection algorithm. IEEE Transactions on Biomedical Engineering, BME-32(3), 230-236.
13. Pinto, J. R., Cardoso, J. S., & Lourenço, A. (2018). Evolution, current challenges, and future possibilities in ECG biometrics. IEEE Access, 6, 34746-34776.
14. Salloum, R., & Kuo, C. C. J. (2017). ECG-based biometrics using recurrent neural networks. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2062-2066.
15. Silva, H., Lourenço, A., Fred, A., & Martins, R. (2021). Deep learning for ECG-based biometric recognition: A comparative study. IEEE Access, 9, 30988-31002.
16. Sokolova, M., & Lapalme, G. (2009). A systematic analysis of performance measures for classification tasks. Information Processing & Management, 45(4), 427-437.
17. Tompkins, W. J. (1993). Biomedical digital signal processing: C language examples and laboratory experiments for the IBM PC. Prentice-Hall.
18. Tohma, S. (2025). Classification of Arrhythmia and Cardiac Anomalies from ECG Signals: A Machine Learning-Based Comparison on MIT-BIH and PTB-DB. Journal of Natural and Engineering Research, 1(1), 19-29, doi : 10.5281/zenodo.18664503
19. Türkyılmaz, M., Kutlu, Y. (2025). The Effect of ECG Signals at Different Time Windows on Biometric Authentication Success. Health Science and Green Technology, 1(1), 44-50, doi : 10.5281/zenodo.18649963
20. Wang, D., Si, Y., Yang, W., Zhang, G., & Liu, T. (2019). A novel electrocardiogram biometric identification method based on temporal-frequency autoencoding. Electronics, 8(6), 667.
21. Zhang, Y., Xiao, Z., Guo, Z., & Wang, Z. (2020). ECG-based personal identification using a convolutional neural network. Pattern Recognition Letters, 125, 668-676.