Title: The Impact of Data Segmentation Parameters on Performance in ECG-Based Identify Recognition Systems

Abstract: This study focuses on the segment duration required for identity recognition systems using electrocardiogram (ECG) signals, which are widely employed in disease diagnostics. Signals from the ECG-ID dataset were preprocessed and evaluated without detecting any critical points. The signals were segmented based on different parameters and fed into a Convolutional Neural Network (CNN) model, with results analyzed accordingly. The findings indicate that successful identity recognition can be achieved even with short segment durations. This highlights significant potential for developing more efficient and faster solutions in biometric security and identity verification systems.

Keywords: Electrocardiogram, segment duration, biometric security, identity verification

• Unar, J. A., Seng, W. C., & Abbasi, A. (2014). A review of biometric technology along with trends and prospects. Pattern recognition, 47(8), 2673-2688.
• Ingale, M., Cordeiro, R., Thentu, S., Park, Y., & Karimian, N. (2020). Ecg biometric authentication: A comparative analysis. IEEE Access, 8, 117853-117866.
• Biel, L., Pettersson, O., Philipson, L., & Wide, P. (2001). ECG analysis: a new approach in human identification. IEEE transactions on instrumentation and measurement, 50(3), 808-812.
• Hassan, Z., Gilani, S. O., & Jamil, M. (2016). Review of fiducial and non-fiducial techniques of feature extraction in ECG based biometric systems. Indian J. Sci. Technol, 9(21), 850-855.
• Wu, J. J., & Zhang, Y. (2014, December). ECG identification based on neural networks. In 2014 11th International Computer Conference on Wavelet Actiev Media Technology and Information Processing (ICCWAMTIP) (pp. 92-96). IEEE.
• Hejazi, M., Al-Haddad, S. A. R., Hashim, S. J., Aziz, A. F. A., & Singh, Y. P. (2017, September). Non-fiducial based ECG biometric authentication using one-class support vector machine. In 2017 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA) (pp. 190-194). IEEE.
• Bajare, S. R., & Ingale, V. V. (2019, July). ECG based biometric for human identification using convolutional neural network. In 2019 10th International Conference on Computing, Communication and Networking Technologies (ICCCNT) (pp. 1-7). IEEE.
• Liu, F., Si, Y., Luo, T., Wang, D., Liu, Q., & Li, L. (2018, December). The ECG identification based on GRNN. In 2018 IEEE International Conference on Communication Systems (ICCS) (pp. 418-422). IEEE.
• Gurkan, H., & Hanilci, A. (2020). ECG based biometric identification method using QRS images and convolutional neural network. Pamukkale University Journal of Engineering Sciences, 26(2), 318-327.
• Elshahed, M. A. (2020). Personal identity verification based ECG biometric using non-fiducial features. International Journal of Electrical and Computer Engineering, 10(3), 3007.
• Ibrahim, A. E., Abdel-Mageid, S., Nada, N., & Elshahed, M. A. (2020). ECG signals for human identification based on fiducial and non-fiducial approaches. International Journal of Advanced Computer Research, 10(47), 89-95.
• Bento, N., Belo, D., & Gamboa, H. (2020). ECG biometrics using spectrograms and deep neural networks. Int. J. Mach. Learn. Comput, 10(2), 259-264.
• Hamza, S., & Ayed, Y. B. (2022). Toward improving person identification using the ElectroCardioGram (ECG) signal based on non-fiducial features. Multimedia Tools and Applications, 81(13), 18543-18561.
• Altan, G., & Kutlu, Y. (2020). Generalization performance of deep autoencoder kernels for identification of abnormalities on electrocardiograms. In Deep learning for data analytics (pp. 37-62). Academic Press.
• Altan, G., & Kutlu, Y. (2015, May). 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.
• Goldberger, A., Amaral, L., Glass, L., Hausdorff, J., Ivanov, P. C., Mark, R., ... & Stanley, H. E. (2000). PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. Circulation [Online]. 101 (23), pp. e215–e220. https://physionet.org/content/ecgiddb/1.0.0/