Application of Neural Network for ECG-based Biometrics System Using QRS Features

Ana Rahma Yuniarti, Syamsul Rizal, Ferdinand Aprillian Manurung


Applications of Biometrics technology are extremely popular today, ranging from access control to automation. Fingerprint is the oldest and the most widely used biometrics technology. However, it’s key features are externally exposed which make it tend to be easily forged. This study investigates the possibility of electrocardiogram (ECG) signal as an alternative modality for biometrics systems. Besides that, the study is conducted using the ECG database under arrhythmia conditions to accommodate the real-world application since arrhythmia exists in large-scale world populations. In this study, a total of 8,972 datasets from 47 subjects were modelled using a machine learning technique (i.e., one-dimensional convolution neural network or 1-D CNN). The results showed that the accuracy (F1-score) of 92% and 0.25 of loss was achieved. Furthermore, we prove that the proposed model is a good fitting based on the visualization plot of the train-test. These findings show that the proposed model is reasonable enough for an ECG-based biometrics system though it's not the best in the literature.

Full Text:



"Thalesgroup," 02 June 2021. [Online]. Available: [Accessed 20 07 2021].

Y. G. K. J. L. S. K. K. P. C. Kim J, "Efficiently Updating ECG-Based Biometric Authentication Based on Incremental Learning," Sensors, vol. 21, no. 5, p. 1568, 2021.

B. Q. M. Nguyen Minh Duc, "blackhat," Ha Noi University of Technology, [Online]. Available: [Accessed 8 8 2021].

K. X. Q. Y. Y. L. R. H. D. Yan Li, "Understanding OSN-based facial disclosure against face authentication systems," in Association for Computing Machinery, Kyoto, 2014.

P. X. J. L. Z. L. B. L. X. F. Yang Zhang, "Fingerprint attack against touch-enabled devices," in Association for Computing Machinery, Raleigh North Carolina, 2012.

P. O. P. L. W. P. Biel L, "ECG analysis: A new approach in human identification," IEEE Transaction on Instrumentation and Measurement, vol. 50, no. 3, p. 808, 2001.

T. W. H. Y. Shen TW, "One-lead ECG for identity verification," in IEEE, Houston, 2002.

I. J. C. A. W. M. W. B. Israel SA, "ECG to identify individuals," Pattern Recognition, vol. 38, no. 1, pp. 133-42, 2005.

S. H. D. Fatemian, "A new ECG feature extractor for biometric recognition," in IEEE, Santorini, 2009.

T. K. H. H. T. S. P. J. Zeng F, "A new statistical-based algorithm for ECG identification," in IEEE, Piraeus-Athens, 2012.

S. R. I. V. Bajare, "ECG based biometric for human identification using convolutional neural network," in IEEE, Kanpur, 2019.

R.-D. Bousseljot, "Physionet," Physikalisch-Technische Bundesanstalt, 25 9 2004. [Online]. Available: [Accessed 20 7 2021].

G. Moody, "Pysionet," MIT Laboratory for Computational Physiology, 3 8 1999. [Online]. Available: [Accessed 20 07 2021].

A. A. H. J. A. E. J. B. M. S. B. C. W. C. A. P. C. A. M. C. S. C. Salim S. Virani, "Circulation," American Heart Association, 27 01 2021. [Online]. Available: [Accessed 20 07 2021].

D. A. K. M. K. S. A. R. A. H. Saqib S, "Intelligent dynamic gesture recognition using cnn empowered by edit distance," Tech Science Press, 28 9 2020. [Online]. Available: [Accessed 9 08 2021].

S. P. S. M. S. C. Merone M., "ECG databases for biometric systems: A systematic review," Expert Systems with Applications, vol. 67, pp. 189-202, 2017.

"Carolina heart and leg center," Carolina heart and leg center P.A, [Online]. Available: [Accessed 8 8 2021].

L. Z. M. J. Xiang Y, "Automatic QRS complex detection using two-level convolutional neural network," BioMedical Engineering Oline, vol. 17, no. 1, p. 13, 2018.


  • There are currently no refbacks.

Journal of Computer Engineering, Electronics and Information Technology (COELITE)
is published by UNIVERSITAS PENDIDIKAN INDONESIA, and managed by Department of Computer Enginering.