Comparative Study of ECG Based Identification

Abstract:

ECG waveform has becoming a new kind of Biometric signal for person identification recently. The identification procedure was based on the establishment of person's own ECG waveform template, one beat of ECG waveform was used as analysis data, 15 persons were involved in the study. In the paper, several algorithms are compared for their ability to identify person. The algorithms are coefficient threshold method and Euclidean distance threshold method, their measurement was based on linear distance. Hausdorff distance threshold method as a non linear distance was also compared. Except this, SWM(support vector machine) was also introduced to do the identification work. From the experimental results, Euclidean distance threshold method and the Hausdorff distance threshold method reached same level of identification, the acceptance rate is around 76.0%, the correlation coefficient threshold method reached 86.0%. As to the SVM, its acceptance rate near 96.0%. Although the amount of experiment data was relatively small, but the result give the researching in good promising and better prospecting.

• Periodical: Applied Mechanics and Materials (Volumes 713-715)
• Pages: 700-703
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.713-715.700
• Online since: January 2015
• Authors: Gang Zheng*, Ya Rong Wang, Qin Qin, Yang Li, Zhong Yi Li
• Keywords: Biometric Recognition, Correlation Coefficient, Electrocardiogram (ECG) Identification, Euclidean Distance, Hausdorff Distance, Support Vector Machine (SVM)

References

[1] R. Hoekema, G.J.H. Uijen, A. van Oosterom: Geometrical aspect of the interindividual variability of multilead ECG recordings, IEEE Trans. Biomedical. Engineering Vol. 48, (2001), pp.551-559.

DOI: 10.1109/10.918594

[2] L. Biel, O. Patterson, L. Philipson, and P. Wide: ECG analysis: a new approach in human identification, IEEE Trans on Instrumentation and Measurement, (2001), pp.808-812.

DOI: 10.1109/19.930458

[3] Israel, S.A., J.M. Irvine, A. Cheng, M.D. Wiederhold, B.K. Wiederhold: ECG to Identify Individuals, Pattern Recognition, Vol. 38, No. 1, ( 2005), pp.138-142.

DOI: 10.1016/j.patcog.2004.05.014

[4] Irvine, J.M., B.K. Wiederhold, L.W. Gavshon, S.A. Israel, S.B. McGehee, R. Meyer, M.D. Wiederhold, Heart Rate Variability: A New Biometric for Human Identification, Proceedings of International Conference on Artificial Intelligence, Vol. III, (2001).

[5] Konstantinos N. Plataniotis, Dimitrios Hatzinakos, Jimmy K. M. Lee. ECG Biometric Recognition Without Key Points Detection, (2006) Biometrics Symposium.

DOI: 10.1109/bcc.2006.4341628

[6] S. Zahra Fatemian, Student Member, IEEE, Dimitrios Hatzinakos: A new ECG feature extractor for biometric recognition, Proceedings of 16th International Conference on Digital Signal Processing, (2009), Vol. 1, pp.1-6.

DOI: 10.1109/icdsp.2009.5201143

[7] Agrafioti, F.; Hatzinakos, D., Signal validation for cardiac biometrics: Proceedings of IEEE International Conference on Acoustics Speech and Signal Processing, (2010), Vol. 1, 1734-1737.

DOI: 10.1109/icassp.2010.5495461