ECG-BASED AUTHENTICATION - Bayesian vs. Nearest Neighbour Classifiers

Carla Oliveira, Ana Fred

Abstract

This paper presents an approach for human authentication based on electrocardiogram (ECG) waveforms. ECG data was collected from 24 individuals during the realization of cognitive tests, where subjects held a surface mount triode placed on the V2 pre cordial derivation. Authentication is based on MAP, One-Class and 1-NN classifiers. Results show that ECG-based authentication may be a feasible tool for biometric systems. The One-Class classifier with class normalization has presented enhanced performance, with an equal error rate of 3.5%.

References

  1. Biel,L., Pettersson,O., Philipson,L. & Wide,P. (2001). ECG Analysis: A New Approach in Human Identification. In IEEE Transactions on Instrumentation and Measurement, Vol. 50, No. 3, 808-812.
  2. Israel,S., Irvine,J., Cheng,A., Wiederhold,M. & Wiederhold,B. (2005). ECG to identify individuals. In Pattern Recognition, Vol. 38, No. 1, 133-142.
  3. Sinus Rhythm. (2008). Retrieved 2008, from http://en.wikipedia.org/wiki/sinus_rhythm.
  4. Wübbeler,G., Stavridis,M., Kreiseler,D., Bousseljot,R. & Elster,C. (2007). Verification of Humans Using the Electrocardiogram. Pattern Recognition Letters, Vol. 28, No. 10, 1172-1175.
  5. Chan,A., Hamdy,M., Badre,A. & Badee,V. (2008). Wavelet Distance Measure for Person Identification Using Electrocardiograms. In IEEE Transactions on Instrumentation and Measurement, Vol. 57, No. 2, 248-253.
  6. Duda,R., Hart,P. & Stork,D. (2001). In Pattern Classification. John Willey & Sons Inc.. New York, 2nd Edition.
  7. Tax,D. (2001). One-Class classification: Concept-learning in the absence of counter-examples. Ph.D. Thesis, Delft University of Technology, Delft.
  8. HiMotion Project. (2008). Retrieved 2008, from http://www.it.pt/auto_temp_web_page_preview.asp?id =305.
  9. MATLAB Release 14 (2007). Retrieved 2008, from http://www.mathworks.com/products/matlab/.
Download


Paper Citation


in Harvard Style

Oliveira C. and Fred A. (2009). ECG-BASED AUTHENTICATION - Bayesian vs. Nearest Neighbour Classifiers . In Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2009) ISBN 978-989-8111-65-4, pages 163-168. DOI: 10.5220/0001549901630168


in Bibtex Style

@conference{biosignals09,
author={Carla Oliveira and Ana Fred},
title={ECG-BASED AUTHENTICATION - Bayesian vs. Nearest Neighbour Classifiers },
booktitle={Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2009)},
year={2009},
pages={163-168},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001549901630168},
isbn={978-989-8111-65-4},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2009)
TI - ECG-BASED AUTHENTICATION - Bayesian vs. Nearest Neighbour Classifiers
SN - 978-989-8111-65-4
AU - Oliveira C.
AU - Fred A.
PY - 2009
SP - 163
EP - 168
DO - 10.5220/0001549901630168