DOI QR코드

DOI QR Code

ECG-based Biometric Authentication Using Random Forest

랜덤 포레스트를 이용한 심전도 기반 생체 인증

  • Kim, JeongKyun (Department of Computer Software, University of Science and Technology) ;
  • Lee, Kang Bok (IoT Research Department, Electronics and Telecommunications Research Institute) ;
  • Hong, Sang Gi (IoT Research Department, Electronics and Telecommunications Research Institute)
  • 김정균 (과학기술연합대학원대학교 컴퓨터소프트웨어전공) ;
  • 이강복 (한국전자통신연구원 IoT 연구본부) ;
  • 홍상기 (한국전자통신연구원 IoT 연구본부)
  • Received : 2017.01.26
  • Accepted : 2017.05.25
  • Published : 2017.06.25

Abstract

This work presents an ECG biometric recognition system for the purpose of biometric authentication. ECG biometric approaches are divided into two major categories, fiducial-based and non-fiducial-based methods. This paper proposes a new non-fiducial framework using discrete cosine transform and a Random Forest classifier. When using DCT, most of the signal information tends to be concentrated in a few low-frequency components. In order to apply feature vector of Random Forest, DCT feature vectors of ECG heartbeats are constructed by using the first 40 DCT coefficients. RF is based on the computation of a large number of decision trees. It is relatively fast, robust and inherently suitable for multi-class problems. Furthermore, it trade-off threshold between admission and rejection of ID inside RF classifier. As a result, proposed method offers 99.9% recognition rates when tested on MIT-BIH NSRDB.

본 논문은 개인 인증 알고리즘에 관한 것으로 심전도를 이용한 생체 인증 방식은 특정 보정기준점을 추출하는 방법과 그렇지 않은 방법으로 분류할 수 있으며 본 논문에서 제안하는 방법은 특정 보정기준점을 추출하지 않는 방법으로 이산 코사인 변환과 랜덤 포레스트 분류기를 사용하였다. 심전도 신호는 R-Peak 점을 기준으로 단일 심박으로 나누었으며 각 심박의 특징 추출을 위해 이산 코사인 변환을 적용하였다. 이산 코사인 변환 계수는 정보가 저주파에 집중되는 특성이 있으므로 초기 저주파에 해당하는 40까지 값을 특징으로 랜덤 포레스트 분류기를 구성하였다. 랜덤 포레스트는 의사결정 트리의 앙상블 분류기로 결정 트리를 기본으로 하고 있으므로 빠른 학습 속도와 많은 양의 데이터 처리 능력, 다양한 클래스를 분류할 수 있어 실생활에 적용 가능하며 무엇보다 ID의 승인과 거절을 위한 임계값을 분류기 내부에서 조절할 수 있어 오 분류에 강건한 알고리즘을 구성할 수 있다. 18개의 심전도 파일로 구성된 MIT-BIT Normal Sinus Rhythm 데이터베이스를 선정하여 성능을 평가하였으며 99.99%의 심전도 인식률을 보였다.

Keywords

References

  1. Task Force of the European Society of Cardiology., "Heart rate variability standards of measurement, physiological interpretation, and clinical use." Eur Heart J, vol. 17, pp. 354-381, 1996. https://doi.org/10.1093/oxfordjournals.eurheartj.a014868
  2. Jain A. K., Ross A., and Prabhakar S., "An introduction to biometric recognition." IEEE Transactions on circuits and systems for video technology, vol. 14, pp. 4-20, 2004. https://doi.org/10.1109/TCSVT.2004.839484
  3. Plataniotis, Konstantinos N., Hatzinakos D., and Lee J. K., "ECG biometric recognition without fiducial detection." Biometrics Symposium: Special Session on Research at the Biometric Consortium Conference. IEEE, pp. 1-6, 2006.
  4. Gang G. W., Min C. H., and Kim T. S.. "Development of Single Channel ECG Signal Based Biometrics System." Journal of the Institute of Electronics Engineers of Korea CI, vol. 49(1), pp. 1-7, 2012.
  5. Biel L., et al., "ECG analysis: a new approach in human identification." Instrumentation and Measurement Technology Conference, 1999. IMTC/99. Proceedings of the 16th IEEE, vol. 1, pp. 557-561, 1999.
  6. Wang Y., et al., "Analysis of human electrocardiogram for biometric recognition." EURASIP journal on Advances in Signal Processing, vol. 2008, pp. 148658, 2007. https://doi.org/10.1155/2008/148658
  7. Odinaka I., et al., "ECG biometric recognition: A comparative analysis." IEEE Transactions on Information Forensics and Security, vol. 7, pp. 1812-1824, 2012. https://doi.org/10.1109/TIFS.2012.2215324
  8. Martinez J. P., et al., "A wavelet-based ECG delineator: evaluation on standard databases." IEEE Transactions on biomedical engineering, vol. 51, pp. 570-581, 2004. https://doi.org/10.1109/TBME.2003.821031
  9. Benitez, D., et al., "The use of the Hilbert transform in ECG signal analysis." Computers in biology and medicine, vol. 51, pp. 570-581, 2004.
  10. Xue Q., Hu Y. H., and Tompkins W. J., "Neural-network-based adaptive matched filtering for QRS detection." IEEE Transactions on Biomedical Engineering, vol. 39, pp. 317-329, 1992. https://doi.org/10.1109/10.126604
  11. Kohler B. U., Hennig C., and Orglmeister R., "QRS detection using zero crossing counts." Applied genomics and proteomics, vol 2, pp 138-145, 2003.
  12. Hamilton P., "Open source ECG analysis." Computers in Cardiology IEEE, pp. 101-104, 2002.
  13. Ahmed N., Natarajan T., and Rao K. R., "Discrete cosine transform." IEEE transactions on Computers, vol. 100, pp. 90-93, 1974.
  14. Chen C, Liaw A, and Breiman L., "Using random forest to learn imbalanced data." University of California, Berkeley, vol. 110, 2004.
  15. Sahambi J. S., Tandon S. N., and Bhatt R. K. P., "Using wavelet transforms for ECG characterization. An on-line digital signal processing system." IEEE Engineering in Medicine and Biology Magazine, vol 16, pp. 77-83, 1997. https://doi.org/10.1109/51.566158
  16. Shen T. W., Tompkins W. J., and Hu Y. H., "One-lead ECG for identity verification." Engineering in Medicine and Biology 24th Annual Conference and the Annual Fall Meeting of the Biomedical Engineering Society EMBS/BMES Conference, vol. 1, pp. 62-63, 2002.
  17. Page A., Kulkarni A., and Mohsenin T., "Utilizing deep neural nets for an embedded ECG-based biometric authentication system." Biomedical Circuits and Systems Conference (BioCAS) IEEE, pp. 1-4, 2015.
  18. Sarkar A., Abbott A. L., and Doerzaph Z., "ECG biometric authentication using a dynamical model." Biometrics Theory, Applications and Systems (BTAS), 2015 IEEE 7th International Conference on, pp. 1-6, 2015.
  19. Belgacem N., et al., "ECG Based Human Identification Using Random Forests." The International Conference on E-Technologies and Business on the Web (EBW2013). Bangkok, Thailand., 2013.