통계적 모델링 기법을 이용한 연속심음신호의 자동분류에 관한 연구

Automatic Classification of Continuous Heart Sound Signals Using the Statistical Modeling Approach

  • 발행 : 2007.05.31

초록

기존의 심음분류를 위한 연구들은 인공신경망을 이용하여 주로 이루어졌다. 그러나 심음신호의 통계적 특성을 분석 한 결과 HMM의 의한 신호모델링이 적합한 것으로 나타났다. 본 연구에서는 다양한 질병을 나타내는 심음신호를 HMM을 이용하여 모델링 하고 인식성능이 심음신호의 클러스터링에 따라서 많이 좌우되는 것을 알 수 있었다. 또한 실제 환경에서의 심음신호는 그 시작과 끝나는 시점이 정해지지 않은 연속신호이다. 따라서 HMM을 이용한 심음분류를 위해서는 연속적인 심음신호로부터 한 사이클의 분할된 심음을 추출할 필요성이 있다. 일반적으로 수동분할은 분할오류를 발생시키며 실시간 심음인식에 적합하지 않으므로 분할과정이 필요치 않는 ergodic형 HMM을 변형하여 사용할 것을 제안하였다. 그리고 제안된 HMM은 연속심음을 이용한 분류실험에서 매우 높은 성능을 보임을 알 수 있었다.

Conventional research works on the classification of the heart sound signal have been done mainly with the artificial neural networks. But the analysis results on the statistical characteristic of the heart sound signal have shown that the HMM is suitable for modeling the heart sound signal. In this paper, we model the various heart sound signals representing different heart diseases with the HMM and find that the classification rate is much affected by the clustering of the heart sound signal. Also, the heart sound signal acquired in real environments is a continuous signal without any specified starting and ending points of time. Hence, for the classification based on the HMM, the continuous cyclic heart sound signal needs to be manually segmented to obtain isolated cycles of the signal. As the manual segmentation will incur the errors in the segmentation and will not be adequate for real time processing, we propose a variant of the ergodic HMM which does not need segmentation procedures. Simulation results show that the proposed method successfully classifies continuous heart sounds with high accuracy.

키워드

참고문헌

  1. T.S.Leung, P.R.White, W.B.Collis, E.Brown, A.P.Salmon, 'Acoustic diagnosis of heart diseases', Proceedings of the 3rd international conference on acoustical and vibratory surveillance methods and diagnostic techniques, Senlis, France, 389-398, 1998
  2. Cather I, 'Neural network assisted cardiac auscultation', Artificial Intelligence in medicine. 7, 53-66, 1995 https://doi.org/10.1016/0933-3657(94)00026-O
  3. Bhatikar S. DeGroff C, Mahajan R, 'A classifier based on the artificial neural network approach for cardiology auscultation in pediatrics', Artificial Intelligence in medicine. 34 (1) 65-76, May 2005 https://doi.org/10.1016/j.artmed.2004.07.014
  4. DeGroff C, Bhatikar S. Hertzberg J, Shandas R, ValdesCruz L. Mahajan R, 'Artificial neural network-based method of screening heart murmur in children', Circulation, 103, 2711-6, 2001 https://doi.org/10.1161/01.CIR.103.22.2711
  5. Gill D. Intrator N, Gavriely N, 'A Probabilistic Model for Phonocardiograms Segmentation Based on Homomorphic Filtering', 18-th Biennial International EURASIP Conference Biosignal 2006. Brno. Czech Republic, .87-89, 2006
  6. Ricke A. Provinelli R. Johnson M, 'Automatic segmentation of heart sound signals using hidden Markov models'. Computer in Cardiology, 9. 953-956, 2005
  7. 김희근, 정용주, 'Hidden Markov Model을 이용한 심음분류에 관한 연구', 한국음향학회지, 25 (3), 166-170, 2006
  8. L. R. Rabiner, 'A tutorial on hidden Markov model and selected applications in speech recognition', IEEE Proc., 77, 257-286, Feb. 1989
  9. Daniel Mason, Listening to the heart: A Comprehensive Collection of Heart Sounds and Murmurs. (F. A. Davis Company. Philadelphia, 2000)
  10. L. E. Baum, G. S. T. Petrie and N. Weiss. 'A maximization technique occurring in the statistical analysis of probabilistic functions of Markov chains'. Ann. Math.Statist., 41,164-171, Jan. 1970 https://doi.org/10.1214/aoms/1177697196
  11. Davis S. B. and Mermelstein P. 'Comparison of parametric representation for monosyllabic word recognition in continuously spoken sentences', IEEE Trans. Acoust., Speech. Signal Processing. 28, 357-366, 1980 https://doi.org/10.1109/TASSP.1980.1163420