The Journal of the Acoustical Society of Korea (한국음향학회지)

The Acoustical Society of Korea (한국음향학회)
권호 표지
DOI QR코드

DOI QR Code

Heart Sound-Based Cardiac Disorder Classifiers Using an SVM to Combine HMM and Murmur Scores

SVM을 이용하여 HMM과 심잡음 점수를 결합한 심음 기반 심장질환 분류기

  • 곽철 (충북대학교 전자정보대학 제어로봇공학과) ;
  • 권오욱 (충북대학교 전자정보대학 제어로봇공학과)
  • Received : 2010.12.09
  • Accepted : 2011.03.23
  • Published : 2011.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose a new cardiac disorder classification method using an support vector machine (SVM) to combine hidden Markov model (HMM) and murmur existence information. Using cepstral features and the HMM Viterbi algorithm, we segment input heart sound signals into HMM states for each cardiac disorder model and compute log-likelihood (score) for every state in the model. To exploit the temporal position characteristics of murmur signals, we divide the input signals into two subbands and compute murmur probability of every subband of each frame, and obtain the murmur score for each state by using the state segmentation information obtained from the Viterbi algorithm. With an input vector containing the HMM state scores and the murmur scores for all cardiac disorder models, SVM finally decides the cardiac disorder category. In cardiac disorder classification experimental results, the proposed method shows the relatively improvement rate of 20.4 % compared to the HMM-based classifier with the conventional cepstral features.

본 논문은 support vector machine (SVM)을 사용하여 은닉 마코프 모델 (HMM)과 심잡음 존재 정보를 결합한 새로운 심장질환 분류 방법을 제안한다. 켑스트럼 특징과 HMM 비터비 (Viterbi) 알고리듬을 이용하여 입력 신호를 모든 심장질환 모델에 대하여 상태 단위로 분할하여 상태별로 로그우도 (점수)를 계산한다. 심잡음 신호의 시간적 위치 특성을 이용하기 위하여 입력신호를 두 개의 부대역으로 나누고 부대역별로 프레임 단위의 심잡음 점수를 계산한 다음, 비터비 알고리듬으로부터 구한 상태 분할 정보를 이용하여 상태단위의 심잡음 점수를 구한다. SVM은 모든 심장질환 종류에 대한 상태 단위의 HMM과 심잡음 점수를 입력으로 하여 최종적으로 심장질환을 판정한다. 심장질환 분류 실험결과, 제안한 방법은 기존의 켑스트럼 특징과 HMM 분류기를 이용한 방법에 비하여 20.4 %의 상대적 개선율을 보여준다.

Keywords

References

  1. S.M. Arcasoy, J.D. Christie, V.A. Ferrari, M.S. Sutton, D.A. Zisman, N.P. Blumenthal, A. Pochettino and R.M. Kotloff, "Echocardiographic assessment of pulmonary hypertension in patients with advanced lung disease," American journal of respiratory and critical care medicine, vol. 167, pp. 735-740, 2003. https://doi.org/10.1164/rccm.200210-1130OC
  2. C.N. Gupta, R. Palaniappan, S. Swaminathan and S.M. Krishnan, "Neural network classification of homomorphic segmented heart sounds," Applied Soft Computing, vol. 7, pp. 286-297, 2007. https://doi.org/10.1016/j.asoc.2005.06.006
  3. R.K. Sinha, Y. Aggarwal and B.N. Das, "Backpropagation artificial neural network classifier to detect changes in heart sound due to mitral valve regurgitation," Journal of Medical Systems, vol. 31, pp. 205-209, 2007. https://doi.org/10.1007/s10916-007-9056-1
  4. R.A. Azra'ai, M.N. bin Taib and N.M. Tahir, "Artificial neural network for identification of heart problem," in Proc. Signal Processing and Communication Systems 2008, Gold Coast, Australia, pp. 1-6, Dec. 2008.
  5. A. Ricke, R. Provinelli and M. Johnson, "Automatic segmentation of heart sound signals using hidden Markov models," Proc. Computers in Cardiology 2005, Lyon, France, pp. 953-956, Sep. 2005.
  6. M. Obayya and F. Abou-Chadi, "Classifying some cardiac abnormalities using heart rate variability signals," in Proc. 25th National Radio Science Conference 2008, Tanta Univ., Egypt, pp. 1-8, Mar. 2008.
  7. S.E. Schmidt, E. Toft, C. Holst-Hansen, C. Graff and J.J. Struijk, "Segmentation of heart sound recordings from an electronic stethoscope by a duration dependent hidden- Markov model," in Proc. Computers in Cardiology 2008, Bologna, Italy, pp. 345-348, Sep. 2008.
  8. 김희근, 정용주, "Ergodic hidden Markov model을 이용한 연속심 음분류에 관한 연구," 대한의료정보학회지, 13권, 1호, 35-41쪽, 2007.
  9. C. Kwak and O.-W. Kwon, "Cardiac disorder classification based on extreme learning machine," in Proc. World Academy of Science, Engineering and Technology 2008, Bangkok, Thailand, vol. 36, pp. 1260-1263, Dec. 2008.
  10. 곽철, 권오욱, "자동 분할과 ELM을 이용한 심장질환 분류 성능 개선", 한국음향학회지, 28권, 1호, 32-43쪽, 2009.
  11. 곽철, 권오욱, "심음 기반의 심장질환 분류를 위한 새로운 시간영역 특징", 한국음향학회지, 29권, 2호, 133-140쪽, 2010.
  12. C. Donghui and L. Zhijing, "A new text categorization method based on HMM and SVM," in Proc. 2010 2nd International Conference on Computer Engineering and Technology, Chengdu, China, pp. 383-386, Apr. 2010.
  13. J.D. Cai and R.W. Yan, "Application of FCM-HMM-SVM based mixed method for fault diagnosis of power electronic circuit," in Proc. International Conference on Mechanic Automation and Control Engineering, Wuhan, China, pp. 3982-3985, Jun. 2010.
  14. S. Haykin, Neural Networks: A comprehensive foundation, 2nd ed., Prentice Hall, 1999.
  15. S. Young, G. Evermann, M. Gales, T. Hain, D. Kershaw, X. Liu, G. Moore, J. Odell, D. Ollason, D. Povey, V. Valtchev and P. Woodland, Hidden Markov Model Toolkit v3.4, Cambridge University, 2006.
  16. D. Mason, Listening to the Heart: A Comprehensive Collection of Heart Sounds and Murmurs, F.A. Davis Company, Philadelphia, 2000.
  17. University of Washington department of medicine, Technique: Heart Sounds & Murmurs, http://depts.washington.edu/physdx/heart/tech.html
  18. Texas heart institute as St. Luke's episcopal hospital, Heart Sound and Murmur Recordings, http://www.texasheart.org/Education/CME/explore/events/eventdetail_5469.cfm