The Journal of the Acoustical Society of Korea (한국음향학회지)

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

DOI QR Code

Performance Improvement of Cardiac Disorder Classification Based on Automatic Segmentation and Extreme Learning Machine

자동 분할과 ELM을 이용한 심장질환 분류 성능 개선

  • 곽철 (충북대학교 제어계측공학과) ;
  • 권오욱 (충북대학교 제어계측공학과)
  • Published : 2009.01.31
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we improve the performance of cardiac disorder classification by continuous heart sound signals using automatic segmentation and extreme learning machine (ELM). The accuracy of the conventional cardiac disorder classification systems degrades because murmurs and click sounds contained in the abnormal heart sound signals cause incorrect or missing starting points of the first (S1) and the second heart pulses (S2) in the automatic segmentation stage, In order to reduce the performance degradation due to segmentation errors, we find the positions of the S1 and S2 pulses, modify them using the time difference of S1 or S2, and extract a single period of heart sound signals. We then obtain a feature vector consisting of the mel-scaled filter bank energy coefficients and the envelope of uniform-sized sub-segments from the single-period heart sound signals. To classify the heart disorders, we use ELM with a single hidden layer. In cardiac disorder classification experiments with 9 cardiac disorder categories, the proposed method shows the classification accuracy of 81.6% and achieves the highest classification accuracy among ELM, multi-layer perceptron (MLP), support vector machine (SVM), and hidden Markov model (HMM).

본 논문은 자동 분할과 extreme learning machine (ELM)을 이용하여 연속 심음신호에 의한 심장질환 분류의 성능을 개선한다. 자동 분할을 위한 전처리 단계에서 비정상적인 심음신호는 심잡음 (murmur)과 클릭음 (click)을 포함하고 있기 때문에 제1음 (S1)과 제2음 (S2) 시작점 검출 결과가 부정확하거나 누락되어 기존의 심장질환 분류 시스템의 정확도를 저하시키게된다. 이러한 분할 오류에 의한 성능 저하를 감소하기 위해 S1 및 S2의 위치를 찾고, S1 및 S2의 시간 차이를 이용하여 부정확한 시작점을 교정한 다음 한 주기 심음 신호를 추출한다. 특징벡터로는 단일 주기의 심음 신호로부터 추출된 멜척도 필터뱅크 로그 에너지 계수와 포락선을 사용한다. 심장질환을 분류하기 위하여 한 개의 은닉층을 가진 ELM 알고리듬을 사용한다. 9가지 심장질환 분류 실험을 수행한 결과, 제안 방법은 81.6%의 분류 정확도를 나타내며, multi-layer perceptron(MLP), support vector machine (SVM), hidden Markov model (HMM) 중에서 가장 높은 분류 정확도를 보여준다.

Keywords

References

  1. D. Barschdorff, S. Ester, T. Dorsel, and E. Most, "Neural network based multi-sensor heart sound analysis," Proc. Computers in Cardiology 1990, Chicago, IL, USA, 303-306, Sep. 1990 https://doi.org/10.1109/CIC.1990.144221
  2. O. Abdel-Alim, N. Hamdy, and M. A. El-Hanjouri, "Heart diseases diagnosis using heart sounds," Proc. 19th NRSC, Alexandria Univ., Egypt, 634-640, Mar, 2002 https://doi.org/10.1109/NRSC.2002.1022675
  3. D. Barschdorff, U. Femmer, and E. Trowitzsch, "Atuomatic phonocardiogram signal analysis in infants based on wavelet transforms and artificial neural networks," Proc. Computers in Cardiology 1995, Vienna, Austria, 753-756, Sep. 1995 https://doi.org/10.1109/CIC.1995.482774
  4. M. El-Hanjouri, W. Alkhaldi, N. Hamdy, and O.A. Alim, "Heart diseases diagnosis using HMM," Proc. IEEE MELECON 2002, Cairo, Egypt, 489-492, May. 2002 https://doi.org/10.1109/MELECON.2002.1014641
  5. A. Ricke, R. Provinelli, and M. Johnson, "Automatic seg-mentation of heart sound signals using hidden Markov models," Proc. Computers in Cardiology 2005, 953-956, Sep. 2005 https://doi.org/10.1109/CIC.2005.1588266
  6. 김희근, 정용주, "Hidden Markov model를 이용한 심음분류에 관한 연구," 한국음향학회지, 3(25), 144-150, 2006
  7. 김희근, 정용주, "Ergodic hidden Markov model을 이용한 연속 심음분류에 관한 연구," 대한의료정보학회지, 13(1), 35-41, 2007
  8. E.R. Davies, Machine Vision 3rd Ed: Theory Algorithms Practicalities, (Morgan Kaufmann, 2005), Chap.4, pp.103-125
  9. G.-B. Huang, Q.-Y. Zhu, and C.-K. Siew, "Extreme learning machine: A new learning scheme of feedforward neural networks," 2004 International Joint Conference on Neural Networks (IJCNN'2004), 2, 985-990, July, 2004 https://doi.org/10.1109/IJCNN.2004.1380068
  10. G.-B. Huang, Q.-Y. Zhu and C.-K. Siew, "Extreme learning machine: Theory and applications, Neurocomputing, 70, 489-501, 2006 https://doi.org/10.1016/j.neucom.2005.12.126
  11. Daniel Mason, Listening to the Heart: A Comprehensive Collection of Heart Sounds and Murmurs, (F. A. Davis Com-pany, Philadephia, 2000)
  12. S. Young, G. Evermann, M. Gales, T. Hain, D. Kershwa, X. Liu, G. Moore, J. Odell, D. Ollason, D. Povey, V. Valtchev, and P. Woodland, Hidden Markov Model Toolkit v.3.4, (Cam-bridge University, 2006)
  13. H. Liang, S. Lukkarinen, and I. Hartimo, "Heart sound segmentation algorithm based on heart sound envelogram," Proc, Computers in Cardiology 1997, Lund, Sweden, 105-108, Sep. 1997 https://doi.org/10.1109/CIC.1997.647841
  14. M. Leshno, V. Y. Lin, A. Pinkus, and S. Schocken, "Multilayer feedforward networks with a nonpolynomial ac-tivation function can approximate any function," Neural Net-works, 6, 861-867, 1993 https://doi.org/10.1016/S0893-6080(05)80131-5
  15. M.F. Møller, "A scaled conjugate gradient algorithm for fast supervised learning," Neural Networks, 4(4), 525-533, 1993 https://doi.org/10.1016/S0893-6080(05)80056-5
  16. F. Schwenker, "Hierarchical support vector machines for multi-class pattern recognition," International Conference on Knowledge-based Intelligent Engineering Systems & Allied Technologies, Brighton, UK, 2, 561-565, 2000 https://doi.org/10.1109/KES.2000.884111
  17. Y. Liu and Y.F. Zheng, "One-against-all multi-class SVM classification using reliability meausres," IEEE International Joint Conference on Neural Networks, 2, 849-854, 2005 https://doi.org/10.1109/IJCNN.2005.1555963