Using Kullback-Leibler Distance in Determining the Classes for the Heart Sound Signal Classification

  • Yong-Joo Chung
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5326)


Many research efforts have been done on the automatic classification of heart sound signals to support clinicians in heart sound diagnosis. Recently, hidden Markov models (HMMs) have been used quite successfully in the automatic classification of the heart sound signal. However, in the classification using HMMs, there are so many heart sound signal types that it is not reasonable to assign a new class to each of them. In this paper, rather than constructing an HMM for each signal type, we propose to build an HMM for a set of acoustically-similar signal types. To define the classes, we use the KL (Kullback-Leibler) distance between different signal types to determine if they should belong to the same class. From the classification experiments on the heart sound data consisting of 25 different types of signals, the proposed method proved to be quite efficient in determining the optimal set of classes.


Classification Accuracy Hide Markov Model Signal Type Heart Sound Mitral Valve Prolapse 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Leung, T.S., White, P.R., Collis, W.B., Brown, E., Salmon, A.P.: Acoustic diagnosis of heart diseases. In: Proceedings of the 3rd international conference on acoustical and vibratory surveillance methods and diagnostic techniques, Senlis, France, pp. 389–398 (1998)Google Scholar
  2. 2.
    Cathers, I.: Neural Network Assisted Cardiac Asculation. Artif. Intell. Med. 7, 53–66 (1995)CrossRefGoogle Scholar
  3. 3.
    Bhatikar, S.R., DeGroff, C., Mahajan, R.L.: A Classifier Based on Artificial Neural Network Approach for Cardiac Auscultation in Pediatrics. Artif. Intell. Med. 33, 251–260 (2005)CrossRefGoogle Scholar
  4. 4.
    Lippmann, R.P.: An Introduction to Computing with Neural Nets. IEEE ASSP Magazine, 4–22 (April 1987)Google Scholar
  5. 5.
    DeGroff, C., Bhatikar, S., Hertzberg, J., Shandas, R., Valdes-Cruz, L., Mahajan, R.: Artificial neural network-based method of screening heart murmur in children. Circulation 103, 2711–2716 (2001)CrossRefGoogle Scholar
  6. 6.
    Gill, D., Intrator, N., Gavriely, N.: A Probabilistic Model for Phonocardiograms Segmentation Based on Homomorphic Filtering. In: 18th Biennial International EURASIP Conference Biosignal, pp. 87–89 (2006)Google Scholar
  7. 7.
    Ricke, A.D., Povinelli, R.J., Johnson, M.T.: Automatic segmentation of heart sound signals using hidden Markov models. Computers in Cardiology, 953–956 (September 2005)Google Scholar
  8. 8.
    Chung, Y.: A Classification Approach for the Heart Sound Signals Using Hidden Markov Models, SSPR/SPR, pp. 375–383 (2006)Google Scholar
  9. 9.
    Rabiner, L.R., Wilpon, J.G., Juang, B.H.: A segmental k-means training procedure for speech recognition. IEEE Trans. ASSP, 2033–2045 (December 1990)Google Scholar
  10. 10.
    Juang, B.H., Rabiner, L.R.: A probabilistic distance measure for hidden Markov models. AT&T Tech. J., 391–408 (1984)Google Scholar
  11. 11.
    Mason, D.: Listening to the Heart, Hahnemann University (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Yong-Joo Chung
    • 1
  1. 1.Department of ElectronicsKeimyung UniversityDaeguSouth Korea

Personalised recommendations