Elsevier

Digital Signal Processing

Volume 18, Issue 6, November 2008, Pages 951-959
Digital Signal Processing

Heart sound classification using wavelet transform and incremental self-organizing map

https://doi.org/10.1016/j.dsp.2008.06.001Get rights and content

Abstract

Determination of heart condition by heart auscultation is a difficult task and requires special training of medical staff. Computerized techniques suggest objective and more accurate results in a fast and easy manner. Hence, in this study it is aimed to perform computer-aided heart sound analysis to give support to medical doctors in decision making. In this study, a novel method is presented for the classification of heart sounds (HSs). Discrete wavelet transform is applied to windowed one cycle of HS. Wavelet transform is used both for the segmentation of S1–S2 sounds and determination of the features. Based on the third, fourth and the fifth decomposition-level detail coefficients, the timings of S1–S2 sounds are determined by an adaptive peak-detector. For the feature extraction, powers of detail coefficients in all five sub-bands are utilized. In the classification stage, Kohonen's SOM network and an incremental self-organizing map (ISOM) are examined comparatively. In order to increase the performance of heart sound classification, an incremental neural network is proposed in this study. It is observed that ISOM successfully classifies the HSs even in noisy environment.

Section snippets

Zümray Dokur received the B.Sc. degree in 1992, the M.Sc. degree in 1995, and Ph.D. degree in 2000, both in Electrical and Electronics Engineering, from Istanbul Technical University, Turkey. Since 1992 she has been with the Department of Electrical and Electronics Engineering at Istanbul Technical University, Turkey, where at present she is an associate professor. Her current research interests include pattern recognition, biomedical signal processing, image processing, computer vision, neural

References (32)

  • H. Yoshida, H. Shine, K. Yana, Instantaneous frequency analysis of systolic murmur for phonocardiogram, in: Proceedings...
  • R.M. Rangayyan et al.

    Phonocardiogram signal analysis: A review

    Crit. Rev. Biomed. Eng.

    (1987)
  • B. Maurice et al.

    The acoustic stethoscope and the electrical amplifying stethoscope and stethograph

    Am. Heart J.

    (1940)
  • A. Iwata et al.

    Algorithm for detecting the first and the second heart sounds by spectral tracking

    Med. Biol. Eng. Comput.

    (1980)
  • W.W. Myint, B. Dillard, An electronic stethoscope with diagnosis capability, in: Proceedings of the 33rd IEEE...
  • S. Lukkarinen et al.

    A new phonocardiographic recording system

    Comput. Cardiol.

    (1997)
  • Cited by (0)

    Zümray Dokur received the B.Sc. degree in 1992, the M.Sc. degree in 1995, and Ph.D. degree in 2000, both in Electrical and Electronics Engineering, from Istanbul Technical University, Turkey. Since 1992 she has been with the Department of Electrical and Electronics Engineering at Istanbul Technical University, Turkey, where at present she is an associate professor. Her current research interests include pattern recognition, biomedical signal processing, image processing, computer vision, neural networks, genetic algorithms, biomedical instrumentation.

    Tamer Ölmez received the B.Sc. degree in Electrical and Electronics Engineering in 1985, the M.Sc. degree in Computer Engineering in 1988, and Ph.D. degree in Electrical and Electronics Engineering in 1995, from Istanbul Technical University, Turkey. Between 1985 and 1988 he worked as a research engineer at TELETAS Turkey. Until the end of 1989 he worked at The Scientific and Technical Research Council of Turkey as a research engineer. Since then he has been with the Department of Electrical and Electronics Engineering at Istanbul Technical University, Turkey, where at present he is a professor. His current research interests include pattern recognition, machine learning, biomedical signal processing, image processing, computer vision, neural networks, genetic algorithms, real-time signal processing applications based on microprocessors.

    View full text