Wavelet Entropy Detection of Heart Sounds

  • T. Leeudomwong
  • P. Woraratsoontorn
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 27)


Heart sound detection has been demonstrated to be important in the diagnosis of heart disease, especially in patients with abnormality of the cardiac valves. Heart sounds are produced from blood flow through the cardiac valves during heart contraction and relaxation, and they can be heard and recorded on the patient’s chest. In this research, two groups of patients, those with normal hearts and those with mitral regurgitation, were studied. The application of wavelet transform analysis to heart sound signals is presented for both groups. The continuous wavelet transform plot shows that patients with mitral regurgitation are likely to have the irregular features of heart sounds in a three-dimensional diagram, whereas normal heart sounds seem to show relatively smooth surfaces. The wavelet entropy is then computed for the heart sounds. A disordered signal offers a high entropy value. Observations of the preliminary results in this research show that the heart sounds from the patients with mitral regurgitation tend to have higher wavelet entropy than those from the patients with normal hearts.


Mitral Regurgitation Normal Heart Heart Sound Continuous Wavelet Transform Cardiac Valve 


  1. 1.
    Brusco M, Nazeran H (2004) Digital phonocardiography: a PDA-based approach. In: Proceedings of the 26th annual international conference of the IEEE EMBS, pp 2299–2302Google Scholar
  2. 2.
    Bunluechokchai S, English MJ (2003) Detection of wavelet transform-processed ventricular late potentials and approximate entropy. IEEE computers in cardiology, pp 549–552Google Scholar
  3. 3.
    Bunluechokchai S, English MJ (2003) Analysis of the high resolution ECG with the continuous wavelet transform. IEEE computers in cardiology, pp 553–556Google Scholar
  4. 4.
    Djebbari A, Reguig B (2002) Short-time Fourier transform analysis of the phonocardiogram signal. In: The 7th IEEE international conference on electronics, circuits and systems, pp 844–847Google Scholar
  5. 5.
    Durand LG and Pibarot P (1995) Digital signal processing of the phonocardiogram: review of the most recent advancements. Crit Rev Biomed Eng163–219Google Scholar
  6. 6.
    Kumar P, Carvalho M, Antunes M, Gil P, Henriques J, Eugenio L (2006) A new algorithm for detection of S1 and S2 heart sounds. In: IEEE international conference on acoustic, speech, and signal processing ICASSP, pp 1180–1183Google Scholar
  7. 7.
    Mgdob HM, Torry JN, Vincent R, Al-Naami B (2003) Application of Morlet transform wavelet in the detection of paradoxical splitting of the second heart sound. IEEE computers in cardiology, pp 323–326Google Scholar
  8. 8.
    Omran S, Tayel M (2004) A heart sound segmentation and feature extraction algorithm using wavelets. In: First international symposium on control, communications and signal processing, pp 235–238Google Scholar
  9. 9.
    Tovar-Corona B, Torry JN (1998) Time-frequency representation of systolic murmurs using wavelets. IEEE computers in cardiology, pp 601–604Google Scholar
  10. 10.
    Zhidong Z, Zhijin Z, Yuquan C (2005) Time-frequency analysis of heart sound based on HHT. In: IEEE international conference on communications, circuits and systems, pp 926–929Google Scholar
  11. 11.
    Zin ZM, Salleh SH, Daliman S, Sulaiman MD (2003) Analysis of heart sounds based on continuous wavelet transform. In: IEEE conference on research and development, pp 19–22Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2009

Authors and Affiliations

  • T. Leeudomwong
    • 1
  • P. Woraratsoontorn
    • 1
  1. 1.Department of Industrial Physics and Medical Instrumentation, Faculty of Applied ScienceKing Mongkut’s Institute of Technology, North BangkokBangsueThailand

Personalised recommendations