STUDY OF TWO FEATURE EXTRACTION METHODS TO DISTINGUISH BETWEEN THE FIRST AND THE SECOND HEART SOUNDS

Ali Moukadem, Alain Dieterlen, Christian Brandt

2012

Abstract

Most of the existing methods for the segmentation of heart sounds use the feature of systole and diastole duration to classify the first heart sound (S1) and the second heart sound (S2). These time intervals can become problematic and useless in several clinical real life settings which are particularly represented by severe tachycardia or in tachyarrhythmia. Consequently with the objective of development of a robust generic module for heart sound segmentation we propose to study two methods of extraction based on Singular Value Decomposition (SVD) technique to distinguish S1 from S2. A K-Neirest Neighbor (KNN) classifier is used to estimate the performance of each feature extraction method. The study uses a database with 80 subjects, including 40 cardiac pathologic sounds which contain different systolic murmurs and tachycardia cases. The first and the second proposed method reached 96 % and 95% correct classification rates, respectively.

References

  1. Ahlstrom C., Nonlinear Phonocardiographic Signal Processing thesis, Linköping University, SE-581 85 Linköping, Sweden, April 2008.
  2. Dokur Z., Ölmez T., Feature determination for heart sounds based on divergence analysis, Digital Signal Process. (2007), doi:10.1016/j.dsp. 2007.11.003.
  3. Felner J., The Second Heart Sound, Clinical Methods: The History, Physical, and Laboratory Examinations. 3rd edition. 1990.
  4. Kumar D., Carvalho P., Antunes M., Paiva R. P., Henriques J., An Adaptive Approach to Abnormal Heart Sound Segmentation, ICASSP 2011.
  5. Hassanpour H., Mesbah M., Boashash B., Time-frequency feature extraction of newborn EEG seizure using svdbased techniques. Eurasip J Appl Sig Proc, 16:2544- 2554, 2004.
  6. Huang N. E., Shen Z., Long S. R., Wu Z. C., Shih H. H., Zheng Q., Yen N. C, Tung C. C, Liu H. H, The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis, Mathematical Physical and Engineering Sciences 454 (1998) 903-995.
  7. Liang H., Lukkarinen S. and Hartimo I., ”Heart Sound Segmentation Algorithm Based On Heart Sound Envelogram”, Proc. of IEEE Computers in Cardiology, 1997, page. 105-108.
  8. Moukadem A., Dieterlen A., Hueber N., Brandt C., Localization of heart sounds based on S-transform and radial basis functions, 15TH Nordic-Baltic conference on biomedical engineering and medical physics (NBC 2011) IFMBE Proceedings, 2011, Volume 34, 168- 171, doi: 10.1007/978-3-642-21683-1_42.
  9. Stockwell R. G., Mansinha L., Lowe R. P., Localization of the complex spectrum: the S-transform, IEEE Trans. Sig. Proc. 44 (4) (1996) 998-1001.
  10. Yan Z. et al., The moment segmentation analysis of heart sound pattern, Comput. Methods & Programs Biomed. (2009), doi:10.1016/j.cmppb.2009.09.008.
Download


Paper Citation


in Harvard Style

Moukadem A., Dieterlen A. and Brandt C. (2012). STUDY OF TWO FEATURE EXTRACTION METHODS TO DISTINGUISH BETWEEN THE FIRST AND THE SECOND HEART SOUNDS . In Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2012) ISBN 978-989-8425-89-8, pages 346-350. DOI: 10.5220/0003743703460350


in Bibtex Style

@conference{biosignals12,
author={Ali Moukadem and Alain Dieterlen and Christian Brandt},
title={STUDY OF TWO FEATURE EXTRACTION METHODS TO DISTINGUISH BETWEEN THE FIRST AND THE SECOND HEART SOUNDS},
booktitle={Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2012)},
year={2012},
pages={346-350},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003743703460350},
isbn={978-989-8425-89-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2012)
TI - STUDY OF TWO FEATURE EXTRACTION METHODS TO DISTINGUISH BETWEEN THE FIRST AND THE SECOND HEART SOUNDS
SN - 978-989-8425-89-8
AU - Moukadem A.
AU - Dieterlen A.
AU - Brandt C.
PY - 2012
SP - 346
EP - 350
DO - 10.5220/0003743703460350