Time-Scale-Based Segmentation for Degraded PCG Signals Using NMF

  • F. Sattar
  • F. Jin
  • A. Moukadem
  • C. Brandt
  • A. Dieterlen
Chapter
Part of the Signals and Communication Technology book series (SCT)

Abstract

This article deals with the challenging problem of segmenting narrowly spaced cardiac events (S1 and S2) in noisy phonocardiogram (PCG) signals by using a novel application of NMF based on time-scale approach. A novel energy-based method is proposed for the segmentation of noisy PCG signals in order to detect cardiac events, which could be closely spaced and separated by noisy gaps. The method is based on time-scale transform as well as nonnegative matrix factorization (NMF) and the segmentation problem is formulated using the paradigm of binary statistical hypothesis testing. The energy of the Morlet wavelet transform and NMF output is employed as a test statistics for segmentation where the number of scales are selected based on the preferences calculated along the time-scales. The simulation results using real recorded noisy PCG data that provide promising performance with high overall accuracy on the segmentation of narrowly separated, high noisy signals by our proposed method.

Keywords

Segmentation PCG signals Cardiac events NMF Wavelet transform 

References

  1. 1.
    A. Moukadem, A. Dieterlen, N. Hueber, C. Brandt, Comparative study of heart sounds localization, bioelectronics, biomedical and bio-inspired systems. SPIE N 8068A-27, Prague (2011)Google Scholar
  2. 2.
    C.S. Lima, A. Tavares, J. Correia, M.J. Cardoso, D. Barbosa, in New Developments in Biomedical Engineering, ed. by Domenico Campolo, ISBN 978-953-7619-57-2 (InTech Publisher), p. 37–72 (2010)Google Scholar
  3. 3.
    H. Liang, S. Lukkarinen, I. Hartimo, Heart Sound Segmentation Algorithm Based on Heart Sound Envelogram (Helsinki University of Technology, Espoo, 1997)CrossRefGoogle Scholar
  4. 4.
    C. Ahlström, Nonlinear Phonocardiographic Signal Processing. Institutionen för Medicinsk Teknik, 2008Google Scholar
  5. 5.
    H. Naseri, M.R. Homaeinezhad, H. Pourkhajeh, Noise/spike detection in phonocardiogram signal as a cyclic random process with non-stationary period interval. Comput. Biol. Med. 43, 1205–1213 (2013)CrossRefGoogle Scholar
  6. 6.
    S. Ari, K. Hembram, G. Saha, Detection of cardiac abnormality from PCG signal using LMS based least square SVM classifier. Expert Syst. Appl. 37(12), 8019–8026 (2010)CrossRefGoogle Scholar
  7. 7.
    H. Hadi, M. Mashor, M. Suboh, M. Mohamed, Classification of heart sound based on S-transform and neural networks, in International Conference on Information Science, Signal Processing and Their Applications (2010)Google Scholar
  8. 8.
    D.D. Lee, H.S. Seung, Algorithms for non-negative matrix factorization. Adv. Neural Inf. Proc. Syst. 13, 556–562 (2001)Google Scholar
  9. 9.
    Y.-X. Wang, Y.-J. Zhang, Nonnegative matrix factorization: a comprehensive review. IEEE Trans. Knowl. Data Eng. 25(6), 1336–1353 (2013)CrossRefGoogle Scholar
  10. 10.
    A.K. Kattepur, F. Jin, F. Sattar, Single channel source separation for convolutive mixture with application to respiratory sounds, in IEEE-EMBS Conference on Bio-inspired Systems and Signal Processing (BIOSIGNALS) (2010)Google Scholar
  11. 11.
    B. Ghoraani, S. Krishnan, Time-frequency matrix feature extraction and classification of environmental audio signals. IEEE Trans. Audio Speech Lang. Process. 19(7), 2197–2209 (2011)CrossRefGoogle Scholar
  12. 12.
    M. Kim, J. Yoo, K. Kang, S. Choi, Nonnegative matrix partial co-factorization for spectral and temporal drum source separation. IEEE J. Sel. Top. Signal Process. 5(6), 1192–1204 (2011)CrossRefGoogle Scholar
  13. 13.
    G. Shah, P. Koch, C.B. Papadias, On the blind recovery of cardiac and respiratory sounds. IEEE J. Biomed. Health Inform. 19(1), 151–157 (2015)CrossRefGoogle Scholar
  14. 14.
    P.O. Hoyer, Non-negative sparse coding, in IEEE Workshop Neural Networks for Signal Process (2002), pp. 557–565Google Scholar
  15. 15.
    J. Eggert, E. Kmrner, Sparse coding and NMF, in IEEE Conference on Neural Networks, vol. 4 (2004), pp. 2529–2533Google Scholar
  16. 16.
    C.J. Lin, Projected gradient methods for non negative matrix factorization. Neural Comput. 19(10), 2756–2779 (2007)MATHMathSciNetCrossRefGoogle Scholar
  17. 17.
    D. Kim, S. Sra, and I.S. Dhillon, Fast newton-type methods for the least squares non negative matrix approximation problem, in SIAM Conference on Data Mining (2007)Google Scholar
  18. 18.
    C. Torrence, G.P. Compo, A practical guide to wavelet analysis. Bull. Am. Meterol. Soc. 79(1), 61–76 (1998)CrossRefGoogle Scholar
  19. 19.
    L.L. Scharf, Statistical Signal Processing: Detection Estimation and Time Series Analysis (Addison-Wesley, Boston, 1991)MATHGoogle Scholar
  20. 20.
    S.M. Kay, Fundamentals of Statistical Signal Processing: Detection Theory (Prentice Hall, Englewood Cliffs, 1998)Google Scholar
  21. 21.
    N. Lee, Q. Huynh, S. Schwartz, New methods of linear time-frequency analysis for signal detection, in IEEE Proceedings on Time-Frequency and Time-Scale Analysis, Paris, June 1996, pp. 13–16Google Scholar
  22. 22.
    A.-J. Van der Veen, E.D.F. Deprettere, A.L. Swindlehurst, Sub-space based signal analysis using singular value decomposition. Proc. IEEE 81(9), 1277–1307 (1993)CrossRefGoogle Scholar
  23. 23.
    B. Huang, A. Kunoth, An optimization based empirical mode decomposition scheme. J. Comput. Appl. Math. 240(2013), 174–183 (2013)MATHMathSciNetCrossRefGoogle Scholar
  24. 24.
    A. Moukadem, A. Dieterlen, N. Hueber, C. Brandt, A robust heart sounds segmentation module based on S-transform. Biomed. Signal Process. Control 8, 273–281 (2013)CrossRefGoogle Scholar
  25. 25.
    S. Ventosa, C. Simon, M. Schimmel, J. Danobeitia, A. Manuel, The S-transform from a wavelet point of view. IEEE Trans. Signal Process. 56(7), 2771–2780 (2008)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2016

Authors and Affiliations

  • F. Sattar
    • 1
  • F. Jin
    • 2
  • A. Moukadem
    • 3
  • C. Brandt
    • 3
  • A. Dieterlen
    • 3
  1. 1.Department of Electrical and Computer EngineeringUniversity of WaterlooWaterlooCanada
  2. 2.Department of Electrical and Computer EngineeringRyerson UniversityTorontoCanada
  3. 3.MIPS LaboratoryUniversity of Haute AlsaceMulhouse CedexFrance

Personalised recommendations