Journal of Medical Systems

, Volume 32, Issue 2, pp 123–135 | Cite as

Generalized Blind Delayed Source Separation Model for Online Non-invasive Twin-fetal Sound Separation: A Phantom Study

Original Paper


The fetal phonocardiogram, which is the acoustic recording of mechanical activity of the fetal heart, facilitates the measurement of the instantaneous fetal heart rate, beat-to-beat differences and duration of systolic and diastolic phases. These measures are sensitive indicators of cardiac function, reflecting fetal well-being. This paper provides an algorithm to non-invasively estimate the phonocardiogram of an individual fetus in a multiple fetus pregnancy. A mixture of fetal phonocardiograms is modeled by a generalized pure delayed mixing model. Mutual independence of fetal phonocardiograms is assumed to apply blind source separation based techniques to extract the fetal phonocardiograms from their mixtures. The performance of the algorithm is verified through simulation results and on experimental data obtained from a phantom that is used to simulate a twin pregnancy.


Multiple pregnancy Fetal heart sound Blind delayed source separation Clinical diagnosis 


  1. 1.
    Martin, J., Births: final data for 2000. Natl. Vital Stat. Rep. 50(5), 2002.Google Scholar
  2. 2.
    Lathauwer, L., Moor, B., and Vandewalle, J., Fetal electrocardiogram extraction by blind source subspace separation. IEEE Trans. Biomed. Eng 47:5567–572, 2000.CrossRefGoogle Scholar
  3. 3.
    Liang, H., Lukkarinen, S., and Hartimo, I., Heart sound segmentation algorithm based on heart sound envelogram. Comput. Cardiol., pp. 105–108, 1997.Google Scholar
  4. 4.
    Greenfield, M., Hearing the fetal heartbeat. Dr. Spock Website, available at:,1510,9851,00.html (last accessed Feb. 2006), 2001.
  5. 5.
    McDonnell, E., and Dripps, J. H., Processing and analysis of fetal phonocardiograms. Proc. Annu. Int. Conf. IEEE Eng 1:61–62, 1989.Google Scholar
  6. 6.
    Ibrahimy, M. I., Ahmed, F., Ali, M. A. M., and Zahedi, E., Real-time signal processing for fetal heart rate monitoring. IEEE Trans. Biomed. Eng 50:2258–261, 2003.CrossRefGoogle Scholar
  7. 7.
    Burel, G., Blind separation of sources: a nonlinear neural algorithm. Neural Netw 5:6937–947, 1992.CrossRefGoogle Scholar
  8. 8.
    Jutten, C., and Herault, J., Blind separation of sources, part 1: an adaptive algorithm based on neuromimetic architecture. Signal Process 24:11–10, 1991.MATHCrossRefGoogle Scholar
  9. 9.
    Platt, J. C., and Faggin, F., Networks for separation of sources that are superimposed and delayed. In: Moody, J., Hanson, S., and Lippman, R. (Eds.), Advances in Neural Information Processing Systems 4Palo Alto: Morgan-Kaufmann, 730–737, 1992.Google Scholar
  10. 10.
    Delfosse, N., and Loubaton, P., Adaptive separation of independent sources: a deflation approach. In: Proc. ICASSP, pp. 41–44, Adelaide, Australia, 1994.Google Scholar
  11. 11.
    Karhunen, J., Wang, L., and Vigario, R., Nonlinear PCA type approaches for source separation and independent component analysis. In: Proc. ICNN, Perth, Western Australia, 1995.Google Scholar
  12. 12.
    Cardoso, J. F., Belouchrani, A., and Laheld, B., A new composite criterion for adaptive and iterative blind source separation. In: Proc. ICASSP, pp. 273–276, Adelaide, Australia, 1994.Google Scholar
  13. 13.
    Comon, P., Independent component analysis, a new concept? Signal Process 36:3287–314, 1994.MATHCrossRefGoogle Scholar
  14. 14.
    Kam, A., and Cohen, A., Separation of twins fetal ECG by means of blind source separation. Electrical and electronic engineers in Israel. The 21st IEEE Convention, pp. 342–345, 2000.Google Scholar
  15. 15.
    Torkkola, K., Blind separation of delayed sources based on information maximization. In: Proc. IEEE ICASSP, pp. 3509–3513, 1996.Google Scholar
  16. 16.
    Kovacs, F., Torok, M., and Habermajer, I., A rule-based phonocardiographic method for long-term fetal heart rate monitoring. IEEE Trans. Biomed. Eng 47:1124–130, 2000.CrossRefGoogle Scholar
  17. 17.
    Bell, A., and Sejnowski, T., An information maximization approach to blind separation and blind deconvolution. Neural Comput 7:61004–1034, 1995.CrossRefGoogle Scholar
  18. 18.
    Nigam, V., and Priemer, R., Blind separation of mixtures of delayed sources. In: Electronic Proceedings of CITSA, Orlando, FL, 2004.Google Scholar
  19. 19.
    Emile, B., Comon, P., and Leroux, J., Estimation of time delays with fewer sensors than sources. IEEE Trans. Signal Process 46:72012–2015, 1998.CrossRefGoogle Scholar
  20. 20., Product information cardiac auscultation of heart murmurs. Available at: (last accessed Feb. 2006)
  21. 21.
    Amari, S., Cichocki, A., and Yang, H. H., A new learning algorithm for blind signal separation. Advances in neural information processing systems. Vol. 8. Cambridge, MA: MIT, 752–763, 1996.Google Scholar
  22. 22.
    Messer, S., and Abbott, D., Optimal wavelet denoising for phonocardiograms. Microelectron. J 32:12931–941, 2001.CrossRefGoogle Scholar
  23. 23.
    Donoho, D. L., De-noising by soft thresholding. IEEE Trans. Inf. Theory 41:3613–627, 1995.MATHCrossRefMathSciNetGoogle Scholar
  24. 24.
    Nigam, V., and Priemer, R., A snore extraction method from mixed sound for a mobile snore recorder. J. Med. Syst. 30:91–99.Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2007

Authors and Affiliations

  1. 1.Ikoa, IncMenlo ParkUSA
  2. 2.Electrical and Computer Engineering DepartmentUniversity of Illinois at ChicagoChicagoUSA

Personalised recommendations