• DocumentCode
    3068670
  • Title

    Robustness of the blind source separation with reference against uncertainties of the reference signals

  • Author

    Netabayashi, Tomoyuki ; Kimura, Yoshitaka ; Chida, Shinichi ; Ito, Takuro ; Ohwada, Kazunari ; Katayama, Norihiro ; Okamura, Kunihiro ; Nakao, Mitsuyuki

  • Author_Institution
    Graduate School of Information Sciences, Tohoku University, Sendai 980-8579, Japan
  • fYear
    2008
  • fDate
    20-25 Aug. 2008
  • Firstpage
    1875
  • Lastpage
    1878
  • Abstract
    The fetal electrocardiogram (ECG) could provide clinical information concerning physiological conditions of the fetus. In order to extract fetal ECG, we proposed the novel algorithm, the blind source separation with reference (BSSR), which successfully extracts a complete waveform of QRS complex and avoids uncertainty in the order of the extracted signals. In the BSSR, the reference signal is supposed to be generated from the ultrasonic Doppler signal. Thus generated reference is expected to suffer from uncertainties in waveform and occurrence timing. Based on simulations, the BSSR is shown to have robustness against the uncertainties of reference signals. In addition, it is shown how the robustness depends on the order of power of correlation function between the reference and extracted signals, which composes a performance function of the BSSR.
  • Keywords
    Blind source separation; Clinical diagnosis; Data mining; Educational institutions; Electrocardiography; Fetus; Robustness; Signal generators; Timing; Uncertainty; Algorithms; Biomedical Engineering; Computer Simulation; Electrocardiography; Electrophysiological Phenomena; Female; Fetal Heart; Humans; Models, Cardiovascular; Pregnancy; Signal Processing, Computer-Assisted;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Engineering in Medicine and Biology Society, 2008. EMBS 2008. 30th Annual International Conference of the IEEE
  • Conference_Location
    Vancouver, BC
  • ISSN
    1557-170X
  • Print_ISBN
    978-1-4244-1814-5
  • Electronic_ISBN
    1557-170X
  • Type

    conf

  • DOI
    10.1109/IEMBS.2008.4649551
  • Filename
    4649551