• DocumentCode
    179173
  • Title

    Fetal heart rate detection using VPW-FRI

  • Author

    Nair, Amrish ; Marziliano, Pina

  • Author_Institution
    Sch. of Electr. & Electron. Eng., Nanyang Technol. Univ., Singapore, Singapore
  • fYear
    2014
  • fDate
    4-9 May 2014
  • Firstpage
    4438
  • Lastpage
    4442
  • Abstract
    Fetal Electrocardiograms (fECG) are an inexpensive and noninvasive method to determine the heart rate (HR) of the fetus. Large variations in the fetal HR is a good indicator that the fetus is in distress thus allowing for clinical intervention. Although advances have been made in the field of fetal HR detection, more can be done to improve accuracy and efficiency. The Variable Pulse Width - Finite Rate of Innovation (VPW-FRI) method is a suitable method given it deals with pulse parameters such as location, width and amplitude. This allows it to automatically segment and identify the foetal QRS complexes and R peak locations from compressed samples which in turn would yield the fetal HR. Our method, which includes model based denoising and multichannel capability, is comparable to other methods involving machine learning, wavelets and ICA.
  • Keywords
    electrocardiography; independent component analysis; learning (artificial intelligence); medical signal detection; obstetrics; signal denoising; wavelet transforms; ICA; R peak locations; VPW-FRI; Variable Pulse Width-Finite Rate of Innovation method; amplitude; clinical intervention; compressed samples which; distress; fECG; fetal electrocardiogram; fetal heart rate detection; fetus; foetal QRS complexes; machine learning; model based denoising; multichannel capability; noninvasive method; pulse parameters; wavelets; width; Accuracy; Electrocardiography; Fetal heart rate; Noise reduction; Speech; Technological innovation; ECG; Fetal Heart Rate; Finite Rate of Innovation;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on
  • Conference_Location
    Florence
  • Type

    conf

  • DOI
    10.1109/ICASSP.2014.6854441
  • Filename
    6854441