Presentation 2011-11-24
Estimation of fetal vector electrocardiography through blind source separation
Yuji NABESHIMA, Yoshitaka KIMURA, Takuya ITO, Naoaki SATO, Akihiro KARASHIMA, Norihiro KATAYAMA, Mitsuyuki NAKAO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Electrocardiograph (ECG) could be modeled as a rotating vector (heartvector) representing spatio-temporal electrical activity of myocardial muscle to some precision. In this case, ECG is a projection of the heart vector on some subspace spanned by recording electrodes. Independent component analysis (ICA) has recently been employed to extract the fetal ECG from maternal abdominal composite signals. When ICA is applied to a vector source, it should separate the vector source into mutually uncorrelated signals up to an order of the spatial dimension. However, due to non-stationary factors including movements of maternal abdominal surface and fetus and contamination of noise and electromyogram, only a single component might be extracted. Here, we propose a method for re-constructing vector ECG even in this situation. Through simulations and application to actual data, the validity of our method is examined. It is suggested that our method could detect alternation of ECG waveform caused by pathological factors.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Fetus / Electrocardiogram / Blind source separation
Paper # MBE2011-59
Date of Issue

Conference Information
Committee MBE
Conference Date 2011/11/17(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To ME and Bio Cybernetics (MBE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Estimation of fetal vector electrocardiography through blind source separation
Sub Title (in English)
Keyword(1) Fetus
Keyword(2) Electrocardiogram
Keyword(3) Blind source separation
1st Author's Name Yuji NABESHIMA
1st Author's Affiliation Graduate School of information Sciences, Tohoku University()
2nd Author's Name Yoshitaka KIMURA
2nd Author's Affiliation Graduate School of information Sciences, Tohoku University
3rd Author's Name Takuya ITO
3rd Author's Affiliation Graduate School of information Sciences, Tohoku University
4th Author's Name Naoaki SATO
4th Author's Affiliation Graduate School of information Sciences, Tohoku University
5th Author's Name Akihiro KARASHIMA
5th Author's Affiliation Graduate School of information Sciences, Tohoku University
6th Author's Name Norihiro KATAYAMA
6th Author's Affiliation Graduate School of information Sciences, Tohoku University
7th Author's Name Mitsuyuki NAKAO
7th Author's Affiliation Graduate School of information Sciences, Tohoku University
Date 2011-11-24
Paper # MBE2011-59
Volume (vol) vol.111
Number (no) 314
Page pp.pp.-
#Pages 5
Date of Issue