Fetal Magnetocardiographic Signals Extracted by ‘Signal Subspace’ Blind Source Separation.

In this paper, we apply independent component analysis to fetal magnetocardiographic data. In particular, we propose an extension of the “cumulant-based iterative inversion” algorithm to include a two-step “signal subspace” subdivision, which allows the user to control the number of components to be estimated by analyzing the eigenvalues distribution in an interactive way. Our results show that this method is a powerful means not only for the extraction of the cardiac signals from the background noise but also for a sharp separation of the baby’s heart from the mother’s

Tipo Pubblicazione: 
Articolo
Author or Creator: 
Salustri
C.
Barbati
G.
Porcaro
Publisher: 
Institute of Electrical and Electronics Engineers,, New York, N.Y. , Stati Uniti d'America
Source: 
IEEE transactions on biomedical engineering (Print) 52 (2005): 1140–1142.
info:cnr-pdr/source/autori:Salustri, C., Barbati, G. and Porcaro , C./titolo:Fetal Magnetocardiographic Signals Extracted by ‘Signal Subspace’ Blind Source Separation./doi:/rivista:IEEE transactions on biomedical engineering (Print)/anno:2005/pagina_da:11
Date: 
2005
Resource Identifier: 
http://www.cnr.it/prodotto/i/46734
http://tiny.cc/uzkezw
ISTC Author: 
Ritratto di carlo.salustri
Real name: