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 babys heart from the mothers
Fetal Magnetocardiographic Signals Extracted by Signal Subspace Blind Source Separation.
Salustri C;
2005
Abstract
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 babys heart from the mothersFile in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.