In this work we introduce a new ICA algorithm, designed to take available prior information on the sources into account. This prior information is included in the form of a 'weak' constraint and is exploited simultaneously with independence in order to separate the sources. This new algorithm outperforms classical ICA algorithms in the case of low SNR. Furthermore, inclusion of additional information about the sources may help enforcing the ordering of the extracted components according to their significance.

Optimizing ICA using generic knowledge of the sources / VALENTE, Giancarlo; De Martino, F.; Balsi, M.; Formisano, E.. - STAMPA. - II:(2005), pp. 27-34. (Intervento presentato al convegno 1st International Workshop on Biosignal Processing and Classification (BPC 2005) tenutosi a Lausanne; Switzerland nel 14-17/9/2005) [10.1109/RME.2005.1542974].

Optimizing ICA using generic knowledge of the sources

VALENTE, Giancarlo;F. De Martino;M. Balsi;
2005

Abstract

In this work we introduce a new ICA algorithm, designed to take available prior information on the sources into account. This prior information is included in the form of a 'weak' constraint and is exploited simultaneously with independence in order to separate the sources. This new algorithm outperforms classical ICA algorithms in the case of low SNR. Furthermore, inclusion of additional information about the sources may help enforcing the ordering of the extracted components according to their significance.
2005
1st International Workshop on Biosignal Processing and Classification (BPC 2005)
Extracted components; Generic knowledge;
Pubblicazione in atti di convegno::04b Atto di convegno in volume
Optimizing ICA using generic knowledge of the sources / VALENTE, Giancarlo; De Martino, F.; Balsi, M.; Formisano, E.. - STAMPA. - II:(2005), pp. 27-34. (Intervento presentato al convegno 1st International Workshop on Biosignal Processing and Classification (BPC 2005) tenutosi a Lausanne; Switzerland nel 14-17/9/2005) [10.1109/RME.2005.1542974].
File allegati a 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.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/417362
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
social impact