ICA and biomedical applications - Université de Rennes Accéder directement au contenu
Chapitre D'ouvrage Année : 2010

ICA and biomedical applications

Laurent Albera
Lucas C Parra
  • Fonction : Auteur
Ahmad Karfoul

Résumé

In this chapter we focus on the use of Independent Component Analysis (ICA) in biomedical systems. Several studies dealing with ICA-based biomedical systems have been reported during the last decade. Nevertheless, most of these studies have only explored a limited number of ICA methods, namely SOBI [7], FastICA [39] and InfoMax [53]. In addition, the performance of ICA algorithms for arbitrary electro-physiological sources is still almost unknown. This prevents us from choosing the best method for a given application, and may limit the role of these methods in biomedical systems. To overcome these limitations, the purpose of our study is first to show the interest of ICA in biomedical applications such as the analysis of human electrophysiological signals. Next, we aim at studying twelve of the most widespread ICA techniques in the signal processing community and identify those that are most appropriate for biomedical signals.
Fichier non déposé

Dates et versions

hal-00909006 , version 1 (25-11-2013)

Identifiants

  • HAL Id : hal-00909006 , version 1

Citer

Laurent Albera, Pierre Comon, Lucas C Parra, Ahmad Karfoul, Amar Kachenoura, et al.. ICA and biomedical applications. P. Comon ; C. Jutte. Handbook of Blind Source Separation, Independent Component Analysis and Applications, Academic Press, 737-78 (chap.18), 2010, 978-2-296-12827-9. ⟨hal-00909006⟩
176 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More