Improving independent component analysis performances by variable selection - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2003

Improving independent component analysis performances by variable selection

Résumé

Blind source separation (BSS) consists in recovering unobserved signals from observed mixtures of them. In most cases the whole set of mixtures is used for the separation, possibly after a dimension reduction by PCA. This paper aims to show that in many applications the quality of the separation can be improved by first selecting a subset of some mixtures among the available ones, possibly by an information content criterion, and performing PCA and BSS afterwards. The benefit of this procedure is shown on simulated electrocardiographic data by extracting the fetal electrocardiogram signal from mixtures recorded on the abdomen of a pregnant woman.
Fichier non déposé

Dates et versions

hal-00232884 , version 1 (03-02-2008)

Identifiants

Citer

F. Vrins, J.L. Lee, Michel Verleysen, Vincent Vigneron, Christian Jutten. Improving independent component analysis performances by variable selection. IEEE International Workshop on Neural Networks for Signal Processing (NNSP 2003), Sep 2003, Toulouse, France. pp.359-368, ⟨10.1109/NNSP.2003.1318035⟩. ⟨hal-00232884⟩
53 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More