Sparse ICA via cluster-wise PCA

Zadeh Massouad Babaie 1 Christian Jutten 2 Ali Mansour 3
Lab-STICC - Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance
Abstract : In this paper, it is shown that independent component analysis (ICA) of sparse signals (sparse ICA) can be seen as a cluster-wise principal component analysis (PCA). Consequently, Sparse ICA may be done by a combination of a clustering algorithm and PCA. For the clustering part, we use, in this paper, an algorithm inspired from K-means. The final algorithm is easy to implement for any number of sources. Experimental results points out the good performance of the method, whose the main restriction is to request an exponential growing of the sample number as the number of sources increases. Keywords: Independent Component Analysis 5ICA), Blind Source Separation (BSS), Sparse ICA, Principal Component Analysis (PCA).
Complete list of metadatas
Contributor : Ali Mansour <>
Submitted on : Tuesday, March 19, 2013 - 6:58:36 PM
Last modification on : Friday, September 6, 2019 - 3:00:06 PM


  • HAL Id : hal-00802463, version 1


Zadeh Massouad Babaie, Christian Jutten, Ali Mansour. Sparse ICA via cluster-wise PCA. Neurocomputing, Elsevier, 2006, 69 (13-15), pp.1458-1466. ⟨hal-00802463⟩



Record views