DocumentCode
1033748
Title
Blind Identification of Underdetermined Mixtures by Simultaneous Matrix Diagonalization
Author
De Lathauwer, Lieven ; Castaing, Joséphine
Author_Institution
Katholieke Univ. Leuven, Leuven
Volume
56
Issue
3
fYear
2008
fDate
3/1/2008 12:00:00 AM
Firstpage
1096
Lastpage
1105
Abstract
In this paper, we study simultaneous matrix diagonalization-based techniques for the estimation of the mixing matrix in underdetermined independent component analysis (ICA). This includes a generalization to underdetermined mixtures of the well-known SOBI algorithm. The problem is reformulated in terms of the parallel factor decomposition (PARAFAC) of a higher-order tensor. We present conditions under which the mixing matrix is unique and discuss several algorithms for its computation.
Keywords
blind source separation; identification; independent component analysis; matrix decomposition; tensors; SOBI algorithm; blind identification; higher-order tensor; independent component analysis; mixing matrix estimation; parallel factor decomposition; simultaneous matrix diagonalization; underdetermined mixtures; Canonical decomposition; higher order tensor; independent component analysis (ICA); parallel factor (PARAFAC) analysis; simultaneous diagonalization; underdetermined mixture;
fLanguage
English
Journal_Title
Signal Processing, IEEE Transactions on
Publisher
ieee
ISSN
1053-587X
Type
jour
DOI
10.1109/TSP.2007.908929
Filename
4430007
Link To Document