Second-Order Blind Identification of Underdetermined Mixtures

In this paper we show that the underdetermined ICA problem can be solved using a set of spatial covariance matrices, in case the sources have sufficiently different temporal autocovariance functions. The result is based on a link with the decomposition of higher-order tensors in rank-one terms. We discuss two algorithms and present theoretical bounds on the number of sources that can be allowed.

[1]  J. Chang,et al.  Analysis of individual differences in multidimensional scaling via an n-way generalization of “Eckart-Young” decomposition , 1970 .

[2]  A. Stegeman,et al.  On Kruskal's uniqueness condition for the Candecomp/Parafac decomposition , 2007 .

[3]  R. Cattell.  “Parallel proportional profiles” and other principles for determining the choice of factors by rotation , 1944 .

[4]  Barak A. Pearlmutter,et al.  Blind Source Separation by Sparse Decomposition in a Signal Dictionary , 2001, Neural Computation.

[5]  Richard A. Harshman,et al.  Foundations of the PARAFAC procedure: Models and conditions for an "explanatory" multi-model factor analysis , 1970 .

[6]  Arogyaswami Paulraj,et al.  An analytical constant modulus algorithm , 1996, IEEE Trans. Signal Process..

[7]  Arie Yeredor,et al.  Non-orthogonal joint diagonalization in the least-squares sense with application in blind source separation , 2002, IEEE Trans. Signal Process..

[8]  J. Kruskal.  Three-way arrays: rank and uniqueness of trilinear decompositions, with application to arithmetic complexity and statistics , 1977 .

[9]  Lieven De Lathauwer,et al.  A Link between the Canonical Decomposition in Multilinear Algebra and Simultaneous Matrix Diagonalization , 2006, SIAM J. Matrix Anal. Appl..

[10]  Joos Vandewalle,et al.  Computation of the Canonical Decomposition by Means of a Simultaneous Generalized Schur Decomposition , 2005, SIAM J. Matrix Anal. Appl..

[11]  Pierre Comon,et al.  Blind identification and source separation in 2×3 under-determined mixtures , 2004, IEEE Trans. Signal Process..

[12]  L. Lathauwer,et al.  Sufficient conditions for uniqueness in Candecomp/Parafac and Indscal with random component matrices , 2006, Psychometrika.

[13]  Terrence J. Sejnowski,et al.  Learning Overcomplete Representations , 2000, Neural Computation.

[14]  B. De Moor,et al.  ICA algorithms for 3 sources and 2 sensors , 1999, Proceedings of the IEEE Signal Processing Workshop on Higher-Order Statistics. SPW-HOS '99.

[15]  Michael Zibulevsky,et al.  Underdetermined blind source separation using sparse representations , 2001, Signal Process..

[16]  Anisse Taleb,et al.  An algorithm for the blind identification of N independent signals with 2 sensors , 2001, Proceedings of the Sixth International Symposium on Signal Processing and its Applications (Cat.No.01EX467).

[17]  Joos Vandewalle,et al.  An algebraic ICA algorithm for 3 sources and 2 sensors , 2000, 2000 10th European Signal Processing Conference.

[18]  Jean-Francois Cardoso,et al.  Super-symmetric decomposition of the fourth-order cumulant tensor. Blind identification of more sources than sensors , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[19]  Eric Moulines,et al.  A blind source separation technique using second-order statistics , 1997, IEEE Trans. Signal Process..

[20]  Pierre Comon,et al.  Enhanced Line Search: A Novel Method to Accelerate PARAFAC , 2008, SIAM J. Matrix Anal. Appl..

[21]  Pierre Comon,et al.  Decomposition of quantics in sums of powers of linear forms , 1996, Signal Process..