Independent component analysis and (simultaneous) third-order tensor diagonalization

IEEE Transactions on Signal Processing

Volumn 49, Issue 10, 2001, Pages 2262-2271

  De Lathauwer, Lieven ^b,c   De Moor, Bart ^a,c   Vandewalle, Joos ^a,c  

^a IEEE   (Belgium)

^b Centre national de la recherche scientifique   (France)

^c UNIVERSITY OF LEUVEN   (Belgium)

Author keywords

Eigenvalue decomposition; Higher order statistics; Independent component analysis; Multilinear algebra; Principal component analysis

Indexed keywords

OPTIMAL DIAGONALIZATION;

ALGORITHMS; APPROXIMATION THEORY; EIGENVALUES AND EIGENFUNCTIONS; MATRIX ALGEBRA; PRINCIPAL COMPONENT ANALYSIS; STATISTICS; TENSORS; THEOREM PROVING;

INDEPENDENT COMPONENT ANALYSIS;

EID: 0035485594     PISSN: 1053587X     EISSN: None     Source Type: Journal    
DOI: 10.1109/78.950782     Document Type: Article

References (15)

1. Blind beamforming for nongaussian signals
2. On the performance of orthogonal source separation algorithms
3. The invariant approach to source separation
4. High-order contrasts for independent component analysis
5. Tensor diagonalization, a useful tool in signal processing
6. Independent component analysis. A new concept?
7. Higher-order power method - Application in independent component analysis
8. Blind source separation by simultaneous third-order tensor diagonalization
9. A residual bound for the mixing matrix in ICA
10. Criteria for complex sources separation
11. Nonsymmetrical contrasts for sources separation
12. A generalization of joint-diagonalization criteria for source separation
13. A generalized ICA algorithm