Multilinear algebra for independent component analysis

Details Multilinear algebra for independent component analysis Multilinear algebra for independent component analysis

Nov 1999

adsabs.harvard.edu/cgi-bin/nph-data_query?bibcode=1999spie.3807..258m&link_type=abstract

Proc. SPIE Vol. 3807, p. 258-266, Advanced Signal Processing Algorithms, Architectures, and Implementations IX, Franklin T. Luk;

Computer Science

Scientific paper

It is shown how some simple multilinear transformations may be used to generate an alternative, and potentially faster, version of the BLISS algorithm for blind signal separation. The BLISS algorithm performs an independent component analysis of the type proposed by Comon but uses a different method for estimating the pairwise rotation angles. It has been applied to a wide range of communication signals and proved extremely successful in practice. The reformulated version of BLISS requires less arithmetic operations provided the number of signals to be separated is fairly small (approximately 3 to 5) as found in a range of important communication scenarios.

Affiliated with

Also associated with

No associations

Rating

Multilinear algebra for independent component analysis does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Multilinear algebra for independent component analysis, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Multilinear algebra for independent component analysis will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-1513858