Web projektu DAR

Research Centre
Data - Algorithms - Decision Making

Established in 2005 under support of MŠMT ČR (project 1M0572)

Publications

Performance analysis of the FastICA algorithm and Cramér-Rao bounds for linear Independent component analysis

Typ:

Jornal article

Authors:

Tichavský P., Koldovský Z., Oja E.

Name of journal:

IEEE Transactions on Signal Processing

Volume:

Year:

2006

Number:

Pages:

1189-1203

ISSN:

1053-587X

Contact:

Ing. Petr Tichavský, CSc. (ÚTIA - Oddělení stochastické informatiky)

Keywords:

blind source separation, independent component analysis ICA

attachment1:

13fastica [file]

Anotation:

This paper derives analytic closed form expressions that characterize the performance of the algorithm FastICA, which is one of the most successful algorithms for independent component analysis. Second, the Cramer-Rao lower bound for linear ICA is derived as an algorithm independent limit of the achievable separation quality. The FastICA algorithm is shown to approach this limit in certain scenarios. Extensive computer simulations supporting the theoretical findings are included.