Ústav teorie informace a automatizace

Jste zde

Bibliografie

Conference Paper (international conference)

Orthogonally-Constrained Extraction of Independent Non-Gaussian Component from Non-Gaussian Background Without ICA

Koldovský Z., Tichavský Petr, Ono N.

: Latent Variable Analysis and Signal Separation, p. 161-170 , Eds: Deville Yannick, Gannot Sharon, Mason Russell, Plumbley Mark D., Ward Dominic

: Latent Variable Analysis and Signal Separation, (Guilford, GB, 20180702)

: GA17-00902S, GA ČR

: Independent Component Analysis, Blind source separation, blind source extraction

: 10.1007/978-3-319-93764-9_16

: http://library.utia.cas.cz/separaty/2018/SI/tichavsky-0492879.pdf

(eng): We propose a new algorithm for Independent Component Extraction that extracts one non-Gaussian component and is capable to exploit the non-Gaussianity of background signals without decomposing them into independent components. The algorithm is suitable for situations when the signal to be extracted is determined through initialization, it shows an extra stable convergence when the target component is dominant. In simulations, the proposed method is compared with Natural Gradient and One-unit FastICA, and it yields improved results in terms of the Signal-to-Interference ratio and the number of successful extractions.

: BB

: 10103

07.01.2019 - 08:39