Adaptive Blind Separation of Instantaneous Linear Mixtures of Independent Sources

0473144 - ÚTIA 2018 RIV CH eng C - Conference Paper (international conference)
Šembera, Ondřej - Tichavský, Petr - Koldovský, Z.
Adaptive Blind Separation of Instantaneous Linear Mixtures of Independent Sources.
Latent Variable Analysis and Signal Separation, 13th International Conference, LVA/ICA 2017. Cham: Springer, 2017 - (Tichavský, P.; Babaie-Zadeh, M.; Michel, O.; Thirion-Moreau, N.), s. 172-181, č. článku 17. Lecture Notes in Computer Science, 10169. ISBN 978-3-319-53546-3. ISSN 0302-9743. E-ISSN 1611-3349.
[Latent Variable Analysis and Signal Separation. Grenoble (FR), 21.02.2017-23.02.2017]
R&D Projects: GA ČR GA17-00902S
Institutional support: RVO:67985556
Keywords : blind source separation * independent component analysis * autoregressive processes
OECD category: Statistics and probability
http://library.utia.cas.cz/separaty/2017/SI/tichavsky-0473144.pdf

In many applications, there is a need to blindly separate independent sources from their linear instantaneous mixtures while the mixing matrix or source properties are slowly or abruptly changing in time. The easiest way to separate the data is to consider off-line estimation of the model parameters repeatedly in time shifting window. Another popular method is the stochastic natural gradient algorithm, which relies on non-Gaussianity of the separated signals and is adaptive by its nature. In this paper, we propose an adaptive version of two blind source separation algorithms which exploit non-stationarity of the original signals. The results indicate that the proposed algorithms slightly outperform the natural gradient in the trade-off between the algorithm’s ability to quickly adapt to changes in the mixing matrix and the variance of the estimate when the mixing is stationary.
Permanent Link: http://hdl.handle.net/11104/0271358