Sparsity in Bayesian Blind Source Separation and Deconvolution
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985556%3A_____%2F13%3A00396464" target="_blank" >RIV/67985556:_____/13:00396464 - isvavai.cz</a>
Result on the web
<a href="http://dx.doi.org/10.1007/978-3-642-40991-2_35" target="_blank" >http://dx.doi.org/10.1007/978-3-642-40991-2_35</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-642-40991-2_35" target="_blank" >10.1007/978-3-642-40991-2_35</a>
Alternative languages
Result language
angličtina
Original language name
Sparsity in Bayesian Blind Source Separation and Deconvolution
Original language description
Blind source separation algorithms are based on various separation criteria. Differences in convolution kernels of the sources are common assumptions in audio and image processing. Since it is still an ill posed problem, any additional information is beneficial. In this contribution, we investigate the use of sparsity criteria for both the source signal and the convolution kernels. A probabilistic model of the problem is introduced and its Variational Bayesian solution derived. The sparsity of the solution is achieved by introduction of unknown variance of the prior on all elements of the convolution kernels and the mixing matrix. Properties of the model are analyzed on simulated data and compared with state of the art methods. Performance of the algorithm is demonstrated on the problem of decomposition of a sequence of medical data. Specifically, the assumption of sparseness is shown to suppress artifacts of unconstrained separation method.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
BB - Applied statistics, operational research
OECD FORD branch
—
Result continuities
Project
<a href="/en/project/GA13-29225S" target="_blank" >GA13-29225S: Image Blind Deconvolution in Demanding Conditions</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2013
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Machine Learning and Knowledge Discovery in Databases
ISBN
978-3-642-40990-5
ISSN
0302-9743
e-ISSN
—
Number of pages
16
Pages from-to
548-563
Publisher name
Springer
Place of publication
Berlin Heidelberg
Event location
Praha
Event date
Sep 24, 2013
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—