| bibtype |
C -
Conference Paper (international conference)
|
| ARLID |
0306561 |
| utime |
20240111140700.5 |
| mtime |
20080410235959.9 |
| title
(primary) (eng) |
Extension of EFICA Algorithm for Blind Separation of Piecewise Stationary Non-Gaussian Sources |
| specification |
| page_count |
4 s. |
| media_type |
CD-ROM |
|
| serial |
| ARLID |
cav_un_epca*0306559 |
| ISBN |
978-1-4244-1483-3 |
| ISBN |
1-4244-1484-9 |
| title
|
ICASSP 2008: IEEE International Conference on Acoustics, Speech, and Signal Processing |
| page_num |
1913-1916 |
| publisher |
| place |
Bryan |
| name |
Conference Management Services |
| year |
2008 |
|
|
| title
(cze) |
Zobecnění algoritmu EFICA pro slepou separaci po částech stacionárních ne-gaussovských procesů |
| keyword |
independent component analysis |
| keyword |
piecewise stationary signals |
| keyword |
blind source separation |
| author
(primary) |
| ARLID |
cav_un_auth*0108100 |
| name1 |
Koldovský |
| name2 |
Zbyněk |
| institution |
UTIA-B |
| full_dept |
Department of Stochastic Informatics |
| fullinstit |
Ústav teorie informace a automatizace AV ČR, v. v. i. |
|
| author
|
| ARLID |
cav_un_auth*0050739 |
| name1 |
Málek |
| name2 |
J. |
| country |
CZ |
|
| author
|
| ARLID |
cav_un_auth*0101212 |
| name1 |
Tichavský |
| name2 |
Petr |
| institution |
UTIA-B |
| full_dept |
Department of Stochastic Informatics |
| fullinstit |
Ústav teorie informace a automatizace AV ČR, v. v. i. |
|
| author
|
| ARLID |
cav_un_auth*0238913 |
| name1 |
Deville |
| name2 |
Y. |
| country |
FR |
|
| author
|
| ARLID |
cav_un_auth*0238914 |
| name1 |
Hosseini |
| name2 |
S. |
| country |
FR |
|
| source |
| source_type |
textový dokument |
| source_size |
150kB |
|
| cas_special |
| project |
| project_id |
1M0572 |
| agency |
GA MŠk |
| ARLID |
cav_un_auth*0001814 |
|
| project |
| project_id |
GP102/07/P384 |
| agency |
GA ČR |
| country |
CZ |
| ARLID |
cav_un_auth*0227962 |
|
| research |
CEZ:AV0Z10750506 |
| abstract
(eng) |
We propose an extension of algorithm EFICA for piecewise stationary and non-Gaussian signals. Cramér-Rao bound for this model is derived and the extended algorithm is shown to be asymptotically efficient if score functions of the signals are known in each block. In contrast to classical ICA algorithms, the proposed method is able to profit from varying distribution of the original signals as well as from their non-stationarity, which is demonstrated on simulations with real-world signals. |
| abstract
(cze) |
V práci je navrženo zobecnění algoritmu EFICA pro slepou separaci po částech stacionárních negaussovských zdrojů. Navržená metoda využívá jak různosti pravděpodobnostního rozložení separovaných signálů v jednotlivých časových intervalech, tak proměnlivosti jejich variance. Přesnost separace dosahuje příslušné Rao-Cramerovy meze za předpokladu, že variance signálů je stejná na všech intervalech. |
| action |
| ARLID |
cav_un_auth*0238885 |
| name |
ICASSP 2008, IEEE International Conference on Acoustics, Speech adn Signal Processing |
| place |
Las Vegas |
| dates |
30.03.2008-04.04.2008 |
| country |
US |
|
| reportyear |
2010 |
| RIV |
BB |
| permalink |
http://hdl.handle.net/11104/0004578 |
| arlyear |
2008 |
| mrcbU56 |
textový dokument 150kB |
| mrcbU63 |
cav_un_epca*0306559 ICASSP 2008: IEEE International Conference on Acoustics, Speech, and Signal Processing 978-1-4244-1483-3 1913 1916 Bryan Conference Management Services 2008 |
|