0083440 20240103184236.420070618235959.9 4 s. cav_un_epca*02532121070-9908146 (2007)417-420Institute of Electrical and Electronics Engineers blind source separation independent component analysis autoregressive ARMA moving average stationary Gaussain random processes cav_un_auth*0213972 Doron E. IL cav_un_auth*0213973 Yeredor A. IL cav_un_auth*0101212 Tichavský Petr UTIA-B Department of Stochastic Informatics Ústav teorie informace a automatizace AV ČR, v. v. i. 1M0572 GA MŠk CZ cav_un_auth*0001814 CEZ:AV0Z10750506 The performance of blind source separation algorithms is commonly measured by the output interference to signal ratio (ISR). In this paper we derive an asymptotic bound on the attainable ISR for the case of Gaussian parametric (auto-regressive (AR), moving-average (MA) or ARMA) processes. Our bound is induced by the Cramer-Rao bound on estimation of the mixing matrix. We point out the relation to some previously obtained results, and provide a concise expression with some associated important insights. Using simulation, we demonstrate that the bound is attained asymptotically by some asymptotically efficient algorithms. Kvalita algoritmu pro slepou separaci je měřena pomocí výstupního poměru interference vůči šumu (ISR). V tomto článku je odvozena asymptotická mez pro ISR pro Gaussovské parametrické (AR, ARMA, MA) stacionarní procesy. V simulacích je ukázáno, že existují asymptoticky eficientní algoritmy, které této hranice dosahují. 2008 BB http://hdl.handle.net/11104/0146683 1.226 0.123 5.2 0.01262 0.645 1794 252 74 1.433 11.03 2.32 2007 cav_un_epca*0253212 IEEE Signal Processing Letters 1070-9908 1558-2361 Roč. 14 č. 6 2007 417 420 Institute of Electrical and Electronics Engineers