Wyniki wyszukiwania - BazTech

1

Multidimensional independent subspace analysis by natural gradient

Wang F., Zhang L., Li R., Zhou Y., Liu N.

Przegląd Elektrotechniczny

|

2012

|

R. 88, nr 9b

51-54

EN

Multidimensional Independent Subspace Analysis (MISA) as an extended Independent Component Analysis (ICA) method has been considered. The general and detailed definition, existence, uniqueness, separability of the MISA model are given and the relationships between ICA and MISA are also discussed. The natural gradient separation algorithm and corresponding simulation results for MISA are constructed based on the maximum likelihood theory and natural gradient method.

PL

W artykule zaprezentowano metodę MISA – multidimensional independent subspace analysis. Przedstawiono też metode IOCA – independent component analysis. Opracowano algorytm separacji – natural gradient separation algorithm.

2

ICA-based Single Channel Audio Separation: New Bases and Measures of Distance

Mika D., Kleczkowski P.

Archives of Acoustics

|

2011

|

Vol. 36, No. 2

311-331

EN

Independent Component Analysis (ICA) can be used for single channel audio separation, if a mixed signal is transformed into time-frequency domain and the resulting matrix of magnitude coefficients is processed by ICA. Previous works used only frequency (spectral) vectors and Kullback-Leibler distance measure for this task. New decomposition bases are proposed: time vectors and time-frequency components. The applicability of several different measures of distance of components are analysed. An algorithm for clustering of components is presented. It was tested on mixes of two and three sounds. The perceptual quality of separation obtained with the measures of distance proposed was evaluated by listening tests, indicating “beta” and “correlation” measures as the most appropriate. The “Euclidean” distance is shown to be appropriate for sounds with varying amplitudes. The perceptual effect of the amount of variance used was also evaluated.

3

Usuwanie artefaktów z danych EEG przy użyciu analizy składowych niezależnych

Górecka J., Kaszyński R.

Pomiary Automatyka Kontrola

|

2008

|

R. 54, nr 12

827-830

PL

Celem przedstawionych wyników badań jest eliminacja wybranych niepożądanych sygnałów przy użyciu analizy składowych niezależnych. W artykule przedstawiono następujące algorytmy BSS (z ang. Blind Signal Separation): HJ oraz Infomax jako narzędzia do separacji i usuwania wybranej grupy artefaktów (mruganie powiek, artefakty mięśniowe) z przebiegów EEG. Jak udowodniono w eksperymentach proponowane algorytmy adaptacyjne mogą efektywnie wykrywać i usuwać wybrane artefakty z przebiegów EEG.

EN

The aim of the performed investigations is to remove selected undesired signals by means of ICA approach. In the paper there are presented the following algorithms BSS (Blind Signal Separation): HJ and Infomax for separation and removal of selected group of artifacts (eye blinks, muscle activity) from EEG recordings. It has been proved in the experiments which are described in the paper that the proposed adaptive algorithms can effectively detect and remove these selected artifacts from EEG recordings.