Multidimensional independent subspace analysis by natural gradient

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

Warianty tytułu

PL

Wielowymiarowa analiza podprzestrzeni MISA wykorzystująca metodę naturalnego gradient

• Języki publikacji: EN

Abstrakty

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.

Słowa kluczowe

EN

independent component analysis; blind signal separation; Independent Subspace Analysis (ISA)

PL

ślepa separacja; metoda naturalnego gradientu; analiza MISA

• Wydawca: Wydawnictwo SIGMA-NOT
• Czasopismo: Przegląd Elektrotechniczny
• Rocznik: 2012
• Tom: R. 88, nr 9b
• Strony: 51--54
• Opis fizyczny: Bibliogr. 19 poz., rys.

Twórcy

autor

Wang F.

• National Key Laboratory for Radar Signal Processing, Xidian University, China
• China Electronics Technology Group Corporation, the 27th Research Institute, China

autor

Zhang L.

• National Key Laboratory for Radar Signal Processing, Xidian University, China

autor

Li R.

• School of Sciences, Henan University of Technology, China

autor

Zhou Y.

• National Key Laboratory for Radar Signal Processing, Xidian University, China

autor

Liu N.

• National Key Laboratory for Radar Signal Processing, Xidian University, China

Bibliografia

• [1] Comon P., Jutten C., Handbook of Blind Source Separation: Independent Component Analysis and Applications. Elsevier, Oxford 2010.
• [2] Cichocki A., Amari S., Adaptive Blind Signal and Image Processing: Learning Algorithms and Applications. John Wiley & Sons, New York 2002.
• [3] Hyvarinen A., Hoyer P., Emergence of phase and shift invariant features by decomposition of natural images into independent feature subspaces, Neural Computation, 12 (2000), No.7, 1705-1720.
• [4] Cardoso J.F., Multidimensional independent component analysis, Proc. of the IEEE 1998 Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP’98), 1998, 1941-1944, Seattle, WA, USA.
• [5] Theis F.J., Blind signal separation into groups of dependent signals using joint block diagonalization, Proc. ISCAS 2005, 2005, Kobe, Japan.
• [6] Poczos B., Lorincz A., Independent Subspace Analysis Using k-Nearest Neighborhood Distances, Lecture Notes in Computer Science, 3697 (2005), 163-168.
• [7] Hyvarinen A., Koster U., FastISA: A fast fixed-point algorithm for independent subspace analysis, Proc. European Symposium on Artificial Neural Networks, 2006, Bruges, Belgium.
• [8] Choi H., Choi S., Relative Gradient Learning for Independent Subspace Analysis, Proc. Int. Joint Conf. Neural Networks (IJCNN), 2006, Vancouver, BC, Canada, 3919-3924.
• [9] Bach F.R., Jordan M.I., Kernel Independent Component Analysis. Journal of Machine Learning Research, 3 (2002), 1-48.
• [10] Caiafa C.F., Proto A.N., Separation of statistically dependent sources using an L2-distance non-Gaussianity measure. Signal Processing, 86 (2006), No.11, 3404-3420.
• [11] Wang F.S., Li H.W., Li R., Novel NonGaussianity Measure Based BSS Algorithm for Dependent Signals, Lecture Notes in Computer Science, 4505 (2007), 837-844.
• [12] Caiafa C.F., Salerno E., Protoa A.N., Fiumi L., Blind spectral unmixing by local maximization of non-Gaussianity. Signal Processing, 88 (2008), No.1, 50-68.
• [13] Zhang K., Chan L.W., An Adaptive Method for Subband Decomposition ICA. Neural Computation, 18 (2006), No.1, 191-223.
• [14] Abrard F., Deville Y., A time-frequency blind signal separation method applicable to underdetermined mixtures of dependent sources, Signal Processing, 85 (2005), No.7, 1389-1403.
• [15] Theis F.J., Uniqueness of complex and multidimensional independent component analysis, Signal Processing, 84 (2004), No.5, 951-956.
• [16] Theis F.J., Towards a general independent subspace analysis, Proc. NIPS, 2007.
• [17] Aghabozorgi M.R., Doost-Hoseini A.M., Blind separation of jointly stationary correlated sources. Signal Processing, 84 (2004), No.2, 317-325.
• [18] Li H., Shen Y.-H., Wang J.-G., Online Blind Separation of Dependent Sources Using Nonnegative Matrix Factorization Based on KL Divergence. Przeglad Elektrotchniczny, 88 (2012), No.1b, 17-20.
• [19] Blanchard G., Kawanabe M., Sugiyama M., Spokoiny V., Muller K.R., In search of non-gaussian components of a highdimensional distribution. Journal of Machine Learning Research, 7 (2006), 247-282.