Title :
Independent component analysis by complex nonlinearities
Author :
Adali, Tülay ; Kim, Taehwan ; Calhoun, Vince
Author_Institution :
Dept. of Comput. Sci. & Electr. Eng., Univ. of Maryland, Baltimore, MD, USA
Abstract :
A number of complex nonlinear functions are proposed for the independent component analysis (ICA) of complex-valued data. We discuss the properties of these nonlinearities and show their efficiency in generating the higher order statistics needed for ICA.
Keywords :
decorrelation; higher order statistics; independent component analysis; nonlinear functions; ICA; complex nonlinear functions; complex nonlinearities; complex-valued data; higher order statistics; independent component analysis; nonlinear decorrelation; Computed tomography; Frequency domain analysis; Higher order statistics; Independent component analysis; Magnetic resonance imaging; Psychiatry; Radar imaging; Random variables; Source separation; Tensile stress;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 2004. Proceedings. (ICASSP '04). IEEE International Conference on
Print_ISBN :
0-7803-8484-9
DOI :
10.1109/ICASSP.2004.1327163
