Summary: INDEPENDENT COMPONENT ANALYSIS BY COMPLEX NONLINEARITIES
, Taehwan Kim,2
and Vince Calhoun3,4
Dept. of CSEE, University of Maryland Baltimore County, Baltimore, MD, 21250
The MITRE Corporation, McLean, VA, 22102
Olin Neuropsychiatry Research Center, Institute of Living, Hartford, CT 06106
Dept. of Psychiatry, Yale University, New Haven, CT 06520
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.
Independent component analysis (ICA) for separating complex-
valued sources is needed for convolutive source-separation in the