Fast and robust deflationary separation of complex valued signals

A fast and robust algorithm for the separation of complex valued signals is presented. It is assumed that the original, complex valued source signals are mutually statistically independent, and that the mixing process is linear. The problem is solved by the independent component analysis (ICA) model. ICA is a statistical method for transforming an observed multidimensional random vector into components that are mutually as independent as possible. Our fast, fixed-point type algorithm is capable of separating complex valued, linearly mixed source signals in a deflationary manner. The computational efficiency of the algorithm is shown by simulations. Also, a theorem on the local consistency of the estimator given by the algorithm is presented.