New fast-ICA algorithms for blind source separation without prewhitening

Abstract

This paper focuses on proposing a new fast-ICA algorithm without prewhitening. First, existing fast-ICA method is reviewed. then, by combing the separating vector in the existing fast-ICA algorithm with the prewhitening matrix, we propose a new separating vector, which is used to separate statistically independent component from the observed data without prewhitening. The iterative rule of new separating vector is developed. Finally, the effectiveness of this new algorithm is verified by computer simulations. © 2011 Springer-Verlag.