An improved fastica algorithm for signal separation of satellite-based ais

Abstract

FastICA algorithm has the advantages of simple form and fast convergence rate. However, it is sensitive to the initial values and the separation effect is badly influence if not chosen appropriately. To deal with this problem, this paper proposes an improved FastICA algorithm by improving the initial values. This new algorithm is based on constant model of space-borne AIS signal and in this paper the effectiveness of the proposed method is conformed by simulation. The experiments show that the mean square error is reduced and the performance is greatly improved.