Impact of higher-order statistics on adaptive algorithms for blind source separation

Abstract

The paper is devoted to present an analysis of the impact of higher order statistics (HOS) in adaptive blind source separation criteria. Despite the well known fact that they are necessary to provide source separation in a general framework, their impact on the performance of adaptive solutions is a still open research field. The approach of probability density function (pdf) recovering is used. In order to verify the analysis, two constrained adaptive algorithms are investigated. Namely, the multiuser kurtosis algorithm (MUK) and the multiuser constrained fitting probability density function algorithm (MU-CFPA) are used due to the desired characteristics of different HOS involved in their design. Simulation results are carried out to basis our analysis.