Blind Channel Equalization Using Second-Order Statistics: A Necessary and Sufficient Condition

Abstract

In this work the blind equalization of a single-input, multiple-output channel has been carried out using second-order statistics. A sufficient and necessary condition for blind equalization based on second order statistics has been given. It has been proved that a single autocorrelation matrix of the source symbols is sufficient for blind equalization. The proposed scheme is generalized; that is, it is valid for white as well as colored source symbols. A linear artificial neural network is developed with a learning algorithm based on the new condition. The results of the new algorithm verify its validity and superior performance.