A　Blind　Equalizer　Based　on　Unsupervised　Gaussian　Cluster　Formation　with　an　Adaptive　Non-Linearit

A Blind Equalizer Based on Unsupervised Gaussian Cluster Formation with an Adaptive Non Linearity

ＡＢｌｉｎｄＥｑｕａｌｉｚｅｒＢａｓｅｄｏｎＵｎｓｕｐｅｒｖｉｓｅｄＧａｕｓｉａｎＣｌｕｓｔｅｒＦｏｒｍａｔｉｏｎｗｉｔｈａｎＡｄａｐｔｉｖｅＮｏｎ┐ＬｉｎｅａｒｉｔｙＬｉｕＨａｎｙｕ（ＤｅｐｔｏｆＥｌｅｃｔｒｉｃａｌａｎｄＣｏｍｐｕｔｅｒＥｎｇｉｎ...

In this paper we present a blind equalizer algorithm based on an unsupervised Gaussian cluster formation technique with an optimized gradient adaptive step size to update the equalizer coefficients. The novelty of this work lies in the optimization of the nonlinearity of the cluster formation used to achieve an optimal soft decision. The proposed iterative procedure combined with the variable step size gradient based adaptation, significantly accelerates the convergence speed of the blind equalization. The advantages of the proposed equalization techniques are illustrated by simulation. Simulation results obtained are compared with the Sato and Godard blind equalizers.