ISI and Burst Noise Interference Minimization Using Wilcoxon Generalized Radial Basis Function Equalizer

This paper presents a novel technique in channel equalization. A wireless communication system is affected by inter-symbol interference, co-channel interference in the presence of additive white Gaussian noise and also with burst noise, where burst noise is defined to be a series of finite-duration Gaussian noise pulses with fixed duration and Poisson occurrence times. Adaptive equalization techniques have been used to mitigate these effects. Artificial Neural Networks based Multilayer Perceptron Network, Radial Basis Function, Recurrent Network, Fuzzy and Adaptive Neuro fuzzy System, conventionally linear adaptive filter trained by LMS and RLS algorithm. In this paper we proposed a RBF based equalizer which is trained using wilcoxon learning method. The equalizer presented shows considerable performance gain for signals corrupted by Burst noise. Simulation studies conducted, demonstrate the performance of wilcoxon training for this class of problem.