Abstract: In this paper, a novel wavelet network based adaptive equalizer (WNBAE) is presented. The structure and stochastic gradient learning algorithm of the WNBAE is given. In the MQAM digital communication reception systems over nonlinear channels the proposed WNBAE has better performance than that of the conventional linear transversal equalizer based on the LMS or the RLS algorithms, as well as that of the decision feedback equalizer based on the RLS algorithm. It outperforms slightly the back propagation network based adaptive equalizer. Several simulations are performed to evaluate the behavior of the WNBAE.

Key words: wavelet network, non-linear channel equalization, MQAM, adaptive equalizer