Channel equalization using radial basis function network

The application of radial basis function (RBF) networks to signal processing has received attention from many researchers. This paper is concerned with improving the previously developed RBF equalizer (Chen et al., 1993) by greatly reducing the number of centers. The basic idea is to select only centers close to the boundary between the different decision classes. The first factor of reducing the network size is 2^τ where τ is the channel lag. The number of centers was further reduced by representing several centers by a single point. Simulation studies show that the error rate performance of an RBF equalizer with the proposed reduction in the number of centers compares favorably with the RBF equalizer having the conventional number of centers. It also performs better than linear equalizers