Reduced RBF Centers based multi-user detection in DS-CDMA systems

The major goal of this paper is to develop a practically implemental radial basis function neural network based multi-user detector for direct sequence code division in multiple access systems. This work is expected to provide an efficient solution by quickly setting up the proper number of radial basis function centers and their locations required in training. The basic idea in this research is to select all the possible radial basis function centers by using supervised k-means clustering technique, select the only centers which locate near seemingly decision boundary, and reduce them further by grouping some of the centers adjacent to each other. Therefore, it reduces the computational burden for finding the proper number of radial basis function centers and their locations in the existing radial basis function based multi-user detector, and ultimately, make its implementation practical.