Optimum multi-user signal detector in SSMA communication systems based on neural networks

This paper is motivated by the fact that, in a multi-user CDMA system, the conventional receiver suffers severe performance degradation as the relative powers of the interfering signals becomes large (i.e., "near-far problem"). Furthermore, in many cases the optimum multi-user receiver, which alleviates the near-far problem, is too complex to be of practical use. By viewing this optimum multi-user detector problem in a CDMA channel as an optimum nonlinear classification decision problem, we apply simple feedforward multilayered perceptrons referred to as the probabilistic neural network based maximum likelihood rule that has the abilities of arbitrary nonlinear transformations, adaptive learning and tracking to implement this classification decision optimally and adaptively. The performance of this proposed neural detector is evaluated via computer simulations in terms of the probability of detection and compared with other neural and conventional detector schemes in a multi-user environment.