Multiuser Detection of Synchronous MC-CDMA Using Hopfield Neural Networks

Multiple-access interference (MAI) is a principal shortcoming of code division multiple access (CDMA) system. As the optimum multiuser detection (MUD) can’t be realized in practice, more attentions are paid to suboptimum detection scheme. We investigated the application of Hopfield neural network (HNN) to the problem of multiuser detection in Multicarrier CDMA(MC-CDMA) communica -tion systems in order to reduce the effect of MAI and multipath fading(MPF), and proposed a blind HNN multiuser detector based on MOE criterion and Lagrange optimization algorithm to produce a real-time suboptimal solution to optimization problems. The performance of the proposed LHNN receiver is evaluated via computer simulations and compared with that of other detectors, which exhibits a number of attractive properties.