MC-CDMA Multiuser Detection Using a Hybrid Immune Clonal Selection Algorithm with Hopfield Neural Network in Fading Channels

In this paper, we present multiuser detection (MUD) technique based on a hybrid immune clonal selection algorithm (ICSA) with Hopfield neural network (HNN), for Multi-Carrier Code Division Multiple Access (MC-CDMA) communications systems. The ICSA is an effective approach for the issue of multiuser detection, however, it needs relative high iterated time to convergence. The performances of the ICSA with different parameters are studied, and the effect of parameter changing is analyzed, however adjusting these parameters cannot significantly accelerate the convergence. Then, Hopfield Neural Networks are embedded into the ICSA to improve further the affinity of the antibodies at each generation. Such a hybridization of the ICSA with the HNNs reduces its computational complexity by providing faster convergence. Simulation results are provided to show that the proposed approach can achieve near-optimal bit error rate (BER) performance with reasonable computational complexity.