We propose in this paper an hybrid immune clonal selection algorithm (ICSA) to approach near-optimal performance for multiple-input multiple-output (MIMO) multiuser detection. The ICSA which guide the heuristic search by imitating the evolutionary mechanism of antibodies, is shown to approach the performance of maximum-likelihood (ML) detector. The Hybrid ICSA multiuser detection (MUD) approach, which introduce embedded Hopfield neural networks (HNN) to accelerate the search convergence and improve local search capability, is further proposed. The simulation results show that it is feasible to achieve near-optimal bit-error-rate (BER) performance with a lower complexity using the proposed algorithm.
展开▼
