Abstract: Based on artificial immunology and genetic algorithm, a hybrid algorithm to design the RBF network is proposed. An artificial immune mechanism for data clustering is used to adaptively specify the amount and initial positions of the RBF centers according to input data set; then RBF network is then trained with genetic algorithm that makes the training process tend to global optima. The application of the algorithm in multiuser detection problems demonstrates that the RBF network trained with the algorithm is concise in structure and has good anti-MAI performance.

Key words: RBF network, multiuser detection, artificial immune clustering, genetic algorithm