Symmetric self-constructing fuzzy neural network beamformers trained with cluster-based minimum bit-error rate method

In this paper, a powerful symmetric self-constructing fuzzy neural network (S-SCFNN) beamformer is proposed for multi-antenna assisted systems. A novel training algorithm for the S-SCFNN beamformer is proposed based on partition of the array input signal space and a cluster-based minimum bit-error rate method. An inherent symmetric property of the array input signal space is exploited to make the training procedure of S-SCFNN more efficient compared to that of standard SCFNN. Simulation results demonstrate that the S-SCFNN beamformer provides superior performance to the classical linear and nonlinear ones, especially when supporting a large amount of users in the rank-deficient multi-antenna assisted system.