Adaptive Multiuser Detection Based on RBF Networks in Impulsive Noise CDMA Channels

摘要

With increasing need for capacity in mobile cellular communications, code division multiple access has been viewed as the technique to meet this goal. However, the conventional receiver suffers from multiuser interference and the near-far effect. To alleviate this problem, various multiuser receivers have been proposed. They have been shown to enhance the performance of the conventional receiver with respect to capacity and interference rejection. But these receivers, intended for Gaussian noise channels, can fail in other environments such as impulsive noise conditions. A possible solution is to exploit the advantages of neural networks. A neural network's ability to reject non-Gaussian noise can be utilized to implement multiuser receivers that reject both impulsive noise and multiuser interference.