Widrow Hoff Learning Algorithm Based Minimization of BER Multi-User Detection in SDMA

In this paper minimization of BER in MUD based on neural network has been proposed. The change in weights from Widrow-Hoff learning algorithm has been used to update the weight vectors of the equalizer. Neural networks can be used for linear design, adaptive prediction, amplitude detection, character recognition and many other applications. In this paper adaptive prediction has been used in detecting the errors caused in AWGN channel. These errors are rectified by using Adaptive prediction methods based LMS algorithm for updating their weights. SDMA scheme with 3 users and 4 receiver antennas has been considered in the present work for obtaining the results. BPSK is used as the modulation scheme.