Blind multiuser detection for DS-CDMA systems: a neural network approach

In this paper a neural network based blind multiuser detection scheme for DS-CDMA systems is presented. It is shown that both the decorrelating detector and the linear minimum-mean-square-error (MMSE) detector can be formulated as a constrained optimization problem and can be resolved efficiently by using neural networks. It is also shown that the proposed method is superior to the minimum-output-energy detector in computational efficiency and to the blind adaptive decorrelating detector in performance. The computational complexity of the proposed scheme is only O(N), making its real-time implementation possible