Multiuser interference mitigation in multipath fading channels using a neural network based blind receiver

In order to enhance the bandwidth utilization, new advanced receivers for next generation mobile communications are developed. Adaptive blind multiuser detection has been widely proposed for applications in CDMA (code division multiple access) wireless communication systems for its principal advantage of eliminating training sequence to set-up receiver filter coefficients. Main drawback of this technique is that it reaches the optimum behavior after a certain number of bit times, which precludes its use in typical time-varying environments. A new neural network approach is proposed in order to solve this drawback. In particular, this paper considers the use of a modified Kennedy-Chua (1988) neural network, based on the Hopfield (1984) model. Numerical results are given to demonstrate the effectiveness of the proposed approach in different time-varying application scenarios.