Neural networks applications for CDMA systems in non-Gaussian multi-path channels

Abstract

Non-Gaussian noise is one of the most common noise models observed in wireless channels. This type of noise has severe impact on wireless systems with multiuser detection devices. In this paper, the issue of multiuser detection in non-Gaussian noise multipath channel is addressed. We also pay a close attention to the neural network applications, and propose a new robust neural network detector for multipath impulsive channels. The maximal ratio combining (MRC) technique is adopted to combine the multipath signals. Moreover, we discuss the performance of the proposed multiuser neural network decorrelating detector (NNDD), under class A Middleton model. Furthermore, the performance of the system under power imbalance scenario is shown. We show that the proposed NNDD has magnificent effect on the system performance. The system performance is measured through the bit error rate (BER). It is shown that the proposed robust receiver reduces the impact of the impulsive noise by processing the received signal and clipping the extreme amplitudes.