Effect of Neural Network-Based Tuning Process on Performance of DS-CDMA Receiver Using Exponentially Weighted Despreading Waveforms

The exponential chip weighting waveforms used in a coherent receiver are designed for the purpose of multiple access interference (MAI) rejection by empha-sizing the transitions of the received signal of interest. The despreading sequence weighted by exponential chip waveforms is determined by one parameter and this parameter needs to be tuned with respect to each signal to noise ratio (SNR) so as to maximize the signal to interference plus noise ratio (SINR) of the decision variable. In this paper, we propose a neural network-based tuning process for automatically tuning the parameter of exponential chip weighting waveforms and present the effect of this process on performance of the receiver in a DS-CDMA system. The numerical results show that although the optimal value of the parameter is automatically and quickly produced by the proposed method, any destructive effect on receiver performance does not occur