Complex RPROP-algorithm for neural network equalization of GSM data bursts

Neural networks have been studied for channel equalization purposes with quite promising results. However, not a lot of published results are available for their performance in realistic mobile systems, such as Global System for Mobile communications (GSM). In this paper we have studied the use of complex-valued multilayer perceptron (MLP) network for equalization purposes when transmitting data bursts through GSM-channels and through a nonlinear channel. In addition to the conventional complex backpropagation algorithm for the training of the network, we have also presented a complex version of the Resilient PROPagation (RPROP) algorithm. These training methods are then compared and studied using GSM channel models as well as a nonlinear channel model. Performance comparisons are made in terms of bit error rates (BERs) and computational complexity. Results show that the MLP network trained with complex RPROP algorithm achieves approximately as good bit error rates as the MLP network trained with complex backpropagation, but with clearly smaller computational load.