Comparing error predictions of GPS position components using, ARMANN, RNN, and ENN in order to use in DGPS

This article describes experimental results of a comparing Global Positioning System error prediction using ARMA Neural Network (ARMANN), Recurrent Neural Network (RNN) and Evolutionary Neural Network (ENN). The result is a highly effective estimation technique for accurate positioning, the experiments show that the prediction total RMS errors are less than 0.12 meter, the experimental test results with real data emphasize that the total performance of ENN is better than other methods.