Accurate prediction of differential GPS corrections using fuzzy cognitive map

Abstract

Fuzzy Cognitive Maps (FCMs) are fuzzy neural networks that are used for modeling and simulation of dynamic systems in a spread spectrum of different areas. In this paper, we apply this method for modeling the time variant errors of Global Positioning System (GPS) receivers, which are utilized for many surveying and navigation applications in various locations. These errors in receivers are ordinarily caused by atmosphere, imprecise orbit, satellite distribution geometry, multi-path, satellite, receiver clock, and selective availability. For increasing the accuracy of positioning, we predict the components' errors of location that are used as Differential GPS (DGPS) corrections in real-time positioning by FCM. To validate the performance, this approach is verified with experimental data from an actual data collection. The simulation studies show the effectiveness of the proposed approach compared with the results of multi-layer perceptron neural network.