m.r mosavi - department of electrical engineering shahid rajaee teachers training university
k mohammadi - iran university of science and technology
m.h refan

this paper presents a mehtod to determine an accurate position by using a low cost GPS receiver and proposes a MLP neural network for better accuracy in GPS positioning at first we intorduce the GPS system errors then measuting the errors of position components real and dynamic patterns of the errors will be created and feed in to the neural network the neural network is trained with such real data to predict the eroors of later seconds the steps design and implementation of the neural network are presented and the experimental results of the tests are stated with real data. theses show position components errors decrease due to training of the neural network.

improve of position accuracy , low cost GPS receiver , MLP neural network