Impact of varying reference points density on performances of fingerprinting based GSM positioning system

Procuring the location information using mobile radio systems is a popular topic amongst researchers. This paper investigates the impact of reference points density on performances of fingerprinting based GSM positioning system. The neural networks based model, was trained with a varying volume of the training set. Having in mind the accuracy and the time consumption for model generation, it was shown that, for optimal performances, the adjacent reference points ought to be 4m to 6m apart.