A comparative study on regression models of GPS GDOP using soft-computing techniques

Abstract

Global Positioning System (GPS) has been used extensively in various fields. One key to success of using GPS is the positioning accuracy. Geometric Dilution of Precision (GDOP) is an indicator showing how well the constellation of GPS satellites is organized geometrically. It is known that increasing the number of satellites for positioning reduces GDOP. However, the calculation of GDOP is a time- and power-consuming task which can be done by solving measurement equations with complicated matrix transformation and inversion. Previous studies have partially solved this problem with artificial neural network(ANN). Though ANN is a powerful function approximation technique, it needs costly training and the trained model may not be applicable to data deviating too much from the training data. Using the technique of support vector regression (SVR), this paper presents the effectiveness of SVR for GDOP approximation. The experimental results show that SVR needs less training time to generate a precise model for GDOP than ANN does.