Support Vector Regression for GDOP

Abstract

Geometric Dilution of Precision (GDOP) is an indicator showing how well the constellation of GPS satellites is organized geometrically. 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. This paper presents a support vector regression (SVR) approach for finding regression models which can reasonably eliminate GDOP without complicated matrix inversion. Ten parameters from the measurement matrix are used as inputs to SVR which produces an estimation of GDOP. Using the proposed method, the processing costs for GPS positioning with low GDOP can be reduced. The experimental results show that the proposed method has good performance.