GPS GDOP approximation using support vector regression algorithm with parametric insensitive model

Global Positioning System (GPS) has extensively been used in various fields. One of the most important factors affecting the precision of the performance of a GPS receiver is the relative positioning of satellites to each other. Therefore, it is essential to choose appropriate accessible satellites utilized in the calculation of GPS positions. Optimal subsets of satellites are determined using the least value of their Geometric Dilution of Precision (GDOP). The most correct method of calculating GPS GDOP uses inverse matrix for all combinations and selecting the lowest ones. However, the inverse matrix method, especially when there are so many satellites, imposes a huge time and power-load on the processor of the GPS navigator. Previous studies have shown that numerical regression on GPS GDOP can get satisfactory results and save many calculation steps. In this paper we apply a new support vector regression machine with parametric-insensitive model (par-v-SVR) to the approximation of GPS GDOP. For a priori chosen v, the par-v-SVR automatically adjusts a flexible tube of arbitrary shape and minimal radius to include the data such that at most a fraction v of the data points lies outside. The experimental results show that par-v-SVR has better performance than previous support vector regression machine.