Abstract: Thegeometric dilution of precision is widely used as criterion for selecting the best set of the measurement devices. Some methods had been proposed to find the value of theGeometric Dilution of Precision (GDOP), such as using inverse matrix to solve the linear equation.But it takes a large amount of computing to find the optimal solution. In this paper, we proposed a method which use neural network with gradient descent adaptive learning rate training algorithm to approximate the value of GDOP. By the simulation results, it is suggested to combine the service base station with three others to estimate the position of mobile station.This will significantly reduce the computational complexity.
[1]. J.Y. Tham, S. Ranganath, M. Ranganath and A. A. Kassim, "A novel unrestricted center-biased diamond search algorithm for block
motion estimation," IEEE Trans. Circuits Syst. Video Technol., vol. 8, no. 4, pp. 369-377, Aug. 1998.
[2]. S. Venkatraman and J. Caffery, "Hybrid TOA/AOA techniques formobile location in non-line-of-sight environments," Proc.
IEEEWireless Commun. and Net. Conf., pp. 274-278, Mar. 2004.
[3]. E.D. Kaplan and C.J. Hegarty, "Understanding GPS: principles andapplications," Artech House Press, Boston, 2005.
[4]. H. Sairo, D. Akopian, and J.Takala, "Weighted dilution of precisionas qualitymeasure in satellite positioning," IEE
ProceedingsRadar, Sonar and Navigation, vol. 150, no. 6, pp. 430–436, 2003.
[5]. Y. Yong and M. Lingjuan, "GDOP results in all-in-view positioningand in four optimum satellites positioning with GPSPRN codes
ranging," Proceedings of the Position, Location andNavigation Symposium (PLANS '04), pp. 723–727, Monterey,Calif, April 2004..