Home > Table of Contents


Proceedings of the 2nd International Symposium on Information Processing (ISIP 2009)

Huangshan, China, August 21-23, 2009

Editors: Fei Yu, Jian Shu, and Guangxue Yue

AP Catalog Number: AP-PROC-CS-09CN002

ISBN: 978-952-5726-02-2 (Print), 978-952-5726-03-9 (CD-ROM)

Page(s): 306-308

Study on the method of GPS Height Fitting Based on Wavelet Neural Network

Chen Gang, Ma Youli, Wang Fangjie, and Liu lilong

Full text: PDF


The height accuracy problem is one of the most difficult problems about GPS research. And different GPS height fitting methods has their own applied conditions. Conversion GPS height is based on neural network (NNM) which is an adaptive mapping method, this method has no assumptions, it is more reasonable in theory and is able to avoid unknown factors, but there is a lot of disadvantages with the NNM: computing complexity, time assuming, unable to detect gross error, instable simulation results, big effect on the results and convergence from the initial weights, even on the convergence rate, never convergent. In order to overcome these deficiencies, in this paper, we combine wavelet analysis theory with neural network methods for GPS height fitting, referred as Wavelet Neural Network (WNN). In this paper, wavelet function is selected through the various contrast, in the end, it chooses a new class of weighted wavelet function. In this paper, it compares the WNN with NNM with instance data, anglicizing good and bad points about WNN in the GPS height fitting.

Index Terms

GPS Height Fitting; wavelet neural network; weighted wavelet

Copyright @ 2009 ACADEMY PUBLISHER All rights reserved