Pseudorange Correction Prediction Using Artificial Neural Network

O.A. Alim, A. El-Rabbany,R. Rashsd, and M. Mohasseb

Abstract:	This paper focuses on modeling and predicting pseudorange corrections transmitted by a marine DGPS radiobeacon using artificial neural networks. Data sets used in building the model are the transmitted pseudorange corrections and broadcast navigation message. Model design is passed through several stages, namely collecting the data, preprocessing the data, building the model, and finally validating the model. The preprocessing stage included the determination of the 3-D beacon-satellite vector as a function of time, which was obtained through the broadcast ephemeris and the known beacon position. Preprocessing data is performed using several programming tools. Special application is written using Microsoft Visual Basic to read the ephemeris data, preprocess the data, and finally store it in Microsoft Access and Excel. Various neural network structures with various training algorithms were examined, including Linear, Radial Biases, and Feedforward. Matlab Neural Network toolbox is used for this purpose. It is found that feedforward neural network with automated regularization is the most suitable for our data. In training the neural network, different approaches are used to take advantage of the pseudorange corrections history while taking into account the required time for prediction and storage limitations. Three data structures are considered in training the neural network, namely all round, compound, and average. Of the various data structures examined, it is found that the average data structure is the most suitable. After pre-modeling, choosing the appropriate neural network and data training stages, comprehensive validation test is conducted to check the achieved horizontal positioning accuracy level when using the proposed neural network. Pseudorange corrections spanning 4 consecutive days were used to train the neural networks, which is then used to predict the pseudorange corrections for the fifth days. In the model validation stage, the predicted pseudorange corrections for the fifth day were compared with the actual (known) pseudorange corrections. These predicted corrections were used in computing station position instead of the real-time pseudorange corrections.
Published in:	Proceedings of the 2006 National Technical Meeting of The Institute of Navigation January 18 - 20, 2006 Hyatt Regency Hotel Monterey, CA
Pages:	396 - 399
Cite this article:	Alim, O.A., El-Rabbany, A., Rashsd, R., Mohasseb, M., "Pseudorange Correction Prediction Using Artificial Neural Network," Proceedings of the 2006 National Technical Meeting of The Institute of Navigation, Monterey, CA, January 2006, pp. 396-399.
Full Paper:	ION Members/Non-Members: 1 Download Credit Sign In