• JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
 
  Bookmark and Share
 
 
Doctoral Thesis
DOI
https://doi.org/10.11606/T.18.2003.tde-18092015-155038
Document
Author
Full name
Carlos Augusto Uchôa da Silva
E-mail
Institute/School/College
Knowledge Area
Date of Defense
Published
São Carlos, 2003
Supervisor
Committee
Segantine, Paulo César Lima (President)
Fonseca Júnior, Edvaldo Simões da
Romero, Roseli Aparecida Francelin
Schaal, Ricardo Ernesto
Veiga, Luís Augusto Koenig
Title in Portuguese
Um método para estimar observáveis GPS usando redes neurais artificiais
Keywords in Portuguese
Código P
GPS
Modelagem
Portadora L2
Redes neurais artificiais
Abstract in Portuguese
O NAVSTAR-GPS, com uma grande variedade de conjuntos receptores e sua aplicabilidade prática em diversas áreas, transformou-se no mais difundido dos sistemas de posicionamento. Porém, necessidades cada vez maiores em termos de precisão trouxeram consigo o ônus de um custo elevado com a aquisição de equipamentos de dupla freqüência. Este trabalho consiste no desenvolvimento de um método que possibilite a modelagem das observáveis GPS, através de Redes Neurais Artificiais, bem como a agregação destes dados a um arquivo gerado por um receptor de uma freqüência, conferindo-lhe características específicas de arquivos gerados por receptores de dupla freqüência e código P. Isto possibilita que dados gerados por receptores de uma freqüência, a imensa maioria dos receptores utilizados no Brasil, possam ser processados como vetores de bases longas. Os resultados obtidos indicam que o uso de modelos neurais, treinados por algoritmos de aprendizado supervisionado, são uma alternativa promissora para estimar dados GPS.
Title in English
A method to estimate GPS data observables using artificial neural networks
Keywords in English
Artificial neural networks
GPS
L2 carrier
Modelling
P code
Abstract in English
The NAVSTAR-GPS, with a great variety of receivers and its practical aplicabillity in several areas, transformed itself in the most known positioning system. But the necessity of improving the results precision brings with it a cost increasing caused by the use of equipments of dual frequency equipments. This work consist on the development of a method that makes possible the GPS data modelling using Neural Networks, as well as the aggregation of these data into a file generated by single frequency receiver, providing to the system specific characteristics of files generated by double frequency an P code receiver. This makes possible that data generated by receivers of single frequency, the majority of receivers in Brazil, can be processed as vectors of long bases. The results obtained indicate that the use of Neural Network models, with algorithms of supervised learning are a promissing alternative to estimate GPS data.
 
WARNING - Viewing this document is conditioned on your acceptance of the following terms of use:
This document is only for private use for research and teaching activities. Reproduction for commercial use is forbidden. This rights cover the whole data about this document as well as its contents. Any uses or copies of this document in whole or in part must include the author's name.
Publishing Date
2015-09-18
 
WARNING: Learn what derived works are clicking here.
All rights of the thesis/dissertation are from the authors
CeTI-SC/STI
Digital Library of Theses and Dissertations of USP. Copyright © 2001-2024. All rights reserved.