Return to search

Checking the integrity of Global Positioning Recommended Minimum (GPRMC) sentences using Artificial Neural Network (ANN)

<p>In this study, Artificial Neural Network (ANN) is used to check the integrity of the Global Positioning Recommended Minimum (GPRMC) sentences. The GPRMC sentences are the most common sentences transmitted by the Global Positioning System (GPS) devices. This sentence contains nearly every thing a GPS application needs. The data integrity is compared on the basis of the classification accuracy and the minimum error obtained using the ANN. The ANN requires data to be presented in a certain format supported by the learning process of the network. Therefore a certain amount of data processing is needed before training patterns are presented to the network. The data pre processing is done by the design and development of different algorithms in C# using Visual Studio.Net 2003. This study uses the BackPropagation (BP) feed forward multilayer ANN algorithm with the learning rate and the momentum as its parameters. The results are analyzed based on different ANN architectures, classification accuracy, Sum of Square Error (SSE), variables sensitivity analysis and training graph. The best obtained ANN architecture shows a good performance with the selection classification of 96.79 % and the selection sum of square error 0.2022. This study uses the ANN tool Trajan 6.0 Demonstrator.</p>

Identiferoai:union.ndltd.org:UPSALLA/oai:DiVA.org:hig-5205
Date January 2009
CreatorsHussain, Tayyab
PublisherUniversity of Gävle, Ämnesavdelningen för samhällsbyggnad
Source SetsDiVA Archive at Upsalla University
LanguageEnglish
Detected LanguageEnglish
TypeStudent thesis, text

Page generated in 0.002 seconds