Header menu link for other important links
Driver Profiling Using Realistic Racing Games
Published in IEEE
Pages: 13 - 17
All humans operating vehicles with several in-puts(steering wheel, pedals, gears etc.) do so in a unique way. We attempt to identify drivers based on this characteristic driving profile. Users were made to playa realistic 3D driving simulation, StuntRally. Their keypress events were logged. These logs were used to train and test different classifiers such as Support Vector Machine(SVM), K Nearest Neighbour(KNN) and Naive Bayes(NB). The SVM performed best with an average testing accuracy of 80 %. © 2018 IEEE.
About the journal
JournalData powered by Typeset2018 Second International Conference on Inventive Communication and Computational Technologies (ICICCT)
PublisherData powered by TypesetIEEE
Open AccessNo