Home // MOBILITY 2014, The Fourth International Conference on Mobile Services, Resources, and Users // View article

Car Ride Classification for Drive Context Recognition

Authors:
Stefan Haas
Kevin Wiesner
Thomas Christian Stone

Keywords: Context-aware Vehicle; Spatial Clustering; Drive Context Prediction

Abstract:
The automotive domain, with its more and more increasing number of comfort and infotainment functions, offers a field of opportunities for learning and context-sensitive functions. In this respect, personal and frequent trips of drivers provide very promising and interesting contexts. To identify frequent driving contexts in a set of recorded GPS tracks, this paper presents two different clustering algorithms: First, a hierarchical Drive-Clustering, which combines drives based on their number of common GPS points. Second, a Start-Stop-Clustering, which combines trips with the same start- and stop-cluster utilizing density based clustering. Especially the Start-Stop-Clustering showed particularly good results, as it does not depend on the concrete routes taken to a stop position and it is able to detect more trip clusters. To predict these trip contexts, a Bayesian network is presented and evaluated, with logged trip data of 21 drivers. The Bayes classifier uses context information such as the time, weekday and the number of persons in the car, to predict the most likely trip-context and thus achieves a good accuracy in the prediction of the different trip contexts.

Pages: 61 to 66

Copyright: Copyright (c) IARIA, 2014

Publication date: July 20, 2014

Published in: conference

ISSN: 2308-3468

ISBN: 978-1-61208-366-7

Location: Paris, France

Dates: from July 20, 2014 to July 24, 2014