Driver behaviour prediction for motion simulators using changepoint segmentation

Hossny, Mostafa, Mohammed, Shady and Nahavandi,S 2015, Driver behaviour prediction for motion simulators using changepoint segmentation, in SMC 2015 : Big Data Analytics for Human-Centric Systems. Proceedings of the 2015 IEEE International Conference on Systems, Man, and Cybernetics, IEEE, Piscataway, N.J., pp. 457-462, doi: 10.1109/SMC.2015.91.

Attached Files
Name Description MIMEType Size Downloads

Title Driver behaviour prediction for motion simulators using changepoint segmentation
Author(s) Hossny, MostafaORCID iD for Hossny, Mostafa orcid.org/0000-0002-1593-6296
Mohammed, ShadyORCID iD for Mohammed, Shady orcid.org/0000-0002-8851-1635
Nahavandi,SORCID iD for Nahavandi,S orcid.org/0000-0002-0360-5270
Conference name IEEE International Conference on Systems, Man, and Cybernetics (2015 : Hong Kong, China)
Conference location Hong Kong, China
Conference dates 9-12 Oct. 2015
Title of proceedings SMC 2015 : Big Data Analytics for Human-Centric Systems. Proceedings of the 2015 IEEE International Conference on Systems, Man, and Cybernetics
Publication date 2015
Start page 457
End page 462
Total pages 6
Publisher IEEE
Place of publication Piscataway, N.J.
Keyword(s) Science & Technology
Technology
Computer Science, Cybernetics
Computer Science, Information Systems
Computer Science, Theory & Methods
Computer Science
Human Machine Interaction
Driver Behaviour Prediction
Particle Filter
Changepoint Approach
Summary Driving phenomenon is a repetitive process, that permits sequential learning under identifying the proper change periods. Sequential filtering is widely used for tracking and prediction of state dynamics. However, it suffers at abrupt changes, which cause sudden incremental prediction error. We provide a sequential filtering approach using online Bayesian detection of change points to decrease prediction error generally, and specifically at abrupt changes. The approach learns from optimally detected segments for identifying driving behaviour. Change points detection is done by the Pruned Exact Linear Time algorithm. Computational cost of our approach is bounded by the cost of the implemented sequential filter. This computational performance is suitable to the online nature of motion simulator's delay reduction. The approach was tested on a simulated driving scenario using Vortex by CM Labs. The state dimensions are simulated 2D space coordinates, and velocity. Particle filter was used for online sequential filtering. Prediction results show that change-point detection improves the quality of state estimation compared to traditional sequential filters, and is more suitable for predicting behavioural activities.
ISBN 9781479986965
ISSN 1062-922X
Language eng
DOI 10.1109/SMC.2015.91
Field of Research 091302 Automation and Control Engineering
Socio Economic Objective 970101 Expanding Knowledge in the Mathematical Sciences
HERDC Research category E1 Full written paper - refereed
ERA Research output type E Conference publication
Copyright notice ©2015, IEEE
Persistent URL http://hdl.handle.net/10536/DRO/DU:30082491

Document type: Conference Paper
Collections: Centre for Intelligent Systems Research
GTP Research
Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 1 times in TR Web of Science
Scopus Citation Count Cited 1 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 369 Abstract Views, 6 File Downloads  -  Detailed Statistics
Created: Wed, 20 Apr 2016, 12:45:56 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.