Learning risky driver behaviours from multi-channel data streams using genetic programming

Xie, F, Song, A, Salim, F, Bouguettaya, A, Sellis, T and Bradbrook, D 2013, 'Learning risky driver behaviours from multi-channel data streams using genetic programming', Lecture Notes in Computer Science, vol. 8272, pp. 202-213.


Document type: Journal Article
Collection: Journal Articles

Title Learning risky driver behaviours from multi-channel data streams using genetic programming
Author(s) Xie, F
Song, A
Salim, F
Bouguettaya, A
Sellis, T
Bradbrook, D
Year 2013
Journal name Lecture Notes in Computer Science
Volume number 8272
Start page 202
End page 213
Total pages 12
Publisher Springer
Abstract Risky driver behaviours such as sudden braking, swerving, and excessive acceleration are a major risk to road safety. In this study, we present a learning method to recognize such behaviours from smartphone sensor input which can be considered as a type of multi-channel time series. Unlike other learning methods, this Genetic Programming (GP) based method does not require pre-processing and manually designed features. Hence domain knowledge and manual coding can be significantly reduced by this approach. This method can achieve accurate real-time recognition of risky driver behaviours on raw input and can outperform classic learning methods operating on features. In addition this GP-based method is general and suitable for detecting multiple types of driver behaviours.
Subject Interorganisational Information Systems and Web Services
DOI - identifier 10.1007/978-3-319-03680-9_22
Copyright notice © Springer International Publishing Switzerland 2013
ISSN 0302-9743
Versions
Version Filter Type
Altmetric details:
Access Statistics: 111 Abstract Views  -  Detailed Statistics
Created: Tue, 21 Jan 2014, 08:43:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us