Next Article in Journal
Vulnerability Assessment to Climate Variability and Climate Change in Tijuana, Mexico
Next Article in Special Issue
Engaging in Pro-Environment Travel Behaviour Research from a Psycho-Social Perspective: A Review of Behavioural Variables and Theories
Previous Article in Journal
Changes in Risk Perception of Seoul National University Students in Nuclear Power under Opposing Government Policy
Previous Article in Special Issue
Persuasive Technologies for Sustainable Mobility: State of the Art and Emerging Trends
Open AccessArticle

Driving Behaviour Style Study with a Hybrid Deep Learning Framework Based on GPS Data

1
Key Laboratory of Road and Traffic Engineering of the Ministry of Education, Tongji University, Shanghai 200092, China
2
Institute of Intelligent Transportation Systems, Zhejiang University, Hangzhou 310058, China
*
Author to whom correspondence should be addressed.
Sustainability 2018, 10(7), 2351; https://doi.org/10.3390/su10072351
Received: 29 March 2018 / Revised: 7 June 2018 / Accepted: 13 June 2018 / Published: 6 July 2018
(This article belongs to the Special Issue Travel Behaviour and Sustainable Transport of the Future)
Innovative technologies and traffic data sources provide great potential to extend advanced strategies and methods in travel behaviour research. Considering the increasing availability of real-time vehicle trajectory data and stimulated by the advances in the modelling and analysis of big data, this paper developed a hybrid unsupervised deep learning model to study driving bahaviour and risk patterns. The approach combines Autoencoder and Self-organized Maps (AESOM), to extract latent features and classify driving behaviour. The specialized neural networks are applied to data from 4032 observations collected from Global Positioning System (GPS) sensors in Shenzhen, China. In two case studies, improper vehicle lateral position maintenance, speeding and inconsistent or excessive acceleration and deceleration have been identified. The experiments have shown that back propagation through multi-layer autoencoders is effective for non-linear and multi-modal dimensionality reduction, giving low reconstruction errors from big GPS datasets. View Full-Text
Keywords: driving behaviour analysis; deep learning; GPS data; risk pattern; AESOM driving behaviour analysis; deep learning; GPS data; risk pattern; AESOM
Show Figures

Figure 1

MDPI and ACS Style

Guo, J.; Liu, Y.; Zhang, L.; Wang, Y. Driving Behaviour Style Study with a Hybrid Deep Learning Framework Based on GPS Data. Sustainability 2018, 10, 2351. https://doi.org/10.3390/su10072351

AMA Style

Guo J, Liu Y, Zhang L, Wang Y. Driving Behaviour Style Study with a Hybrid Deep Learning Framework Based on GPS Data. Sustainability. 2018; 10(7):2351. https://doi.org/10.3390/su10072351

Chicago/Turabian Style

Guo, Jingqiu; Liu, Yangzexi; Zhang, Lanfang; Wang, Yibing. 2018. "Driving Behaviour Style Study with a Hybrid Deep Learning Framework Based on GPS Data" Sustainability 10, no. 7: 2351. https://doi.org/10.3390/su10072351

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop