Graph modelling approaches for motorway traffic flow prediction

Mihaita, A-S; Papachatgis, Z; Rizoiu, M-A

Graph modelling approaches for motorway traffic flow prediction

Mihaita, A-S Papachatgis, Z Rizoiu, M-A

Permalink

Publication Type:: Conference Proceeding
Citation:: In 23rd IEEE International Conference on Intelligent Transportation Systems (ITSC'20) (pp. 1--8). Rhodes, Greece (2020)

Closed Access

	Filename	Description	Size
	MIHAITA_ITSC-20.pdf	Accepted version	4.37 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Mihaita, A-S
dc.contributor.author	Papachatgis, Z
dc.contributor.author	Rizoiu, M-A
dc.date.accessioned	2021-01-20T04:54:44Z
dc.date.available	2021-01-20T04:54:44Z
dc.identifier.citation	In 23rd IEEE International Conference on Intelligent Transportation Systems (ITSC'20) (pp. 1--8). Rhodes, Greece (2020)
dc.identifier.uri	http://hdl.handle.net/10453/145503
dc.description.abstract	Traffic flow prediction, particularly in areas that experience highly dynamic flows such as motorways, is a major issue faced in traffic management. Due to increasingly large volumes of data sets being generated every minute, deep learning methods have been used extensively in the latest years for both short and long term prediction. However, such models, despite their efficiency, need large amounts of historical information to be provided, and they take a considerable amount of time and computing resources to train, validate and test. This paper presents two new spatial-temporal approaches for building accurate short-term prediction along a popular motorway in Sydney, by making use of the graph structure of the motorway network (including exits and entries). The methods are built on proximity-based approaches, denoted backtracking and interpolation, which uses the most recent and closest traffic flow information for each of the target counting stations along the motorway. The results indicate that for short-term predictions (less than 10 minutes into the future), the proposed graph-based approaches outperform state-of-the-art deep learning models, such as long-term short memory, convolutional neuronal networks or hybrid models.
dc.language	en
dc.relation	http://purl.org/au-research/grants/arc/LP180100114
dc.relation.ispartof	In 23rd IEEE International Conference on Intelligent Transportation Systems (ITSC'20) (pp. 1--8). Rhodes, Greece (2020)
dc.rights	info:eu-repo/semantics/closedAccess
dc.title	Graph modelling approaches for motorway traffic flow prediction
dc.type	Conference Proceeding
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/A/DRsch The Data Science Institute
pubs.organisational-group	/University of Technology Sydney
utslib.copyright.status	closed_access	*
dc.date.updated	2021-01-20T04:54:13Z

Abstract:

Traffic flow prediction, particularly in areas that experience highly dynamic flows such as motorways, is a major issue faced in traffic management. Due to increasingly large volumes of data sets being generated every minute, deep learning methods have been used extensively in the latest years for both short and long term prediction. However, such models, despite their efficiency, need large amounts of historical information to be provided, and they take a considerable amount of time and computing resources to train, validate and test. This paper presents two new spatial-temporal approaches for building accurate short-term prediction along a popular motorway in Sydney, by making use of the graph structure of the motorway network (including exits and entries). The methods are built on proximity-based approaches, denoted backtracking and interpolation, which uses the most recent and closest traffic flow information for each of the target counting stations along the motorway. The results indicate that for short-term predictions (less than 10 minutes into the future), the proposed graph-based approaches outperform state-of-the-art deep learning models, such as long-term short memory, convolutional neuronal networks or hybrid models.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/145503