A Trade-off between Accuracy and Complexity: Short-term Traffic Flow Prediction with Spatio-temporal Correlations

Duan, P; Mao, G; Zhang, C; Kang, J

A Trade-off between Accuracy and Complexity: Short-term Traffic Flow Prediction with Spatio-temporal Correlations

Duan, P Mao, G

Zhang, C Kang, J

Permalink

Publication Type:: Conference Proceeding
Citation:: IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC, 2018, 2018-November pp. 1658 - 1663
Issue Date:: 2018-12-07

Closed Access

	Filename	Description	Size
	08569976.pdf	Published version	503.92 kB	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	Duan, P	en_US
dc.contributor.author	Mao, G https://orcid.org/0000-0002-3598-4949	en_US
dc.contributor.author	Zhang, C	en_US
dc.contributor.author	Kang, J	en_US
dc.date.issued	2018-12-07	en_US
dc.identifier.citation	IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC, 2018, 2018-November pp. 1658 - 1663	en_US
dc.identifier.isbn	9781728103235	en_US
dc.identifier.uri	http://hdl.handle.net/10453/133469
dc.description.abstract	© 2018 IEEE. Considering spatio-temporal correlation between traffic in different roads has benefit for building an accurate spatio-temporal model for traffic prediction. However, it implies high computational complexity for model building in the context of a complicated network topology, e.g., urban network. Hence, this paper develops a method for capturing and quantifying the intricate spatio-temporal correlations. The contributions of this paper are as follows. First, we offer a physically intuitive approach to capture the spatio-temporal correlation between traffic in different roads, which is related to the road network topology, time-varying speed, and time-varying trip distribution. With this approach, only the parameters, namely time-varying lags, in our STARIMA (Space-Time Autoregressive Integrated Moving Average) based model should be adjusted in different time periods of the day. It guarantees the prediction accuracy and makes the predictor readily amendable to suit changing road and traffic conditions. Second, a metric named traffic transition probability calculated based on trip distribution, as well as a threshold \varepsilon are applied for selecting the most spatio-temporally correlated neighbors of a target road. Thus, the complexity of model building will be reduced dramatically. Trace-driven experiments are conducted from two aspects. First, our proposed prediction method has superior accuracy compared with ARIMA and the back propagation neural network model (BPNN) based method, but has much reduced computational complexity. Second, the results show that the prediction accuracy is not always proportional to the increase in the number of spatial neighbors considered for a target road. The trade-off between accuracy and complexity depends on the configuration of \varepsilon.	en_US
dc.relation.ispartof	IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC	en_US
dc.relation.isbasedon	10.1109/ITSC.2018.8569976	en_US
dc.rights	info:eu-repo/semantics/closedAccess
dc.title	A Trade-off between Accuracy and Complexity: Short-term Traffic Flow Prediction with Spatio-temporal Correlations	en_US
dc.type	Conference Proceeding
utslib.citation.volume	2018-November	en_US
utslib.for	0805 Distributed Computing	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
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/School of Electrical and Data Engineering
pubs.organisational-group	/University of Technology Sydney/Strength - CRIN - Realtime Information Networks
utslib.copyright.status	closed_access	*
pubs.publication-status	Published	en_US
pubs.volume	2018-November	en_US

Abstract:

© 2018 IEEE. Considering spatio-temporal correlation between traffic in different roads has benefit for building an accurate spatio-temporal model for traffic prediction. However, it implies high computational complexity for model building in the context of a complicated network topology, e.g., urban network. Hence, this paper develops a method for capturing and quantifying the intricate spatio-temporal correlations. The contributions of this paper are as follows. First, we offer a physically intuitive approach to capture the spatio-temporal correlation between traffic in different roads, which is related to the road network topology, time-varying speed, and time-varying trip distribution. With this approach, only the parameters, namely time-varying lags, in our STARIMA (Space-Time Autoregressive Integrated Moving Average) based model should be adjusted in different time periods of the day. It guarantees the prediction accuracy and makes the predictor readily amendable to suit changing road and traffic conditions. Second, a metric named traffic transition probability calculated based on trip distribution, as well as a threshold \varepsilon are applied for selecting the most spatio-temporally correlated neighbors of a target road. Thus, the complexity of model building will be reduced dramatically. Trace-driven experiments are conducted from two aspects. First, our proposed prediction method has superior accuracy compared with ARIMA and the back propagation neural network model (BPNN) based method, but has much reduced computational complexity. Second, the results show that the prediction accuracy is not always proportional to the increase in the number of spatial neighbors considered for a target road. The trade-off between accuracy and complexity depends on the configuration of \varepsilon.

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

http://hdl.handle.net/10453/133469