Spatio-Temporal Clustering of Traffic Networks

Venkatasubramaniam, A., Evers, L. and Ampountolas, K. (2017) Spatio-Temporal Clustering of Traffic Networks. 32nd International Workshop on Statistical Modelling (IWSM), Groningen, The Netherlands, 3-7 Jul 2017.

[img] Text
164206.pdf - Accepted Version
Restricted to Repository staff only


Publisher's URL:


We present a novel Bayesian clustering method for spatio-temporal data observed on a network and apply this model to cluster an urban traffic network. This method employs a distance dependent Chinese restaurant process (DDCRP) to provide a cluster structure, by incorporating the observed data and geographic constraints of the network. However, in order to fully capture the dependency structure of the data, a conditional auto-regressive model (CAR) is used to model the spatial dependency within each cluster.

Item Type:Conference or Workshop Item
Additional Information:Research funded by the Lord Kelvin Adam Smith scholarship, University of Glasgow, 2014-2018
Keywords:Bayesian, distance-dependent Chinese restaurant process (DDCRP), network, clustering, spatial, temporal, congestion
Glasgow Author(s) Enlighten ID:Ampountolas, Dr Konstantinos and Evers, Dr Ludger and Venkatasubramaniam, Ashwini
Authors: Venkatasubramaniam, A., Evers, L., and Ampountolas, K.
College/School:College of Science and Engineering
College of Science and Engineering > School of Engineering > Infrastructure and Environment
College of Science and Engineering > School of Mathematics and Statistics > Statistics
Related URLs:

University Staff: Request a correction | Enlighten Editors: Update this record

Project CodeAward NoProject NamePrincipal InvestigatorFunder's NameFunder RefLead Dept
651922Urban Big Data Research CentrePiyushimita ThakuriahEconomic and Social Research Council (ESRC)ES/L011921/1SPS - URBAN STUDIES