Measuring variability in urban traffic flow by use of principal component analysis

Tsekeris, T; Stathopoulos, A

dc.contributor.author	Tsekeris, T	en
dc.contributor.author	Stathopoulos, A	en
dc.date.accessioned	2014-03-01T01:55:26Z
dc.date.available	2014-03-01T01:55:26Z
dc.date.issued	2006	en
dc.identifier.issn	10948848	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/27731
dc.relation.uri	http://www.scopus.com/inward/record.url?eid=2-s2.0-33845979473&partnerID=40&md5=159293faf2d23ab61694da519f71809e	en
dc.subject	Principal component analysis	en
dc.subject	Smoothing models	en
dc.subject	Traffic flow variability	en
dc.subject	Urban networks	en
dc.title	Measuring variability in urban traffic flow by use of principal component analysis	en
heal.type	journalArticle	en
heal.publicationDate	2006	en
heal.abstract	This paper presents a new approach for the spatiotemporal analysis of variation in traffic flow. Traffic detectors located in several arterial links of an extended urban network yield the time series of aggregate data used in the approach, which is based on the Principal Component Analysis (PCA) of these time series spanning several weeks. The analysis demonstrates the small variability in traffic flow over the whole network. The statistical analysis of common sources of temporal variation in traffic flow provides considerable insight into the properties of long-term flow dynamics. The approach was found to be capable of identifying the location and the impact of extreme events in the network.	en
heal.journalName	Journal of Transportation and Statistics	en
dc.identifier.volume	9	en
dc.identifier.issue	1	en
dc.identifier.spage	49	en
dc.identifier.epage	62	en