An extreme value based neural clustering approach for identifying traffic states

Vlahogianni, EI; Karlaftis, MG; Stathopoulos, A

dc.contributor.author	Vlahogianni, EI	en
dc.contributor.author	Karlaftis, MG	en
dc.contributor.author	Stathopoulos, A	en
dc.date.accessioned	2014-03-01T02:43:06Z
dc.date.available	2014-03-01T02:43:06Z
dc.date.issued	2005	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/31237
dc.subject	Extreme Event	en
dc.subject	Extreme Value	en
dc.subject	Peak Detection	en
dc.subject	Real-time Traffic	en
dc.subject	Self Organization	en
dc.subject	Time Series	en
dc.subject.other	Boundary conditions	en
dc.subject.other	Data flow analysis	en
dc.subject.other	Data reduction	en
dc.subject.other	Information retrieval	en
dc.subject.other	Neural networks	en
dc.subject.other	Real time systems	en
dc.subject.other	Modeling congested condition	en
dc.subject.other	Real-time traffic data	en
dc.subject.other	Traffic data	en
dc.subject.other	Traffic forecasting	en
dc.subject.other	Highway traffic control	en
dc.title	An extreme value based neural clustering approach for identifying traffic states	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/ITSC.2005.1520197	en
heal.identifier.secondary	http://dx.doi.org/10.1109/ITSC.2005.1520197	en
heal.identifier.secondary	1520197	en
heal.publicationDate	2005	en
heal.abstract	Traffic data are characterized by the occurrence of extreme events and frequent shifts to and from congestion. Current practice in traffic forecasting suppresses or disregards these features. But, indications suggest that these features may encompass useful information for modeling congested condition, as well as the transitions to and from congestion. This paper proposes a self-organizing approach to clustering traffic conditions based on information acquired from the 'peaking' behavior of traffic. Primary findings suggest that traffic has a strong transitional behavior that is reflected by frequent peaks detected in time series of volume and occupancy. The main finding is that traffic can be clustered into four distinct areas of traffic characteristics: (i) free-flow, (ii) medium flow states where traffic volume fluctuates in high values and occupancy is low, (iii) medium flow states where volume fluctuates in high values but occupancy increases sharply, and (iv) congestion. The main contribution of this approach is that it enables extracting a posteriori information from real-time traffic data as it pertains to boundary traffic conditions and it clusters traffic based on the occurrence of transitional movements. © 2005 IEEE.	en
heal.journalName	IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC	en
dc.identifier.doi	10.1109/ITSC.2005.1520197	en
dc.identifier.volume	2005	en
dc.identifier.spage	1056	en
dc.identifier.epage	1061	en