Traffic State Prediction Using Markov Chain Models
2007 (English)In: Proceedings of the European Control Conference 2007, 2007, 2428-2435 p.Conference paper (Refereed)
Motorway traffic management and control relieson models that estimate and predict traffic conditions. In thispaper, a methodology for the identification and short-termprediction of the traffic state is presented. The methodologycombines model-based clustering, variable-length Markovchains and nearest neighbor classification. An application ofthe methodology for short-term speed prediction in a freewaynetwork in Irvine, CA, shows encouraging results.
Place, publisher, year, edition, pages
2007. 2428-2435 p.
Transport Systems and Logistics
IdentifiersURN: urn:nbn:se:kth:diva-88168OAI: oai:DiVA.org:kth-88168DiVA: diva2:502157
European Control Conference 2007, Kos, Greece, July 2-5, 2007
TSC import 1997 2012-02-14. QC 201205222012-02-142012-02-142012-05-22Bibliographically approved