Traffic flow prediction has become a hot spot in the intelligent transportation system study. In this paper, novel methods are proposed to predict traffic flow. We divide 24 hours into 4 stages according to the bimodal distribution of traffic flow, and integrate topology features of urban traffic network into 4 typical machine learning methods. Experiments on the traffic flow of Qinhuangdao city demonstrate the effectiveness and potential of the proposed methods.
Traffic flow forecast with urban transport network
01.08.2016
559667 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
MAS-Based Urban Rail Transport Ridership Forecast System and Traffic Generation Analysis
Trans Tech Publications | 2010
|The Forecast of Dynamic Traffic Flow
ASCE | 2000
|