01334442

Component

Current vehicle navigation systems receive congestion information via RDS-TMC (Radio Data System – Traffic Message Channel) to the extent that congestion is detected. A better quality of guidance would be possible, however, if short-term duration prediction of incidents were available beside information about current congestion. This study used incident duration modelling techniques for the congestion prediction problem for use in in-vehicle navigation systems. A unique database of TMC messages collected for the London road network is used in this study. A model that predicts incident duration is fitted with London TMC data using factors that affect the incident duration as explanatory variables. The prediction accuracy of the model was compared with other naive predictors. It is shown that the proposed model achieves higher prediction accuracy than the naive models. Moreover, the paper proposes avenues for future research to further improve incident duration prediction and practical recommendations to data providers.

01329018

11-3830

English

19p

2011

Transportation Research Board 90th Annual Meeting

DVD

Figures; Maps; Photos; References (37) ; Tables (6)

Advanced traveler information systems; Automobile navigation systems; Driver information systems; Highway operations; Incident detection; Time duration; Traffic congestion; Traveler information and communication systems

Radio Data System Traffic Message Channel

Predictors

London (England)

Data and Information Technology; Highways; Operations and Traffic Management; Planning and Forecasting; I72: Traffic and Transport Planning

Transportation Research Board Annual Meeting 2011 Paper #11-3830

TRIS, TRB

Feb 17 2011 6:39PM