AbstractUrban traffic congestion is one of the most severe problems of everyday life in Metropolitan areas. In an effort to deal with this problem, intelligent transportation systems (ITS) technologies have concentrated in recent years on dealing with urban congestion. One of the most critical aspects of ITS success is the provision of accurate real-time information and short-term predictions of traffic parameters such as traffic volumes, travel speeds and occupancies. The present paper concentrates on developing flexible and explicitly multivariate time-series state space models using core urban area loop detector data. Using 3-min volume measurements from urban arterial streets near downtown Athens, models were developed that feed on data from upstream detectors to improve on the predictions of downstream locations. The results clearly suggest that different model specifications are appropriate for different time periods of the day. Further, it also appears that the use of multivariate state space models improves on the prediction accuracy over univariate time series ones.
A multivariate state space approach for urban traffic flow modeling and prediction
Tramsportation Research, Part C: Emerging Technologies ; 11 , 2 ; 121-135
2002-04-29
15 pages
Article (Journal)
Electronic Resource
English
A multivariate state space approach for urban traffic flow modeling and prediction
Online Contents | 2003
|Multivariate Vehicular Traffic Flow Prediction: Evaluation of ARIMAX Modeling
Online Contents | 2001
|Multivariate Vehicular Traffic Flow Prediction: Evaluation of ARIMAX Modeling
Transportation Research Record | 2001
|Traffic flow prediction method for multivariate traffic flow spatio-temporal data information
European Patent Office | 2024
|