Vehicle travel time on arterial roads is a crucial parameter for traffic management and traveler information systems. A travel time distribution is an effective way to represent the essential properties of this parameter. This paper proposes a modified Gaussian Mixture Model for representing travel time distributions on arterial roads with signalized intersections. The proposed model is applicable to travel time data from both fixed and mobile sensors. The performance of the model was evaluated using real travel time measurements from fixed sensors in the field and virtual mobile sensor data generated from those real-world measurements. The evaluation results show very good performance of the model in representing the traffic state on arterial roads. The model can be applied to historical datasets to estimate the amount of stop time and non-stop time for vehicles on arterial links during a specific time period, which is useful information for a variety of traffic applications, such as arterial travel time prediction and arterial traffic energy/emission estimation.
Arterial roadway travel time distribution estimation and vehicle movement classification using a modified Gaussian Mixture Model
2013-10-01
956598 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Arterial Travel Time Estimation Using SCATS Detectors
ASCE | 2002
|Real-Time Prediction of Arterial Roadway Travel Times Using Data Collected by Bluetooth Detectors
Transportation Research Record | 2014
|Taylor & Francis Verlag | 2012
|