Travel time information is generally nonlinear and nonstationary in a dynamic environment, and therefore no consistent tendency can be easily observed. This research developed a novel approach that combined the empirical decomposition method for speed data analysis and gray theory for travel time prediction to predict the arrival time at each stop along a bus route. In addition, sensitivity analysis was performed for different numbers of stops. With an average prediction error of less than 3.5%, the experiments showed that the proposed prediction approach, which employed both historical and real-time speed data collected from the geographic positioning system, outperformed Chou's approach, which used only historical speed data. The proposed prediction method could be readily incorporated into a cell phone–based information retrieval system that indicated bus position en route as well as its arrival times at all stops.
Travel Time Prediction Using Empirical Mode Decomposition and Gray Theory
Example of National Central University Bus in Taiwan
Transportation Research Record: Journal of the Transportation Research Board
Transportation Research Record: Journal of the Transportation Research Board ; 2324 , 1 ; 11-19
2012-01-01
Article (Journal)
Electronic Resource
English
Hybrid Empirical Mode Decomposition-Neuro Model for Short-Term Travel Time Prediction on Freeways
British Library Conference Proceedings | 2005
|Travel Time Prediction Using Singular Value Decomposition
British Library Online Contents | 2006
|Trip Mode Recommendation Using Travel Time Prediction
British Library Conference Proceedings | 1996
|TRAVEL TIME PREDICTION PROGRAM, TRAVEL TIME PREDICTION DEVICE, AND TRAVEL TIME PREDICTION METHOD
European Patent Office | 2018
|