01660365

Component

This research adopts a functional data analysis method that is based mainly on a mixture prediction method to analyze and predict travel times; such analysis and prediction constitute an essential component in Intelligent Transportation Systems applications. The mixture prediction method is developed through three major modules, i.e., functional clustering for historical functional travel time patterns, probabilistic functional classification for newly observed travel time trajectories, and linear regression model fitting for travel time prediction.The research framework was demonstrated with data retrieved from the website under the database TDCS_M04A constructed for Taiwan Area National Freeway Bureau of Taiwan’s Ministry of Transportation and Communications. The preliminary result shows the optimal number of clusters equal to two and the best combination of observed time (?) and unobserved ( ?) time occurred at ( ?=3,?=2) with mean absolute percentage error (MAPE) equal to 7.26 and thus the usefulness of functional data analysis in analyzing and predicting the travel time trajectories on freeways is supported, similar to results obtained for the traffic flow trajectories. However, real application must be performed and intensive research on clustering, posterior cluster membership probability and different combination of (?, ?) under various traffic conditions should be conducted before a firm conclusion can be reached. Moreover, the merit of the functional data analysis, particularly the functional clustering method, may be equally applied to other “decomposition” type methods, such as Hilbert-Hwang Transform (HHT), with a hope to enhance the accuracy in prediction of travel times.

This paper was sponsored by TRB committee ABJ30 Standing Committee on Urban Transportation Data and Information Systems.

18-02142

English

4p

2018

Transportation Research Board 97th Annual Meeting

Digital/other

References

Data analysis; Freeway management systems; Mathematical prediction; Travel time

Taiwan

Highways; Operations and Traffic Management; Planning and Forecasting

Transportation Research Board Annual Meeting 2018 Paper #18-02142

TRIS, TRB, ATRI

Jan 8 2018 10:31AM