원문정보
초록
영어
In this study, we characterized traffic density modeled from coarse data by using data signatures to effectively and efficiently represent traffic flow behavior. Using the 2006 North Luzon Expressway North Bound (NLEX NB) Balintawak (Blk), Bocaue (Boc), Meycauayan (Mcy), and Marilao (Mrl) segments' hourly traffic volume and time mean speed data sets provided by the National Center for Transportation Studies (NCTS), we generated hourly traffic density data set. Each point in the data was represented by a 4D data signature where cluster models and 2D visualizations were formulated and varying traffic density behaviors were identified, i.e. high and low traffic congestions, outliers, etc. Best-fit curves, confidence bands and ellipses were generated in the visualizations for additional cluster information. From a finer-grained 6-minute interval NLEX Blk-NB density data set, the coarser-grained hourly density data set of Blk was validated for consistency and correctness of results. Finally, we ascertained probable causes of the behaviors to provide insights for better traffic management in the expressway.
목차
1. Introduction
1.1. Definitions
2. Methodology
2.1. Building Effective Density Models from Sparse Data Points
2.2. Data signature-based clustering and visualization of the density models
3. Results and Discussions
3.1. Graphs of the segments’ density data sets
3.2. Data Signature-based Visualization Models
4. Conclusions and Recommendations
Acknowledgements
References