Big Transportation Data Analytics
Traffic volume data is crucial in many applications, including transportation operation analysis, congestion management, accident prevention, etc. Yet an extensive capture of accurate volume information on a large-scale network can be difficult and costly. This research focuses on hourly traffic volume prediction in a statewide network using spatial-temporal features and heterogenous data sources. The authors present a classic machine learning technique - support vector machine (SVM) and compare its efficiency for traffic volume prediction with traditional estimation method. Further, the study develops an innovative spatial prediction method. The method is built off a state-of-the-art tree ensemble model - extreme gradient boosting tree (XGBoost) - to handle the large-scale features and hourly traffic volume samples. Moreover, spatial dependency among road segments is considered using graph theory. Specifically, the authors created a traffic network graph leveraging probe trajectory data and implemented a graph-based approach - breadth first search (BFS) - to search neighboring sites in this graph for computing spatial dependency. The proposed spatial dependency feature is subsequently incorporated as a new feature fed into XGBoost. The proposed methods are applied to 101 continuous count station (CCS) sites in the State of Utah. Prediction accuracy and training time are compared across the proposed models.
- Record URL:
- Record URL:
-
Supplemental Notes:
- This document was sponsored by the U.S. Department of Transportation, University Transportation Centers Program.
-
Corporate Authors:
University of Utah, Salt Lake City
Department of Civil and Environmental Engineering
Salt Lake City, UT United States North Dakota State University
Fargo, ND United States 58108Office of the Assistant Secretary for Research and Technology
University Transportation Centers Program
Department of Transportation
Washington, DC United States 20590 -
Authors:
- Liu, Xiaoyue Cathy
- Yi, Zhiyan
- Publication Date: 2021-3
Language
- English
Media Info
- Media Type: Digital/other
- Edition: Final Report
- Features: Appendices; Figures; References; Tables;
- Pagination: 42p
Subject/Index Terms
- TRT Terms: Data analysis; Machine learning; Mathematical prediction; Spatial analysis; Traffic data; Traffic forecasting; Traffic volume; Vehicle trajectories
- Geographic Terms: Utah
- Subject Areas: Data and Information Technology; Highways; Operations and Traffic Management; Planning and Forecasting;
Filing Info
- Accession Number: 01769067
- Record Type: Publication
- Report/Paper Numbers: MPC-543, MPC 21-428
- Files: UTC, NTL, TRIS, ATRI, USDOT
- Created Date: Apr 5 2021 10:55AM