Extracting Vehicle Trip Patterns Using a Radial-based Clustering Method

Identification of recurrent vehicle trip patterns aids the characterization of travel behavior and preferences. This paper considers the development of a radial-based method to cluster vehicle geospatial data, and mine vehicle trip patterns based on origin and destination points. High-resolution vehicle GPS traces were collected through a pilot vehicle use survey in Singapore using on-board data loggers. The clustering methodology presented in the paper is applicable in the current scenario wherein clusters of location points are adjacent to each other, have different densities, and the number of clusters is unknown. The GPS data points were clustered for specific regions of interest located within a specific locale or radius; the spatial information of origin and destination points, and a radius were considered as the input of the algorithm. The radii of the origin and destination clusters were estimated based on the lag between the GPS and engine sensor recordings by the device at the start and end of trips, respectively. Finally, a percentile rule was applied to appropriately quantify these values specific for each vehicle. The radius was found to be unique for individual sample vehicles. Moreover, the effect of cluster radius on the number of clusters formed was found to be significant. These results were plotted using mapping software – Google Earth™ – to visualize the trip patterns. The algorithm was validated by matching the origin and destination points of most frequently occurring origin-destination pairs assessed by the algorithm, which in this case were the drivers’ home and work locations.

• 
• Supplemental Notes:
  • This paper was sponsored by TRB committee ABJ70 Standing Committee on Artificial Intelligence and Advanced Computing Applications.
• Corporate Authors:

  Transportation Research Board

  500 Fifth Street, NW
  Washington, DC  United States  20001
• Authors:
  • Verma, Aman
  • Cheah, Lynette
• Conference:
  • Transportation Research Board 95th Annual Meeting
  • Location: Washington DC, United States
  • Date: 2016-1-10 to 2016-1-14
• Date: 2016

Language

• English

Media Info

• Media Type: Digital/other
• Features: Figures; References; Tables;
• Pagination: 17p
• Monograph Title: TRB 95th Annual Meeting Compendium of Papers

Subject/Index Terms

• TRT Terms: Algorithms; Cluster analysis; Digital mapping; Methodology; Travel patterns
• Candidate Terms: Geospatial analysis
• Subject Areas: Data and Information Technology; Highways; I72: Traffic and Transport Planning;

Filing Info

• Accession Number: 01590336
• Record Type: Publication
• Report/Paper Numbers: 16-3514
• Files: PRP, TRIS, TRB, ATRI
• Created Date: Feb 16 2016 3:31PM