Examining the Influence of Built Environment on Traffic Crashes: A Spatial Data Mining Approach

Data mining, a process for extracting implicit, nontrivial, previously unknown, and potentially useful information from databases, has gained the attention of transportation safety researchers. However, only a few studies have used association rule data mining for crash analysis, and the literature that specifically examines the influence of built environment on traffic crashes by applying spatial data mining techniques is very shallow. This research takes a spatial association rule data mining approach to developing on account of this influence. The approach consists of five steps: crash data aggregation, calculation of transportation D variables, extraction of spatial topological and distance relationships, numerical data discretization, and rule mining and visualization. The census block group is selected as the unit of analysis. The apriori rule mining algorithm based R package is used to mine the rules. The results show that many rules were mined for block groups with large numbers of crashes. The resulting rules use a mix of D variables, spatial distance variables, and topological variables. This suggests that multiple elements of built environment interact to influence the occurrence of crashes. The results also show that residential and commercial land use types play an essential role in the occurrence of large numbers of crashes. These land use types influence crashes through spatial distance and topological variables in combination with built environment D variables. Furthermore, the density, diversity, and design variables are not as important in the occurrence of crashes as the distance and destination variables.

• Supplemental Notes:
  • This paper was sponsored by TRB committee ABJ60 Standing Committee on Geographic Information Science and Applications.
• Corporate Authors:

  Transportation Research Board

  500 Fifth Street, NW
  Washington, DC  United States  20001
• Authors:
  • Ouyang, Yiqiang
  • Bejleri, Ilir
• 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: 20p
• Monograph Title: TRB 95th Annual Meeting Compendium of Papers

Subject/Index Terms

• TRT Terms: Built environment; Crash analysis; Crash causes; Data mining; Land use; Spatial analysis
• Geographic Terms: Miami-Dade County (Florida)
• Subject Areas: Data and Information Technology; Highways; Safety and Human Factors; I72: Traffic and Transport Planning; I82: Accidents and Transport Infrastructure;

Filing Info

• Accession Number: 01590383
• Record Type: Publication
• Report/Paper Numbers: 16-6530
• Files: TRIS, TRB, ATRI
• Created Date: Feb 17 2016 11:59AM