Mining and Learning from Railway Safety Data with Graphs and Tensors

Railway systems are very complex pieces of cyberinfrastructure, interfacing with a number of transportation agents and other pieces of cyberinfrastructure. For instance, a railway crossing includes interactions between the railway system and a traffic intersection. Such a rich ecosystem of interactions among heterogeneous agents poses fascinating research challenges in modeling railway systems with data and conducting data-driven railway crossing safety assessment. In this project, the authors leverage and extend powerful tensor and graph mining methods which can extract “needles in the haystack” within the abundance of collected data and produce actionable insights to better understand emerging accident patterns from historical data, identify underlying similarities in such patterns.

• Record URL:
  • https://www.utrgv.edu/railwaysafety/_files/documents/reports/mining-and-learning-from-railway-safety-data_093024.pdf
• Record URL:
  • https://rosap.ntl.bts.gov/view/dot/79292
• Supplemental Notes:
  • This document was sponsored by the U.S. Department of Transportation, University Transportation Centers Program.
• Corporate Authors:

  University of California Riverside

  Center for Environmental Research and Technology
  Riverside, CA  United States  92507

  University Transportation Center for Railway Safety

  University of Texas, Rio Grande Valley
  1201 W. University Dr.
  Edinburg, TX  United States  78539

  Office of the Assistant Secretary for Research and Technology

  Department of Transportation
  1200 New Jersey Avenue, SE
  Washington, DC  United States  20590
• Authors:
  • Chen, Jia
  • Papalexakis, Evangelos
• Publication Date: 2024-9-15

Language

• English

Media Info

• Media Type: Digital/other
• Edition: Final Report
• Features: Figures; References; Tables;
• Pagination: 15p

Subject/Index Terms

• TRT Terms: At grade intersections; Data mining; Data science; Graph theory; Risk assessment; Safety analysis
• Subject Areas: Data and Information Technology; Railroads; Safety and Human Factors;

Filing Info

• Accession Number: 01940831
• Record Type: Publication
• Report/Paper Numbers: UTCRS-UCR-O2CY23
• Contract Numbers: 69A3552348340
• Files: UTC, NTL, TRIS, USDOT
• Created Date: Dec 23 2024 5:04PM