Design and Analysis of Traffic Incident Detection Based on ADTree

For aim applied to develop Intelligent Transportation System (ITS), a traffic incident detection method based on Alternating decision tree (ADTree) algorithm is presented. Different from general decision tree, ADTree model is a decision tree algorithm based on boosting algorithm. ADTree model provide a mechanism for combining the weak hypotheses generated during boosting into a single interpretable representation. The detection performance of the ADTree was compared to multi-layer feed forward neural networks (MLFNN) and Radical Basis Function neural networks (RBFNN) which yield superior incident detection performance in the previous studies. The experimental results indicate that ADTree model is competitive with MLFNN and RBFNN.

• 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:
  • Liu, Qingchao
  • Wong, Qianwen
  • Lu, Jian
  • Chen, Long
  • Jiang, Haobin
  • Chen, Shuyan
• Conference:
  • Transportation Research Board 96th Annual Meeting
  • Location: Washington DC, United States
  • Date: 2017-1-8 to 2017-1-12
• Date: 2017

Language

• English

Media Info

• Media Type: Digital/other
• Features: Figures; References; Tables;
• Pagination: 20p
• Monograph Title: TRB 96th Annual Meeting Compendium of Papers

Subject/Index Terms

• TRT Terms: Algorithms; Decision trees; Incident detection; Neural networks
• Subject Areas: Data and Information Technology; Highways; Operations and Traffic Management;

Filing Info

• Accession Number: 01627624
• Record Type: Publication
• Report/Paper Numbers: 17-03100
• Files: TRIS, TRB, ATRI
• Created Date: Feb 27 2017 5:12PM