Development of traffic accidents prediction model with intelligent system theory

  • Authors:
  • SooBeom Lee;TaiSik Lee;Hyung Jin Kim;YoungKyun Lee

  • Affiliations:
  • Dept. of Transportation Engineering, Univ. of Seoul, Korea;Dept. of Civil and Environment Engineering, Hanyang Univ., Korea;Dept of Urban Planning and Engineering, Yonsei Univ., Korea;ITS Policy and Program Division, Ministry of Construction & Transportation, Kwacheon

  • Venue:
  • ICCSA'05 Proceedings of the 2005 international conference on Computational Science and Its Applications - Volume Part II
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

It is important to clarify the relationship between traffic accidents and various influencing factors in order to reduce the number of traffic accidents. This study developed a traffic accident frequency prediction model using multi-linear regression and quantification theories which are commonly applied in the field of traffic safety to verify the influences of various factors in the traffic accident frequency. The data was collected on the Korean National Highway 17 which shows the highest accident frequency and fatality in Chonbuk Province. In order to minimize the uncertainty of the data, the fuzzy theory and neural network theory were applied. The neural network theory can provide fair learning performance by modeling the human neural system mathematically. In conclusion, this study focused on the practicability of the fuzzy reasoning theory and the neural network theory for traffic safety analysis.