• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Development of a real-time crash prediction and prevention system for urban expressways

Research Project

Project/Area Number 25420535
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Research Field Civil engineering project/Traffic engineering
Research InstitutionTokyo Institute of Technology

Principal Investigator

Muromachi Yasunori  東京工業大学, 環境・社会理工学院, 准教授 (40251350)

Co-Investigator(Kenkyū-buntansha) 兵藤 哲朗  東京海洋大学, 学術研究院, 教授 (40218748)
Research Collaborator HOSSAIN Moinul  
Project Period (FY) 2013-04-01 – 2017-03-31
Project Status Completed (Fiscal Year 2016)
Budget Amount *help
¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2015: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2014: ¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000)
Fiscal Year 2013: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Keywords交通事故 / 都市高速道路 / リアルタイム / 国際研究者交流 / リアルタイム交通事故予測 / ベイジアンネットワーク
Outline of Final Research Achievements

In this research, we develop a real-time crash prediction and prevention system for urban expressways that can detect traffic conditions that are likely to occur in real time in traffic accidents, and can select and implement prevention measures highly effective in improving traffic conditions. With regard to the crash prediction system, we introduced Dynamic Bayesian Network to improve the prediction performance of the real-time crash prediction model, and the expectation maximization algorithm and adaptive algorithm to improve the robustness of the model. With regard to the crash prevention system, we developed a system that can examine the effect of improving traffic conditions by vehicle control on the whole route, using the real-time crash prediction and prevention system and simulation.

Report

(5 results)
  • 2016 Annual Research Report   Final Research Report ( PDF )
  • 2015 Research-status Report
  • 2014 Research-status Report
  • 2013 Research-status Report
  • Research Products

    (5 results)

All 2016 2015 2013 Other

All Int'l Joint Research (1 results) Journal Article (1 results) (of which Int'l Joint Research: 1 results,  Peer Reviewed: 1 results,  Acknowledgement Compliant: 1 results) Presentation (3 results)

  • [Int'l Joint Research] Islamic University of Technology(バングラデシュ)

    • Related Report
      2015 Research-status Report
  • [Journal Article] REAL-TIME CRASH PREDICTION MODEL FOR URBAN EXPRESSWAY USING DYNAMIC BAYESIAN NETWORK2016

    • Author(s)
      Roy, A., Kobayashi, R., Hossain, M., Muromachi, Y.
    • Journal Title

      Journal of Japan Society of Civil Engineers, Ser. D3 (Infrastructure Planning and Management)

      Volume: 72 Issue: 5 Pages: I_1331-I_1338

    • DOI

      10.2208/jscejipm.72.I_1331

    • NAID

      130005435577

    • ISSN
      2185-6540
    • Related Report
      2016 Annual Research Report
    • Peer Reviewed / Int'l Joint Research / Acknowledgement Compliant
  • [Presentation] The Development of Robust Real-time Crash Prediction Models with Bayesian Network2016

    • Author(s)
      Roy, A., Muromachi, Y.
    • Organizer
      土木計画学研究・講演集
    • Place of Presentation
      北海道大学
    • Year and Date
      2016-05-28
    • Related Report
      2016 Annual Research Report
  • [Presentation] Route Safety Management through Real-time Crash Prediction Model2015

    • Author(s)
      Ananya ROY, Ryosuke KOBAYASHI, Moinul HOSSAIN, Yasunori MUROMACHI
    • Organizer
      JSCE Proceedings of Infrastructure Planning
    • Place of Presentation
      福岡
    • Year and Date
      2015-06-06
    • Related Report
      2015 Research-status Report
  • [Presentation] ベイジアンネットワークを用いたリアルタイム交通事故予測モデルの構築2013

    • Author(s)
      小林涼介・室町泰徳
    • Organizer
      第48回土木計画学研究発表会
    • Place of Presentation
      大阪市立大学
    • Related Report
      2013 Research-status Report

URL: 

Published: 2014-07-25   Modified: 2022-02-22  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi