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

Deep learning model for accident risk prediction

Research Project

Project/Area Number 20K14851
Research Category

Grant-in-Aid for Early-Career Scientists

Allocation TypeMulti-year Fund
Review Section Basic Section 22050:Civil engineering plan and transportation engineering-related
Research InstitutionEhime University

Principal Investigator

Tsubota Takahiro  愛媛大学, 理工学研究科(工学系), 講師 (00780066)

Project Period (FY) 2020-04-01 – 2022-03-31
Project Status Completed (Fiscal Year 2021)
Budget Amount *help
¥4,030,000 (Direct Cost: ¥3,100,000、Indirect Cost: ¥930,000)
Fiscal Year 2021: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2020: ¥2,470,000 (Direct Cost: ¥1,900,000、Indirect Cost: ¥570,000)
KeywordsTraffic accident / Traffic engineering / Deep learning / 畳込みニューラルネットワーク / Accident prediction / Accident Risk / Deep Learning / 畳込ニューラルネットワーク / Traffic Safety / 交通事故リスク / 深層学習 / 高速道路 / 交通マネジメント / ビッグデータ
Outline of Research at the Start

本研究では,動的に変動する事故リスクを考慮した交通マネジメントの実装を念頭に,交通事故リスクをリアルタイムに評価可能なディープラーニングモデルを構築するとともに,同モデルの有効性を実ネットワークにおいて検証する.具体的には,都市内,および都市間高速道路を対象とし,交通流観測データや天候データ,ならびに事故データ等を長期間蓄積したビッグデータを活用して研究を遂行する.2020年度は交通工学の知見を援用しつつ,交通事故発生リスク推定モデルの構築に有効な変数の選択,および同モデルの構築に取り組む.2021年度には実道路ネットワークの実交通流を対象に,構築したモデルの推定精度を検証する.

Outline of Final Research Achievements

This study aims to build a traffic accident risk prediction model using a deep learning model and to identify input data that can contribute to improving the prediction accuracy of the model. A near-future traffic accident risk prediction model was built for an intercity expressway. The model is based on a convolutional neural network, and speed, traffic volume, and time occupancy (OCC) of vehicle detectors were used as inputs. In order to examine the impact of the quality of the input data, an analysis was conducted considering the time-varying components of the traffic conditions. The results showed that the time-varying components of traffic volume and OCC were effective in improving forecast accuracy. It was also confirmed that the output of the constructed model was generally consistent with the actual accident probability.

Academic Significance and Societal Importance of the Research Achievements

交通事故は物的・人的に多大な損失をもたらす為、事故の起こりやすさ、すなわち事故リスクを予測し、ドライバーへの情報提供や交通対策により事故の発生を未然に防ぐことが重要となる。本研究で構築した事故リスク予測モデルは近未来の事故リスクを高精度に予測する為、事故リスク低減を目指した交通管制に活用可能であると期待される。また、深層学習モデルの精度向上において、交通工学分野の知見が有用であることを示した点においても、同分野におけるAI技術の活用において重要な示唆を与えたといえる。

Report

(3 results)
  • 2021 Annual Research Report   Final Research Report ( PDF )
  • 2020 Research-status Report
  • Research Products

    (7 results)

All 2021 2020

All Journal Article (1 results) (of which Peer Reviewed: 1 results,  Open Access: 1 results) Presentation (6 results) (of which Int'l Joint Research: 3 results)

  • [Journal Article] PREDICTION OF TRAFFIC ACCIDENT LIKELIHOOD ON INTERCITY EXPRESSWAY BY CONVOLUTIONAL NEURAL NETWORK2020

    • Author(s)
      Takahiro TSUBOTA, Toshio YOSHII, Jian XING
    • Journal Title

      Intelligence, Informatics and Infrastructure

      Volume: 1 Issue: 1 Pages: 11-17

    • DOI

      10.11532/jsceiii.1.1_11

    • NAID

      130007940725

    • ISSN
      2435-9262
    • Year and Date
      2020-11-11
    • Related Report
      2020 Research-status Report
    • Peer Reviewed / Open Access
  • [Presentation] Effect of the Multicollinearity of Interaction Terms on the Performance of the ANN Model2021

    • Author(s)
      Celso Luis FERNANDO, Toshio YOSHII, Takahiro TSUBOTA, Hirotoshi SHIRAYANAGI
    • Organizer
      Proceedings of the Eastern Asia Society for Transportation Studies
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] A Factor Extraction Method using Deep Learning Technique on Traffic Accident Risk2021

    • Author(s)
      Celso Luis Fernando, Toshio Yoshii, Takahiro Tsubota, Hirotoshi Shirayanagi
    • Organizer
      2021 International Symposium on Transportation Data & Modelling (ISTDM 2021)
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Deep Learning Model for Predicting Traffic Accident Risk on an Expressway2021

    • Author(s)
      Takahiro Tsubota, Mamoru Shimmizu, Toshio Yoshii, Hirotoshi Shirayanagi
    • Organizer
      2021 International Symposium on Transportation Data & Modelling (ISTDM 2021)
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 交互作用項の多重共線性が ANN モデルのパフォーマンスに及ぼす影響2020

    • Author(s)
      Celso Luis FERNANDO, 吉井稔雄, 坪田隆宏, 白柳洋俊
    • Organizer
      第18回ITSシンポジウム2020
    • Related Report
      2020 Research-status Report
  • [Presentation] 首都高速道路におけるAIを用いたオンライン事故リスク算定モデルの構築と活用可能性の検証2020

    • Author(s)
      田中淳, 吉井稔雄, 坪田隆宏, 田畑大, 川松祐太, Chhatkuli Subas, 城所貴之
    • Organizer
      第18回ITSシンポジウム2020
    • Related Report
      2020 Research-status Report
  • [Presentation] CNNを用いた都市間高速道路の交通事故リスク予測モデル2020

    • Author(s)
      坪田 隆宏, 吉井 稔雄, XING Jian
    • Organizer
      第40回交通工学研究発表会
    • Related Report
      2020 Research-status Report

URL: 

Published: 2020-04-28   Modified: 2023-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi