Incident Detection Method using Longitudinal Occupancy Time-Series Data

• NARIOKA Naoya

  Graduate School of Science and Technology, Tokyo Institute of Technology

• SEO Toru

  Graduate School of Science and Technology, Tokyo Institute of Technology

• KUSAKABE Takahiko

  Graduate School of Science and Technology, Tokyo Institute of Technology

• ASAKURA Yasuo

  Graduate School of Science and Technology, Tokyo Institute of Technology

抄録

Incidents frequently occur in the expressway. A fast and precise detection of incidents is required to mitigate negative impacts caused by delay of traffic managements. This study proposes an incident detection method using a non-parametric model. In the proposed method, traffic incidents are detected by developing a conditional probability function of traffic state using the long term data which is observed by traffic detectors (longitudinal occupancy time-series data). The proposed method was verified empirically using actual field data, then compared with existing incident detection methods. Analysis results show that the proposed method has high applicability due to no need of complex parameter calibrations.

収録刊行物

• Journal of the Eastern Asia Society for Transportation Studies

  Journal of the Eastern Asia Society for Transportation Studies 10 (0), 1720-1733, 2013

  Eastern Asia Society for Transportation Studies

キーワード

• incident detection
• longitudinal time-series data
• traffic detector
• non-parametric model

詳細情報

• CRID: 1390001205289495040
• NII論文ID: 130003384773
• DOI: 10.11175/easts.10.1720
• ISSN: 18811124
• 本文言語コード: en
• データソース種別:
  • JaLC
  • CiNii Articles
  • KAKEN
• 抄録ライセンスフラグ: 使用不可