Joint Estimation of Paths and Travel Times with Bluetooth Traffic Monitoring

While Bluetooth data sets facilitate the estimation of travel times across sensor pairs, the resulting estimations contain noise because of the data quality and missed detection probability. Additionally, estimating vehicle paths from Bluetooth records is not a straightforward task.This paper proposes a joint method to simultaneously infer vehicle paths and estimate travel times using Bluetooth records. Path inference requires a priori information on link travel times; biased estimation of a priori information might lead to unrealistic shortest paths and deteriorate the quality of the estimated link travel times. The iterative application of path inference and travel time allocation methods is expected to converge to a fixed point solution where the input and output travel times are practically the same. The methodology is applied in a case study of Bluetooth measurements in Brisbane, Australia. The results clearly show that the proposed model quickly converges to a fixed-point solution, and there are relevant changes in the estimated travel times over the iterations, which highlights the importance of the joint framework. The results are also validated against ground truth travel times which are collated by creating a testing set out of the whole set. Travel time estimates are robust to the changes in the size of the available measurements, and the proposed model significantly outperforms a naive model where travel times are estimated via direct matching of Bluetooth devices across different sensors.

  • Supplemental Notes:
    • This paper was sponsored by TRB committee AHB15 Standing Committee on Intelligent Transportation Systems.
  • Corporate Authors:

    Transportation Research Board

    ,    
  • Authors:
    • Yildirimoglu, Mehmet
  • Conference:
  • Date: 2019

Language

  • English

Media Info

  • Media Type: Digital/other
  • Features: Figures; Maps; References; Tables;
  • Pagination: 16p

Subject/Index Terms

Filing Info

  • Accession Number: 01698362
  • Record Type: Publication
  • Report/Paper Numbers: 19-03806
  • Files: TRIS, TRB, ATRI
  • Created Date: Dec 7 2018 9:53AM