Skip to main content
placeholder image

Towards Attention based ConvLSTM for Long-Term Travel Time Prediction of Bus Journey

Journal Article


Download full-text (Open Access)

Abstract


  • Travel time prediction is critical for advanced travelerinformation systems (ATISs), which

    provides valuable information for enhancing the efficiency and effectiveness of the urban

    transportation systems. However, in the area of bus trips, existing studies have focused on directly

    using the structured data to predict travel time for a single bus trip. For state‐of‐the‐art public

    transportation information systems, a bus journey generally has multiple bus trips. Additionally,

    due to the lack of study on data fusion, it is even inadequate for the development of underlying

    intelligent transportation systems. In this paper, we propose a novel framework for a hybrid data‐

    driven travel time prediction model for bus journeys based on open data. We explore a

    convolutional long short‐term memory (ConvLSTM) model with a self‐attention mechanism that

    accurately predicts the running time of each segment of the trips and the waiting time at each

    station. The model is more robust to capture long‐range dependence in time series data as well.

UOW Authors


  •   Wu, Jianqing (external author)
  •   Wu, Qiang (external author)
  •   Shen, Jun
  •   Cai, Chen (external author)

Publication Date


  • 2020

Citation


  • Wu, J., Wu, Q., Shen, J. & Cai, C. (2020). Towards Attention based ConvLSTM for Long-Term Travel Time Prediction of Bus Journey. Sensors, 20 3354-1-3354-13.

Scopus Eid


  • 2-s2.0-85086450118

Ro Full-text Url


  • https://ro.uow.edu.au/cgi/viewcontent.cgi?article=5089&context=eispapers1

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers1/4062

Start Page


  • 3354-1

End Page


  • 3354-13

Volume


  • 20

Place Of Publication


  • Switzerland

Abstract


  • Travel time prediction is critical for advanced travelerinformation systems (ATISs), which

    provides valuable information for enhancing the efficiency and effectiveness of the urban

    transportation systems. However, in the area of bus trips, existing studies have focused on directly

    using the structured data to predict travel time for a single bus trip. For state‐of‐the‐art public

    transportation information systems, a bus journey generally has multiple bus trips. Additionally,

    due to the lack of study on data fusion, it is even inadequate for the development of underlying

    intelligent transportation systems. In this paper, we propose a novel framework for a hybrid data‐

    driven travel time prediction model for bus journeys based on open data. We explore a

    convolutional long short‐term memory (ConvLSTM) model with a self‐attention mechanism that

    accurately predicts the running time of each segment of the trips and the waiting time at each

    station. The model is more robust to capture long‐range dependence in time series data as well.

UOW Authors


  •   Wu, Jianqing (external author)
  •   Wu, Qiang (external author)
  •   Shen, Jun
  •   Cai, Chen (external author)

Publication Date


  • 2020

Citation


  • Wu, J., Wu, Q., Shen, J. & Cai, C. (2020). Towards Attention based ConvLSTM for Long-Term Travel Time Prediction of Bus Journey. Sensors, 20 3354-1-3354-13.

Scopus Eid


  • 2-s2.0-85086450118

Ro Full-text Url


  • https://ro.uow.edu.au/cgi/viewcontent.cgi?article=5089&context=eispapers1

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers1/4062

Start Page


  • 3354-1

End Page


  • 3354-13

Volume


  • 20

Place Of Publication


  • Switzerland