Multi-attention graph neural networks for city-wide bus travel time estimation using limited data

作者：

Highlights：

• First time to achieve city-wide bus travel time prediction with limited data.

• First time to build bus networks based on a graph for travel time prediction.

• A spatial–temporal graph attention network to learn travel patterns from each other.

• Test results show the model can accurately predict bus travel time with limited data.

摘要

•First time to achieve city-wide bus travel time prediction with limited data.•First time to build bus networks based on a graph for travel time prediction.•A spatial–temporal graph attention network to learn travel patterns from each other.•Test results show the model can accurately predict bus travel time with limited data.

论文关键词：Bus travel time prediction,Graph neural network,Multi-attention,Sparse data

论文评审过程：Received 31 October 2021, Revised 16 February 2022, Accepted 28 March 2022, Available online 9 April 2022, Version of Record 27 April 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117057