Multi-output bus travel time prediction with convolutional LSTM neural network

作者：

Highlights：

• Method for precise bus travel time prediction using deep learning.

• Models both cross-link (spatial) and cross-temporal correlations.

• Designed for urban areas where congestion, events, etc. highly influence flow.

• Empirically evaluated on large dataset from the Greater Copenhagen.

• Significantly outperforms the compared baseline methods.

摘要

•Method for precise bus travel time prediction using deep learning.•Models both cross-link (spatial) and cross-temporal correlations.•Designed for urban areas where congestion, events, etc. highly influence flow.•Empirically evaluated on large dataset from the Greater Copenhagen.•Significantly outperforms the compared baseline methods.

论文关键词：Bus travel time prediction,Intelligent Transport Systems,Convolutional neural network (CNN),Long short-term memory (LSTM),Deep learning

论文评审过程：Received 6 December 2017, Revised 21 November 2018, Accepted 22 November 2018, Available online 22 November 2018, Version of Record 8 December 2018.

论文官网地址：https://doi.org/10.1016/j.eswa.2018.11.028