Seq2Img-DRNET: A travel time index prediction algorithm for complex road network at regional level

作者：

Highlights：

• Our method transforms time series data into image data for spatiotemporal information fusion.

• A convolutional neural network model is constructed to accurately predict the travel time index.

• Aiming at urban business districts and scenic spots prone to traffic congestion.

• The prediction accuracy is significantly higher than the existing baseline model.

摘要

•Our method transforms time series data into image data for spatiotemporal information fusion.•A convolutional neural network model is constructed to accurately predict the travel time index.•Aiming at urban business districts and scenic spots prone to traffic congestion.•The prediction accuracy is significantly higher than the existing baseline model.

论文关键词：Travel time index prediction,Feature learning network of regional complex road network,Convolution neural network,Intelligent transportation

论文评审过程：Received 16 December 2020, Revised 10 May 2021, Accepted 1 July 2021, Available online 24 July 2021, Version of Record 28 July 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115554