A spatiotemporal hierarchical attention mechanism-based model for multi-step station-level crowd flow prediction

DOI10.1016/J.INS.2020.07.049zbMATH Open1479.76010OpenAlexW3046213253WikidataQ114386621 ScholiaQ114386621MaRDI QIDQ2054089FDOQ2054089

Authors: Yirong Zhou, Jun Li, Hao Chen, Ye Wu, Jiangjiang Wu, Luo Chen 

Publication date: 30 November 2021

Published in: Information Sciences (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.ins.2020.07.049

Recommendations

• Predicting citywide crowd flows using deep spatio-temporal residual networks
• Metro short-term traffic flow prediction with deep learning
• Multi-view metro station clustering based on passenger flows: a functional data-edged network community detection approach
• A new approach to the prediction of passenger flow in a transit system
• An interpretable model for short term traffic flow prediction

zbMATH Keywords

spatio-temporal analysismulti-output regressioncrowd-flow forecasthierarchical attention mechanismmulti-step ahead prediction

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Traffic and pedestrian flow models (76A30)

Cites Work

• Deep learning
• Inventory rebalancing and vehicle routing in bike sharing systems
• Predicting citywide crowd flows using deep spatio-temporal residual networks

Cited In (2)

• An EEMD-EWT-LSTM-based short-term prediction approach for inbound metro ridership
• Predicting citywide crowd flows using deep spatio-temporal residual networks

Uses Software

• XGBoost
• Adam
• Tensor2Tensor
• U-Net

This page was built for publication: A spatiotemporal hierarchical attention mechanism-based model for multi-step station-level crowd flow prediction

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2054089)