SAD-ARGRU: A Metro Passenger Flow Prediction Model for Graph Residual Gated Recurrent Networks

Jilin Zhang, Yanling Chen (), Shuaifeng Zhang and Yang Zhang
Additional contact information
Jilin Zhang: School of Transportation, Fujian University of Technology, Fuzhou 350118, China
Yanling Chen: School of Transportation, Fujian University of Technology, Fuzhou 350118, China
Shuaifeng Zhang: School of Transportation, Fujian University of Technology, Fuzhou 350118, China
Yang Zhang: School of Transportation, Fujian University of Technology, Fuzhou 350118, China

Mathematics, 2024, vol. 12, issue 8, 1-22

Abstract: This paper proposes a graph residual gated recurrent network subway passenger flow prediction model considering the flat-peak characteristics, which firstly proposes the use of an adaptive density clustering method, which is capable of dynamically dividing the flat-peak time period of subway passenger flow. Secondly, this paper proposes graph residual gated recurrent network, which uses a graph convolutional network fused with a residual network and combined with a gated recurrent network, to simultaneously learn the temporal and spatial characteristics of passenger flow. Finally, this paper proposes to use the spatial attention mechanism to learn the spatial features around the subway stations, construct the spatial local feature components, and fully learn the spatial features around the stations to realize the local quantization of the spatial features around the subway stations. The experimental results show that the graph residual gated recurrent network considering the flat-peak characteristics can effectively improve the prediction performance of the model, and the method proposed in this paper has the highest prediction accuracy when compared with the traditional prediction model.

Keywords: spatial attention mechanism; local character component; graph convolutional network; gate recurrent unit (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/12/8/1175/pdf (application/pdf)
https://www.mdpi.com/2227-7390/12/8/1175/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:12:y:2024:i:8:p:1175-:d:1375460

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().