- Title
- Adaptive spatio-temporal graph learning for bus station profiling
- Creator
- Hou, Mingliang; Xia, Feng; Chen, Xin; Saikrishna, Vidya; Chen, Honglong
- Date
- 2024
- Type
- Text; Journal article
- Identifier
- http://researchonline.federation.edu.au/vital/access/HandleResolver/1959.17/204864
- Identifier
- vital:20103
- Identifier
-
https://doi.org/10.1145/3636459
- Identifier
- ISSN:2374-0353 (ISSN)
- Abstract
- Understanding and managing public transportation systems require capturing complex spatio-temporal correlations within datasets. Existing studies often use predefined graphs in graph learning frameworks, neglecting shifted spatial and long-term temporal correlations, which are crucial in practical applications. To address these problems, we propose a novel bus station profiling framework to automatically infer the spatio-temporal correlations and capture the shifted spatial and long-term temporal correlations in the public transportation dataset. The proposed framework adopts and advances the graph learning structure through the following innovative ideas: (1) designing an adaptive graph learning mechanism to capture the interactions between spatio-temporal correlations rather than relying on pre-defined graphs, (2) modeling shifted correlation in shifted spatial graphs to learn fine-grained spatio-temporal features, and (3) employing self-attention mechanism to learn the long-term temporal correlations preserved in public transportation data. We conduct extensive experiments on three real-world datasets and exploit the learned profiles of stations for the station passenger flow prediction task. Experimental results demonstrate that the proposed framework outperforms all baselines under different settings and can produce meaningful bus station profiles. © 2024 held by the owner/author(s).
- Publisher
- Association for Computing Machinery
- Relation
- ACM Transactions on Spatial Algorithms and Systems Vol. 10, no. 3 (2024), p.
- Rights
- All metadata describing materials held in, or linked to, the repository is freely available under a CC0 licence
- Rights
- Copyright © 2024 held by the owner/author(s)
- Subject
- 4013 Geomatic engineering; 4601 Applied computing; Bus station; Graph learning; Intelligent transportation; Profiling; Spatio-temporal data
- Reviewed
- Hits: 94
- Visitors: 91
- Downloads: 0
Thumbnail | File | Description | Size | Format |
---|