File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1016/j.inffus.2024.102695
- Find via
Supplementary
-
Citations:
- Appears in Collections:
Article: Multimodal fusion for large-scale traffic prediction with heterogeneous retentive networks
Title | Multimodal fusion for large-scale traffic prediction with heterogeneous retentive networks |
---|---|
Authors | |
Issue Date | 13-Sep-2024 |
Publisher | Elsevier |
Citation | Information Fusion, 2024, v. 114 How to Cite? |
Abstract | Traffic speed prediction is a critical challenge in transportation research due to the complex spatiotemporal dynamics of urban mobility. This study proposes a novel framework for fusing diverse data modalities to enhance short-term traffic speed forecasting accuracy. We introduce the Heterogeneous Retentive Network (H-RetNet), which integrates multisource urban data into high-dimensional representations encoded with geospatial relationships. By combining the H-RetNet with a Gated Recurrent Unit (GRU), our model captures intricate spatial and temporal correlations. We validate the approach using a real-world Beijing traffic dataset encompassing social media, real estate, and point of interest data. Experiments demonstrate superior performance over existing methods, with the fusion architecture improving robustness. Specifically, we observe a 21.91% reduction in MSE, underscoring the potential of our framework to inform and enhance traffic management strategies. |
Persistent Identifier | http://hdl.handle.net/10722/347657 |
ISSN | 2023 Impact Factor: 14.7 2023 SCImago Journal Rankings: 5.647 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yan, Yimo | - |
dc.contributor.author | Cui, Songyi | - |
dc.contributor.author | Liu, Jiahui | - |
dc.contributor.author | Zhao, Yaping | - |
dc.contributor.author | Zhou, Bodong | - |
dc.contributor.author | Kuo, Yong-Hong | - |
dc.date.accessioned | 2024-09-26T00:30:25Z | - |
dc.date.available | 2024-09-26T00:30:25Z | - |
dc.date.issued | 2024-09-13 | - |
dc.identifier.citation | Information Fusion, 2024, v. 114 | - |
dc.identifier.issn | 1566-2535 | - |
dc.identifier.uri | http://hdl.handle.net/10722/347657 | - |
dc.description.abstract | <p>Traffic speed prediction is a critical challenge in transportation research due to the complex spatiotemporal dynamics of urban mobility. This study proposes a novel framework for fusing diverse data modalities to enhance short-term traffic speed forecasting accuracy. We introduce the Heterogeneous Retentive Network (H-RetNet), which integrates multisource urban data into high-dimensional representations encoded with geospatial relationships. By combining the H-RetNet with a Gated Recurrent Unit (GRU), our model captures intricate spatial and temporal correlations. We validate the approach using a real-world Beijing traffic dataset encompassing social media, real estate, and point of interest data. Experiments demonstrate superior performance over existing methods, with the fusion architecture improving robustness. Specifically, we observe a 21.91% reduction in MSE, underscoring the potential of our framework to inform and enhance traffic management strategies.</p><p><br></p> | - |
dc.language | eng | - |
dc.publisher | Elsevier | - |
dc.relation.ispartof | Information Fusion | - |
dc.title | Multimodal fusion for large-scale traffic prediction with heterogeneous retentive networks | - |
dc.type | Article | - |
dc.identifier.doi | 10.1016/j.inffus.2024.102695 | - |
dc.identifier.volume | 114 | - |
dc.identifier.eissn | 1872-6305 | - |
dc.identifier.issnl | 1566-2535 | - |