Application Research of Cross-Attention Mechanism for Traffic Prediction Based on Heterogeneous Data

Open Access

Issue		ITM Web Conf. Volume 70, 2025 2024 2^nd International Conference on Data Science, Advanced Algorithm and Intelligent Computing (DAI 2024)


Article Number		01004
Number of page(s)		7
Section		Traffic Prediction and Analysis
DOI		https://doi.org/10.1051/itmconf/20257001004
Published online		23 January 2025

J. M. Hu, Research on short-term traffic flow prediction method under the influence of weather factors, Master’s thesis, Jilin Univ. (2021). [Google Scholar]
W. M. Liu, X. Y. Yin, L. P. Guan, An event detection algorithm based on multiinformation fusion, J. Changsha Commun. Univ. (01), 58–62 (2004). [Google Scholar]
Z. Li, G. J. Guiyan, Y. L. Yong, Algorithms of SVM-AID based on data-level and decision-making-level data fusion methods, in 2008 Chinese Control and Decision Conference, IEEE, 3851–3856 (2008). [Google Scholar]
Y. Y. Chen, Z. L. Pan, Q. S. Wu, et al., Research on traffic event detection system based on multi-data fusion, Highway Traffic Technol. (App. Technol. Ed.) 8 (08), 375377 (2012). [Google Scholar]
N. G. Polson, V. O. Sokolov, Deep learning for short-term traffic flow prediction, Transp. Res. Part C: Emerg. Technol. 79, 1-17 (2017). [CrossRef] [Google Scholar]
L. Yu, B. Du, X. Hu, et al., Deep spatio-temporal graph convolutional network for traffic accident prediction, Neurocomputing 423, 135-147 (2021). [CrossRef] [Google Scholar]
X. H. Sun, Analysis and prediction of urban traffic flow based on deep learning, Master’s thesis, Jilin Univ. (2023). [Google Scholar]
Y. M. Dong, Traffic flow prediction based on spatio-temporal feature learning, Master’s thesis, Univ. of Electronic Sci. and Technol. China (2022). [Google Scholar]
H. M. Tang, Research on privacy-preserving traffic flow prediction scheme based on federated learning, Master’s thesis, East China Normal Univ. (2023). [Google Scholar]
Y. H. Liu, H. X. Shen, Spatio-temporal prediction of traffic accident severity based on ensemble learning models, Sci. Technol. Innov. Appl. 14 (08), 28-35 (2024). [Google Scholar]
B. Zhai, J. Lu, Y. Wang, et al., Real-time prediction of crash risk on freeways under fog conditions, Int. J. Transp. Sci. Technol. 9 (4), 287-298 (2020). [CrossRef] [Google Scholar]
F. Malin, I. Norros, S. Innamaa, Accident risk of road and weather conditions on different road types, Accid. Anal. Prev. 122, 181-188 (2019). [CrossRef] [Google Scholar]
N. Becker, H. W. Rust, U. Ulbrich, Predictive modeling of hourly probabilities for weather-related road accidents, Nat. Hazards Earth Syst. Sci. 20 (10), 2857-2871 (2020). [CrossRef] [Google Scholar]
S. Lassacher, D. Veneziano, S. Albert, et al., Traffic management of special events in small communities, Transp. Res. Rec. 2099 (1), 85-93 (2009). [CrossRef] [Google Scholar]
W. T. Pan, Short-term passenger flow prediction of urban rail transit under large-scale events, Master’s thesis, Beijing Jiaotong Univ. (2023). [Google Scholar]
R. Bramon, I. Boada, A. Bardera, et al., Multimodal data fusion based on mutual information, IEEE Trans. Vis. Comput. Graph. 18 (9), 1574-1587 (2011). [Google Scholar]
J. Gao, P. Li, Z. Chen, et al., A survey on deep learning for multimodal data fusion, Neural Comput. 32 (5), 829-864 (2020). [CrossRef] [MathSciNet] [Google Scholar]
Z. Qiu, T. Zhu, Y. Jin, et al., A graph attention fusion network for event-driven traffic speed prediction, Inf. Sci. 622, 405-423 (2023). [CrossRef] [Google Scholar]
B. L. Zhang, Z. H. Pan, J. Z. Jiang, et al., Multi-modal perception fusion method based on cross-attention mechanism, China J. Highway Transp. 37 (03), 181-193 (2024). [Google Scholar]
J. Yu, Z. Wang, V. Vasudevan, et al., Coca: Contrastive captioners are image-text foundation models, arXiv preprint arXiv:2205.01917 (2022). [Google Scholar]

Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.

Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.

Initial download of the metrics may take a while.