Article Details

Title · Authors · Abstract · Keywords · DOI · References

Expressway Traffic Flow Prediction Based on Multi-source Heterogeneous Data Fusion

DENG Mingxue, XU Wenjin

(Qingdao University of Science and Technology, Qingdao 266061, China)

Section：Artificial Intelligence · Vol. 2026, Issue 2 · Pages：67-73 · 2096-4706（2026）02-0067-07 · CLC number：TP391 · Document code：A · DOI：10.19850/j.cnki.2096-4706.2026.02.013

Abstract

Expressway traffic flow prediction is affected by multiple factors, such as holidays, historical traffic conditions and climate, and exhibits complex spatio-temporal dependencies. To address this problem, this paper proposes a novel Data-fused Spatio-Temporal Graph Attention Network (RSTGCN), which is specifically designed for short-term expressway traffic flow prediction. The model integrates data preprocessing, feature fusion, spatio-temporal graph attention and Transformer architecture. The feature fusion module integrates multi-source data to comprehensively capture variations in traffic flow. The spatio-temporal graph attention network extracts the spatio-temporal features of traffic flow, taking into account spatial layout and temporal dependencies. The Transformer architecture enhances the capability of processing long-sequence data. Experimental results show that the model outperforms benchmark models in prediction performance, and ablation experiments verify the effectiveness of each module.

Keywords

multi-source data; expressway; feature fusion

References

  1. [1] Zhao Peng, Li Lu Research on Predicting Urban Rail Transit Station Arrival Based on ARIMA Model [J]. Journal of Chongqing Jiaotong University: Natural Science Edition, 2020, 39 (1): 40-44
  2. [2] Bai Weihua, Zhang Chuanbin, Zhang Qianyi, etc Short term traffic flow prediction based on outlier recognition Kalman filter [J]. Computer Application Research, 2021, 38 (3): 817-821
  3. [3] Xu Peng, Jiang Fengru Short term traffic flow prediction based on ant colony optimization support vector machine [J]. Computer Applications and Software, 2013, 30 (3): 250-254
  4. [4] Tian Jia, Wang Deyong, Shi Wenxi Short term traffic flow prediction based on ensemble empirical mode decomposition and random forest [J]. Science, Technology and Engineering, 2023, 23 (29): 12612-12619
  5. [5] Wang Xin, Wu Ji, Liu Chao, etc Fault time series prediction based on LSTM recurrent neural network [J]. Journal of Beihang University, 2018, 44 (4): 772-784
  6. [6] Li Lei, Zhang Qingmiao, Zhao Junhui, etc Short term traffic flow prediction based on improved CNN-LSTM combination model [J]. Chinese Journal of Applied Sciences, 2021, 39 (2): 185-198
  7. [7] Shen Fuxin, Bing Qichun, Zhang Weijian, etc Short term traffic flow prediction on expressways based on CEEMD-GRU combined model [J]. Journal of Hebei University of Science and Technology, 2021, 42 (5): 454-461
  8. [8] Zhang Xijun, Yu Guangjie, Cui Yong, etc Short term traffic flow prediction based on clustering algorithm and graph neural network [J]. Journal of Jilin University: Engineering Edition, 2024, 54 (6): 1593-1600
  9. [9] Wang Weitai, Wang Xiaoqiang, Li Leixiao, etc Overview of the Construction and Application of Spatiotemporal Graph Neural Networks in Traffic Flow Prediction Research [J]. Computer Engineering and Applications, 2024, 60 (8): 31-45
  10. [10] Liang Xiuxia, Xia Manman, He Yueyang, etc Traffic flow prediction based on spatiotemporal multi head graph attention network [J]. Acta Sinica, 2024, 52 (2): 500-509
  11. [11] Zhang Jipeng Research on Traffic Prediction Based on Decoupled Neural Networks [D]. Changsha: Central South University, 2024
  12. [12] Zhang Kai, Lu Haipeng, Han Ying, etc Short term vehicle speed prediction using spatiotemporal convolution with fused variational mode decomposition [J]. Journal of System Simulation, 2023, 35 (8): 1651-1660
  13. [13] Qin Yuanqi, Ji Qingyuan, Ge Jun, etc Research on Dynamic Short term Reasoning and Accurate Prediction of Urban Transportation Network [J]. Journal of Intelligent Science and Technology, 2022, 4 (3): 380-395
  14. [14] LI H，LIU J，HAN S Y，et al. STFGCN: Spatial-Temporal Fusion Graph Convolutional Network for Traffic Prediction [J/OL].Expert Systems with Applications，2024，255：124648（2024-07-06）.https://doi.org/10.1016/j.eswa.2024.124648.
  15. [15] SHIN Y，YOON Y. PGCN: Progressive Graph Convolutional Networks for Spatial-Temporal Traffic Forecasting [J].IEEE Transactions on Intelligent Transportation Systems，2024，25（7）：7633-7644.
  16. [16] SUN L，LIU M，LIU G，et al. FD-TGCN: Fast and Dynamic Temporal Graph Convolution Network for Traffic Flow Prediction [J].Information Fusion，2024，106：102291.
  17. [17] ZHAO Z，SHEN G，WANG L，et al. Graph Spatial-Temporal Transformer Network for Traffic Prediction [J/OL].Big Data Research，2024，36：100427（2024-01-30）.https://doi.org/10.1016/j.bdr.2024.100427.
  18. [18] MNIH V，HEESS N，GRAVES A，et al. Recurrent Models of Visual Attention [J].Advances in Neural Information Processing Systems，2014，27：1-9.
  19. [19] BAHDANAU D，CHO K，BENGIO Y. Neural Machine Translation by Jointly Learning to Align and Translate [J/OL].arXiv:1409.0473 [cs.CL].（2016-05-19）.https://arxiv.org/abs/1409.0473?ref=inweb3.com.
  20. [20] SZEGEDY C，LIU W，JIA Y，et al. Going Deeper with Convolutions [C]//2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Boston：IEEE，2015：1-9.
  21. [21] DENG L，HINTON G，KINGSBURY B. New Types of Deep Neural Network Learning for Speech Recognition and Related Applications: An Overview [C]//2013 IEEE International Conference on Acoustics, Speech and Signal Processing.Vancouver：IEEE，2013：8599-8603.
  22. [22] SONG H，RAJAN D，THIAGARAJAN J J，et al. Attend and Diagnose: Clinical Time Series Analysis Using Attention Models [C]//Thirty-Second AAAI Conference on Artificial Intelligence.New Orleans：AAAI，2018：1-8.
  23. [23] HUANG S，WANG D，WU X，et al. DSANet: Dual Self-Attention Network for Multivariate Time Series Forecasting [C]//Proceedings of the 28th ACM International Conference on Information and Knowledge Management.Beijing：ACM，2019：2129-2132.
  24. [24] GUO S，LIN Y，FENG N，et al. Attention Based Spatial-Temporal Graph Convolutional Networks for Traffic Flow Forecasting [C]//Proceedings of the AAAI Conference on Artificial Intelligence. Honolulu：AAAI，2019：922-929.
  25. [25] GUO S，LIN Y，WAN H，et al. Learning Dynamics and Heterogeneity of Spatial-Temporal Graph Data for Traffic Forecasting [J].IEEE Transactions on Knowledge and Data Engineering，2021，34（11）：5415-5428.
  26. [26] JIANG J，HAN C，ZHAO W X，et al. PDTFormer: Propagation Delay-Aware Dynamic Long-Range Transformer for Traffic Flow Prediction [C]//Proceedings of the AAAI Conference on Artificial Intelligence.Washington：AAAI，2023：4365-4373.
  27. [27] XU M X，DAI W R，LIU C M，et al. Spatial-Temporal Transformer Networks for Traffic Flow Forecasting [J/OL].arXiv:2001.02908 [eess.SP].（2021-05-29）.https://arxiv.org/abs/2001.02908?context=cs.
  28. [28] HOCHREITER S，SCHMIDHUBER J. Long Short-Term Memory [J].Neural Computation，1997，9（8）：1735-1780.
  29. [29] LIU Z，SHEN Y，LAKSHMINARASIMHAN V B，et al. Efficient Low-Rank Multimodal Fusion with Modality-Specific Factors [C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics Melbourne：ACL，2018：2247-2256.

About the authors

Deng Mingxue (2001-), female, Han ethnicity, from Heze, Shandong, currently pursuing a master's degree in data mining; Corresponding author: Xu Wenjin (1977-), male, Han ethnicity, from Weifang, Shandong Province, associate professor, PhD, research direction: artificial intelligence, data mining, domain large language models, digital twins.