In order to help optimize traffic management, reduce congestion, improve travel efficiency, and provide scientific decision support for urban planning and intelligent transportation systems, a multi-dimensional long-term traffic flow prediction model based on graph neural networks is proposed in this paper. A multi-channel stackable block structure is used in this model. The hidden time information is captured and transmitted in the time-varying channel. The spatial patterns are captured using graph convolutional neural network in the prediction channel. Each stackable block is learning through layer by layer decomposition using the saved information in the purification channel. The final prediction results are weighted summary of each stackable block output. This model is more accurate than other baseline models through experiments on two large-scale real-world road network traffic datasets. This model can provide technical support for the long-term traffic flow prediction of our country.
PanB, DemiryurekU, ShahabiC. Utilizing real-world transportation data for accurate traffic prediction[C]∥International Conference on Data Mining, Washington, USA, 2012: 595-604.
[2]
ChangC C, LinC J. LIBSVM: a library for support vector machines[J].ACM Transactions on Intelligent Systems and Technology, 2011, 2(3): 27-42.
[3]
SunS, ZhangC, YuG. A bayesian network approach to traffic flow forecasting[J]. IEEE Transactions on Intelligent Transportation Systems, 2006, 7(1): 124-132.
HochreiterS, SchmidhuberJ. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780.
[6]
ChungJ, GulcehreC, ChoK, et al. Empirical evaluation of gated recurrent neural networks on sequence modeling[EB/OL].(2014-12-11)[2024-09-02].
[7]
KipfT N, WellingM. Semi-supervised classification with graph convolutional networks[J/OL]. [2024-09-02]. DOI: 10.48550/arXiv.1609.02907 .
[8]
GuoS, LinY, FengN, et al. Attention based spatial-temporal graph convolutional networks for traffic flow forecasting[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33(1): 922-929.
[9]
ZhaoL, SongY, ZhangC, et al. T-GCN: a temporal graph convolutional network for traffic prediction[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 21(9): 3848-3858.
[10]
YuB, YinH, ZhuZ. Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting[C]∥Proceedings of the 27th International Joint Conference on Artificial Intelligence, Stockholm, Sweden, 2018: 3634-3640.
[11]
SongC, LinY, GuoS, et al. Spatial-temporal synchronous graph convolutional networks: a new framework for spatial-temporal network data forecasting[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(1): 914-921.
GaoHai-long, XuYi-bo, HouDe-zao, et al. Short⁃term traffic flow prediction algorithm for road network based on deep asynchronous residual network[J]. Journal of Jilin University (Engineering and Technology Edition), 2023, 53(12): 3458-3464.
[14]
LiZ, HanY, XuZ, et al. Pmgcn: progressive multi-graph convolutional network for traffic forecasting[J]. ISPRS International Journal of Geo-Information, 2023, 12(6): 27-28.
[15]
JiangJ, HanC, ZhaoW X, et al. Pdformer: propagation delay-aware dynamic long-range transformer for traffic flow prediction[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2023, 37(4): 4365-4373.
[16]
SutskeverI. Sequence to sequence learning with neural networks[C]∥Proceedings of the 27th International Conference on Neural Information Processing Systems, Montreal, Canada, 2014: 3104-3112.
[17]
LiY, YuR, ShahabiC, et al. Diffusion convolutional recurrent neural network: data-driven traffic forecasting[C]∥Proceedings of the International Conference on Learning Representations, Vancouver, Canada, 2018: 1-16.
[18]
WengW, FanJ, WuH, et al. A decomposition dynamic graph convolutional recurrent network for traffic forecasting[J]. Pattern Recognition, 2023, 142: 109670.