Medium and long-term traffic flow prediction
based on ACNN-Trans model

doi:10.19682/j.cnki.1005-8885.2023.2013

中国邮电高校学报(英文) ›› 2023, Vol. 30 ›› Issue (4): 21-32.doi: 10.19682/j.cnki.1005-8885.2023.2013

• Artificial Intelligence • 上一篇下一篇

Medium and long-term traffic flow prediction based on ACNN-Trans model

Zhang Xijun, Zhang Guannan, Zhang Xianli, Zhang Hong, Zhang Minghu

School of Computer and Communication, Lanzhou University of Technology, Lanzhou 730050, China

收稿日期:2022-08-17 修回日期:2023-06-19 接受日期:2023-08-31 出版日期:2023-08-31 发布日期:2023-08-31
通讯作者: Zhang Xijun, E-mail: zhangxijun198079@sina.com E-mail:zhangxijun198079@sina.com
基金资助:
This work was supported by the National Natural Science Foundation of China ( 62162040 ), Gansu Province Higher Education Innovation Fund-Funded Project ( 2021A-028 ), Gansu Provincial Science and Technology Program Funding Project ( 21ZD4GA028 ) and Gansu Provincial Science and Technology Plan Funding Key Project of Natural Science Foundation of China (22JR5RA226).

Medium and long-term traffic flow prediction based on ACNN-Trans model

Zhang Xijun, Zhang Guannan, Zhang Xianli, Zhang Hong, Zhang Minghu

School of Computer and Communication, Lanzhou University of Technology, Lanzhou 730050, China

Received:2022-08-17 Revised:2023-06-19 Accepted:2023-08-31 Online:2023-08-31 Published:2023-08-31
Contact: Zhang Xijun, E-mail: zhangxijun198079@sina.com E-mail:zhangxijun198079@sina.com
Supported by:
This work was supported by the National Natural Science Foundation of China ( 62162040 ), Gansu Province Higher Education Innovation Fund-Funded Project ( 2021A-028 ), Gansu Provincial Science and Technology Program Funding Project ( 21ZD4GA028 ) and Gansu Provincial Science and Technology Plan Funding Key Project of Natural Science Foundation of China (22JR5RA226).

摘要/Abstract

摘要： Aiming at the failure of traditional medium and long-term traffic flow forecasting methods to effectively process long-time series data and extract the spatio-temporal characteristics between road nodes, a com-bined prediction model attention based on convolutional neural network (CNN) and transformer ( ACNN-Trans ) network is proposed. The spatial features between nodes on complex roads are extracted by CNN. The embedded attention mechanism is adaptively pay attention to the results of feature extraction. The spatial features of the node traffic flow are dug by the embedded attention mechanism. The traffic flow sequence is calculated by the transformer network. The temporal correlation of long-term series data is captured by the relative position weight between the data. Finally, the 30-min and 60-min traffic flow predictions are respectively modeled by the extracted temporal and spatial features. The results show that the prediction results of the ACNN-Trans combined model are better than other models on two different real datasets. Comparing to the baseline models, the root mean square error (RMSE) index of the prediction results is reduced by an average of 34.58%, which verifies the effectiveness of ACNN-Trans model.

关键词: traffic flow prediction, intelligent transportation, attention mechanism, transformer

Abstract: Aiming at the failure of traditional medium and long-term traffic flow forecasting methods to effectively process long-time series data and extract the spatio-temporal characteristics between road nodes, a com-bined prediction model attention based on convolutional neural network (CNN) and transformer ( ACNN-Trans ) network is proposed. The spatial features between nodes on complex roads are extracted by CNN. The embedded attention mechanism is adaptively pay attention to the results of feature extraction. The spatial features of the node traffic flow are dug by the embedded attention mechanism. The traffic flow sequence is calculated by the transformer network. The temporal correlation of long-term series data is captured by the relative position weight between the data. Finally, the 30-min and 60-min traffic flow predictions are respectively modeled by the extracted temporal and spatial features. The results show that the prediction results of the ACNN-Trans combined model are better than other models on two different real datasets. Comparing to the baseline models, the root mean square error (RMSE) index of the prediction results is reduced by an average of 34.58%, which verifies the effectiveness of ACNN-Trans model.

Key words: traffic flow prediction, intelligent transportation, attention mechanism, transformer

Zhang Xijun, Zhang Guannan, Zhang Xianli, Zhang Hong, Zhang Minghu. Medium and long-term traffic flow prediction based on ACNN-Trans model[J]. The Journal of China Universities of Posts and Telecommunications, 2023, 30(4): 21-32.

参考文献

References

[1] LIN J X. Traffic prediction of road speed based on conventional neural network. Computer Knowedge and Technology, 2019, 15(9): 176 - 178 (in Chinese).

[2] CONNOR J T, MARTIN R D, ATLAS L E. Recurrent neural networks and robust time series prediction. IEEE Transactions on Neural Networks, 1994, 5(2): 240 - 254.

[3] HOCHREITER S, SCHMIDHUBER J. Long short-term memory. Neural Computation, 1997, 9(8): 1735 - 1780.

[4] CHO K, VAN MERRINBOER B, GULCEHRE C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP'14), 2014, Oct 25 - 29, Doha, Qatar. Stroudsburg, PA, USA: Association for Computational Linguistics, 2014: 1724 - 1734.

[5] FU R, ZHANG Z, LI L. Using LSTM and GRU neural network methods for traffic flow prediction. Proceedings of the 31st Youth Academic Annual Conference of Chinese Association of Automation (YAC'16), 2016, Nov 11 - 13, Wuhan, China. Piscataway, NJ, USA: IEEE, 2016: 324 - 328.

[6] WU Z H, PAN S R, CHEN F W, et al. A comprehensive survey on graph neural networks. IEEE Transactions on Neural Networks and Learning Systems, 2021, 32(1): 4 - 24.

[7] KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks. arXiv Preprint, arXiv: 1609. 02907, 2016.

[8] ZHAO L, SONG Y J, ZHANG C, et al. T-GCN: A temporal graph convolutional network for traffic prediction. IEEE Transactions on Intelligent Transportation Systems, 2020, 21(9): 3848 - 3858.

[9] ZHANG J N, SHI X J, XIE J Y, et al. GaAN: Gated attention networks for learning on large and spatiotemporal graphs. arXiv preprint, arXiv: 1803. 07294, 2018.

[10] YANG B, KANG Y, YUAN Y, et al. STLBAGAN: Spatio-temporal learnable bidirectional attention generative adversarial networks for missing traffic data imputation. Knowledge-Based Systems, 2021, 215: Article 106705.

[11] YAN H, FU L Y, QI Y, et al. Learning a robust classifier for short-term traffic state prediction. Knowledge-Based Systems, 2022, 242: Article 108368.

[12] TA X X, LIU Z H, HU X, et al. Adaptive spatio-temporal graph neural network for traffic forecasting. Knowledge-Based Systems, 2022, 242: Article 108199.

[13] REN Y L, JIANG H, JI N, et al. TBSM: A traffic burst-sensitive model for short-term prediction under special events. Knowledge-Based Systems, 2022, 240: Article 108120.

[14] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need. Advances in Neural Information Processing Systems 30: Proceedings of the 31st International Conference on Neural Information Processing Systems ( NIPS'17 ), 2017, Dec 4 - 9, Long Beach, CA, USA. Red Hook, NY, USA: Curran Associates Inc, 2017: 6000 - 6010.

[15] WANG X Y, MA Y, WANG Y Q, et al. Traffic flow prediction via spatial temporal graph neural network. Proceedings of the 2020 Web Conference ( WWW'20 ), 2020, Apr 20 - 24, Taipei, China. New York, NY, USA: ACM, 2020: 1082 - 1092.

[16] XU M X, DAI W R, LIU C M, et al. Spatial-temporal transformer networks for traffic flow forecasting. arXiv preprint, arXiv: 2001. 02908, 2020.

[17] LIN G Y, DING J N, DING S T, et al. Passenger flow prediction with transformer: The Shenzhen metro case. Proceedings of the 2021 International Conference on Big Data Analysis and Computer Science ( BDACS'21 ), 2021, Jun 25 - 27, Kunming, China. Piscataway, NJ, USA: IEEE, 2021: 97 - 100.

[18] LIU P J, SALEH M, POT E, et al. Generating Wikipedia by summarizing long sequences. arXiv preprint, arXiv: 1801. 10198, 2018.

[19] PARMAR N, VASWANI A, USZKOREIT J, et al. Image transformer. Proceedings of the 35th International Conference on Machine Learning ( PMLR'18 ), 2018, Jul 10 - 15, Stockholm Sweden. Stroudsburg, PA, USA: International Machine Learning Society, 2018: 4055 - 4064.

[20] ZHOU L W, ZHOU Y B, CORSO J J, et al. End-to-end dense video captioning with masked transformer. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition ( CVPR'18 ), 2018, Jun 18 - 23, Salt Lake City, UT, USA. Piscataway, NJ, USA: IEEE, 2018: 8739 - 8748.

[21] RUAN H C, FENG X X, ZHENG H F. Graph transformer attention networks for traffic flow prediction. Proceedings of the 7th International Conference on Computer and Communications (ICCC'21), 2021, Dec 10 - 13, Chengdu, China. Piscataway, NJ, USA: IEEE, 2021: 1778 - 1782.

[22] XIE Y L, NIU J J, ZHANG Y, et al. Multisize patched spatial-temporal transformer network for short-and long-term crowd flow prediction. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(11): 21548 - 21568.

[23] LI Y, REN Q Q, JIN H, et al. LSTN: Long short-term traffic flow forecasting with transformer networks. Proceedings of the 26th International Conference on Pattern Recognition ( ICPR'22 ), 2022, Aug 21 - 25, Montreal, Canada. Piscataway, NJ, USA: IEEE, 2022: 4793 - 4800.

[24] RAMANA K, SRIVASTAVA G, KUMAR M R, et al. A vision transformer approach for traffic congestion prediction in urban areas. IEEE Transactions on Intelligent Transportation Systems, 2023, 24(4): 3922 - 3934.

[25] CHEN C L, LIU Y B, CHEN L, et al. Bidirectional spatial-temporal adaptive transformer for urban traffic flow forecasting. IEEE Transactions on Neural Networks and Learning Systems, Early Access Article, DOI: 10.1109/TNNLS.2022.3183903.

[26] PU B, LIU J S, KANG Y, et al. MVSTT: A multiview spatial-temporal transformer network for traffic-flow forecasting. IEEE Transactions on Cybernetics, Early Access Article, DOI: 10.1109/TCYB.2022.3223918.

Medium and long-term traffic flow prediction based on ACNN-Trans model

Medium and long-term traffic flow prediction based on ACNN-Trans model

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

编辑推荐

Metrics

本文评价