面向动态交通流预测的双流图卷积网络

doi:10.3778/j.issn.1673-9418.2009097

计算机科学与探索 ›› 2022, Vol. 16 ›› Issue (2): 384-394.DOI: 10.3778/j.issn.1673-9418.2009097

面向动态交通流预测的双流图卷积网络

李朝阳¹, 李琳¹^,⁺(), 陶晓辉²

1.武汉理工大学计算机科学与技术学院,武汉 430070
2.南昆士兰大学理学院,澳大利亚图文巴 4350

收稿日期:2020-08-14 修回日期:2020-10-20 出版日期:2022-02-01 发布日期:2020-11-06
通讯作者: + E-mail: cathylilin@whut.edu.cn
作者简介:李朝阳（1997—）,女,山东泰安人,硕士研究生,主要研究方向为机器学习、数据挖掘。
李琳（1977—）,女,湖南衡阳人,博士,教授,博士生导师,主要研究方向为数据分析、机器学习、信息检索、Web个性化推荐、社交媒体挖掘、自然语言处理等。
陶晓辉（1969—）,男,广西桂林人,博士,副教授,主要研究方向为数据分析、机器学习、知识工程、信息检索、健康信息学。
基金资助:
武汉理工大学自主创新研究基金(205210003)

Two-Stream Graph Convolutional Neural Network for Dynamic Traffic Flow Fore-casting

LI Zhaoyang¹, LI Lin¹^,⁺(), TAO Xiaohui²

1. School of Computer Science and Technology, Wuhan University of Technology, Wuhan 430070, China
2. School of Sciences, University of Southern Queensland, Toowoomba 4350, Australia

Received:2020-08-14 Revised:2020-10-20 Online:2022-02-01 Published:2020-11-06
About author:LI Zhaoyang, born in 1997, M.S. candidate. Her research interests include machine learning and data mining.
LI Lin, born in 1977, Ph.D., professor, Ph.D. supervisor. Her research interests include data analytics, machine learning, information retrieval, Web personalization & recommendation, social media mining, natural language processing, etc.
TAO Xiaohui, born in 1969, Ph.D., associate professor. His research interests include data analytics, machine learning, knowledge engineering, information retrieval and health informatics.
Supported by:
Fundamental Research Funds for Wuhan University of Technology(205210003)

摘要/Abstract

摘要：

准确的交通流预测能够为管理部门提供合理的决策依据,为驾驶员提供实时的道路状况预警,是交通领域至关重要的问题。近年来,相关研究利用图卷积神经网络（GCN）处理非欧式空间结构的特点,对来自复杂路网的交通流数据进行空间相关性建模。然而,现有基于图卷积的交通流预测方法未能充分考虑空间相关性的有向性和动态性这两个重要特点。考虑到动态交通流呈现出由固定道路结构约束的稳定空间相关性和受交通环境变化影响的动态空间相关性,提出了一种用于动态交通流预测的端到端双流图卷积网络（TSGCN）。首先,将实时交通流数据分解为具有不同空间相关性的稳定分量和动态分量。其中,稳定分量表示受路网约束和交通习惯影响的部分,动态分量则代表因交通状况变化（如交通拥堵和恶劣天气）引起的波动。然后,通过双流图卷积层提取稳定和动态的空间相关性。最后,使用参数化跳过连接方法来融合时空相关性以获得最终的预测结果。在两个公开的真实交通数据集上的实验结果表明,提出的模型优于对比的交通流预测方法。

关键词: 交通流预测, 图卷积神经网络（GCN）, 时空相关性

Abstract:

Accurate traffic flow prediction can provide decision-making basis for traffic management departments and early warning of road conditions for drivers, which is a crucial issue in the field of transportation. In recent years, related studies have used the characteristics of graph convolution neural network (GCN) in processing non-Euclidean structure data to model the spatial correlation of traffic flow data from complex road networks. However, existing traffic flow forecasting methods based on graph convolution fail to fully consider the directionality and dynamics of spatial correlation. Considering that dynamic traffic flow presents stable spatial correlation constrained by fixed road structure and dynamic spatial correlation influenced by traffic environment changes, this paper proposes an end-to-end two-stream graph convolution network (TSGCN) for dynamic traffic flow forecasting. Firstly, real-time traffic flow data are decomposed into stable components and dynamic components with different spatial correlations. Specifically, the stable components are constrained by the physical road network and traffic habits, while the dynamic components represent the fluctuations caused by changes in traffic conditions (such as traffic congestion and bad weather). Then, the stable and dynamic spatial correlations are extracted through the two-stream graph convolution layer. Finally, this paper uses the parameterized skip connection to fuse the spatial-temporal correlations to obtain the final prediction results. Experimental results on two published real-world traffic flow da-tasets show that the proposed model is better than several popular baselines.

Key words: trafﬁc ?ow forecasting;, graph convolution neural network (GCN), spatial-temporal correlation

中图分类号:

TP311

李朝阳, 李琳, 陶晓辉. 面向动态交通流预测的双流图卷积网络[J]. 计算机科学与探索, 2022, 16(2): 384-394.

LI Zhaoyang, LI Lin, TAO Xiaohui. Two-Stream Graph Convolutional Neural Network for Dynamic Traffic Flow Fore-casting[J]. Journal of Frontiers of Computer Science and Technology, 2022, 16(2): 384-394.

图/表 8

图1 交通流数据的时空相关性建模

Fig.1 Spatial-temporal correlation modeling of trafﬁc flow data

图2 TSGCN模型整体框架

Fig.2 Framework of TSGCN model

图3 双流图卷积层结构图

Fig.3 Process of two-stream GCN layer

图4 METR-LA数据集和PEMS-BAY数据集测试数据可视化

Fig.4 Visualization of test data of METR-LA and PEMS-BAY datasets

图5 基于METR-LA数据集的参数 d s设置对比

Fig.5 Comparison of parameter d s setting based on METR-LA dataset

表1 TSGCN模型与基线模型的性能对比

Table 1 Performance comparison of TSGCN with baseline models

Dataset	Model	15 min			30 min			60 min
Dataset	Model	MAE	RMSE	MAPE/%	MAE	RMSE	MAPE/%	MAE	RMSE	MAPE/%
PeMS-BAY	ARIMA	1.62	3.30	3.50	2.33	4.76	5.40	3.38	6.50	8.30
	FC-LSTM	2.05	4.19	4.80	2.20	4.55	5.20	2.37	4.96	5.70
	DCRNN	1.38	2.95	2.90	1.74	3.97	3.90	2.07	4.74	4.90
	Graph WaveNet	1.30	2.74	2.73	1.63	3.70	3.67	1.95	4.52	4.63
	TSGCN	1.12	2.22	2.27	1.36	2.88	3.71	1.62	3.61	3.71
METR-LA	ARIMA	3.99	8.21	9.60	5.15	10.45	12.70	6.90	13.23	17.40
	FC-LSTM	3.44	6.30	9.60	3.77	7.23	10.90	4.37	8.69	13.20
	DCRNN	2.77	5.38	7.30	3.15	6.45	8.80	3.60	7.60	10.50
	Graph WaveNet	2.69	5.15	6.90	3.07	6.22	8.37	3.53	7.37	10.01
	TSGCN	2.55	4.68	6.45	2.81	5.38	7.40	3.14	6.24	8.71

图6 METR-LA数据集一周内数据可视化结果

Fig.6 Visualization results within one week on METR-LA dataset

图7 TSGCN模型与基线模型在不同预测时间下的MAE对比

Fig.7 Comparison of MAE between TSGCN model and baseline models under different prediction time

参考文献 30

[1]	VAN DER VOORT M, DOUGHERTY M, WATSON S. Combining Kohonen maps with ARIMA time series models to forecast traffic flow[J]. Transportation Research Part C: Emerging Technologies, 1996, 4(5):307-318. DOI URL
[2]	WILLIAMS B M, HOEL L A. Modeling and forecasting vehicular traffic flow as a seasonal ARIMA process: theo-retical basis and empirical results[J]. Journal of Trans-portation Engineering, 2003, 129(6):664-672.
[3]	KUMAR S V, VANAJAKSHI L. Short-term traffic flow prediction using seasonal ARIMA model with limited input data[J]. European Transport Research Review, 2015, 7(3):1-9. DOI URL
[4]	JEONG Y S, BYON Y J, CASTRO-NETO M M, et al. Su-pervised weighting-online learning algorithm for short-term traffic flow prediction[J]. IEEE Transactions on Intelligent Transportation Systems, 2013, 14(4):1700-1707. DOI URL
[5]	WANG J, SHI Q. Short-term traffic speed forecasting hybrid model based on chaos-wavelet analysis-support vector mac-hine theory[J]. Transportation Research Part C: Emerging Technologies, 2013, 27:219-232. DOI URL
[6]	ZHANG Y, XIE Y. Forecasting of short-term freeway vo-lume with v-support vector machines[J]. Transportation Re-search Record: Journal of the Transportation Research Board, 2007(1):92-99.
[7]	ERMAGUN A, LEVINSON D. Spatiotemporal traffic fore-casting: review and proposed directions[J]. Transport Re-views, 2018, 38(6):786-814.
[8]	VLAHOGIANNI E I, KARLAFTIS M G, GOLIAS J C. Short-term traffic forecasting: where we are and where we’re going[J]. Transportation Research Part C: Emerging Tech-nologies, 2014, 43:3-19.
[9]	MA X, DAI Z, HE Z, et al. Learning traffic as images: a deep convolutional neural network for large-scale transportation network speed prediction[J]. Sensors, 2017, 17(4):818. DOI URL
[10]	杜圣东, 李天瑞, 杨燕, 等. 一种基于序列到序列时空注意力学习的交通流预测模型[J]. 计算机研究与发展, 2020, 57(8):1715-1728.
	DU S D, LI T R, YANG Y, et al. A sequence-to-sequence spatial-temporal attention learning model for urban traffic flow prediction[J]. Journal of Computer Research and De-velopment, 2020, 57(8):1715-1728.
[11]	ZHANG J, ZHENG Y, QI D. Deep spatio-temporal resi-dual networks for citywide crowd flows prediction[C]//Pro-ceedings of the 31st AAAI Conference on Artificial Intel-ligence. Menlo Park: AAAI, 2017: 1655-1661.
[12]	ZHANG J, ZHENG Y, QI D, et al. Predicting citywide crowd flows using deep spatio-temporal residual networks[J]. Ar-tificial Intelligence, 2018, 259:147-166.
[13]	JIANG W, ZHANG L. Geospatial data to images: a deep-learning framework for traffic forecasting[J]. Tsinghua Science & Technology, 2019, 24(1):52-64.
[14]	YAO H, TANG X, WEI H, et al. Modeling spatial-temporal dynamics for traffic prediction[J]. arXiv:1803.01254, 2018.
[15]	徐冰冰, 岑科廷, 黄俊杰, 等. 图卷积神经网络综述[J]. 计算机学报, 2020, 43(5):755-780.
	XU B B, CEN K T, HUANG J J, et al. A survey on graph convolutional neural network[J]. Chinese Journal of Com-puters, 2020, 43(5):755-780.
[16]	LI Y, YU R, SHAHABI C, et al. Diffusion convolutional re-current neural network: data-driven traffic forecasting[C]//Proceedings of the 6th International Conference on Learning Representations, Vancouver, Apr 30-May 3, 2018.
[17]	FANG S, ZHANG Q, MENG G, et al. GSTNet: global spatial-temporal network for traffic flow prediction[C]//Procee-dings of the 28th International Joint Conference on Artifi-cial Intelligence, Macao, China, Aug 10-16, 2019. Menlo Park: AAAI, 2019: 10-16.
[18]	GUO S, LIN Y, FENG N, et al. Attention based spatial-temporal graph convolutional networks for traffic flow fore-casting[C]//Proceedings of the 2019 AAAI Conference on Artificial Intelligence. Menlo Park: AAAI, 2019: 922-929.
[19]	DIAO Z, WANG X, ZHANG D, et al. Dynamic spatial-temporal graph convolutional neural networks for traffic forecasting[C]//Proceedings of the 2019 AAAI Conference on Artificial Intelligence. Menlo Park: AAAI, 2019: 890-897.
[20]	冯宁, 郭晟楠, 宋超, 等. 面向交通流量预测的多组件时空图卷积网络[J]. 软件学报, 2019, 30(3):759-769.
	FENG N, GUO S N, SONG C, et al. Multi-component spatial-temporal graph convolution networks for traffic flow fore-casting[J]. Journal of Software, 2019, 30(3):759-769.
[21]	YU B, YIN H, ZHU Z. Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting[C]//Proceedings of the 27th International Joint Conference on Artificial Intelligence. Menlo Park: AAAI, 2018: 3634-3640.
[22]	ZHAO L, SONG Y, ZHANG C, et al. T-GCN: a temporal graph convolutional network for traffic prediction[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 21:3848-3858. DOI URL
[23]	WU Z, PAN S, LONG G, et al. Graph WaveNet for deep spatial-temporal graph modeling[C]//Proceedings of the 28th International Joint Conference on Artificial Intelli-gence, Macao, China, Aug 10-16, 2019. Menlo Park: AAAI, 2019: 1907-1913.
[24]	ZHAI D, LIU A, CHEN S, et al. SeqST-ResNet: a sequen-tial spatial temporal ResNet for task prediction in spatial crowdsourcing[C]//LNCS 11446: Proceedings of the 2019 International Conference on Database Systems for Advan-ced Applications. Cham: Springer, 2019: 260-275.
[25]	YAO H, WU F, KE J, et al. Deep multi-view spatial-temporal network for taxi demand prediction[C]//Procee-dings of the 32nd AAAI Conference on Artificial Intelli-gence. Menlo Park: AAAI, 2018: 2588-2595.
[26]	SUTSKEVER I, VINYALS O, LE Q V. Sequence to sequ-ence learning with neural networks[C]//Proceedings of the Advances in Neural Information Processing Systems. Red Hook: Curran Associates, 2014: 3104-3112.
[27]	BRUNA J, ZAREMBA W, SZLAM A, et al. Spectral net-works and locally connected networks on graphs[C]//Pro-ceedings of the 2nd International Conference on Learning Representations, Banff, Apr 14-16, 2014.
[28]	DEFFERRARD M, BRESSON X, VANDERGHEYNST P. Convolutional neural networks on graphs with fast locali-zed spectral filtering[C]//Proceedings of the Advances in Neural Information Processing Systems. Red Hook: Curran Associates, 2016: 3844-3852.
[29]	DAUPHIN Y N, FAN A, AULI M, et al. Language mode-ling with gated convolutional networks[C]// Proceedings of the 34th International Conference on Machine Learning, Sydney, Aug 6-11, 2017: 933-941.
[30]	VAN DEN OORD A, DIELEMAN S, ZEN H, et al. Wave-Net: a generative model for raw audio[C]// Proceedings of the 9th ISCA Speech Synconfproc Workshop, Sunnyvale, Sep 13-15, 2016: 125.

面向动态交通流预测的双流图卷积网络

Two-Stream Graph Convolutional Neural Network for Dynamic Traffic Flow Fore-casting

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献 30

相关文章 1

编辑推荐

Metrics