Traffic flow forecasting via spatial-temporal multi-graph fusion

doi:10.11772/j.issn.1001-9081.2023081226

Journal of Computer Applications ›› 2024, Vol. 44 ›› Issue (8): 2618-2625.DOI: 10.11772/j.issn.1001-9081.2023081226

• Frontier and comprehensive applications • Previous Articles Next Articles

Traffic flow forecasting via spatial-temporal multi-graph fusion

Yanjie GU¹, Yingjun ZHANG¹^,²^,³(), Xiaoqian LIU¹, Wei ZHOU¹^,⁴, Wei SUN¹

^1.College of Computer and Information Technology，Beijing Jiaotong University，Beijing 100044，China
^2.Beijing Key Laboratory of Traffic Data Analysis and Mining （Beijing Jiaotong University），Beijing 100044，China
^3.Frontiers Science Center for Smart High?speed Railway System，Beijing Jiaotong University，Beijing 100044，China
^4.Key Laboratory of Big Data & Artificial Intelligence in Transportation，Ministry of Education （Beijing Jiaotong University），Beijing 100044，China

Received:2023-09-08 Revised:2023-10-19 Accepted:2023-11-02 Online:2024-08-22 Published:2024-08-10
Contact: Yingjun ZHANG
About author:GU Yanjie， born in 1999， M. S. candidate. His research interests include machine learning， time series prediction.
LIU Xiaoqian， born in 1996， Ph. D. candidate. Her research interests include data mining， evolutionary learning， fuzzy cognitive maps.
ZHOU Wei， born in 1973， Ph. D.， research fellow. Her research interests include data mining， artificial intelligence， computer education.
SUN Wei， born in 1998， Ph. D. candidate. His research interests include data mining， temporal causal learning.
Supported by:
Fundamental Research Funds for Central Universities(2022JBQY009)

基于时空多图融合的交通流量预测

顾焰杰¹, 张英俊¹^,²^,³(), 刘晓倩¹, 周围¹^,⁴, 孙威¹

^1.北京交通大学计算机与信息技术学院，北京 100044
^2.交通数据分析与挖掘北京市重点实验室（北京交通大学），北京 100044
^3.北京交通大学智慧高铁系统前沿科学中心，北京 100044
^4.交通大数据与人工智能教育部重点实验室（北京交通大学），北京 100044

通讯作者: 张英俊
作者简介:顾焰杰（1999—），男，河北邢台人，硕士研究生，CCF会员，主要研究方向：机器学习、时间序列预测
张英俊（1980—），男，内蒙古呼和浩特人，副教授，博士，CCF会员，主要研究方向：数据挖掘 zhangyj@bjtu.edu.cn
刘晓倩（1996—），女，甘肃靖远人，博士研究生，主要研究方向：数据挖掘、进化学习、模糊认知图
周围（1973—），女，河北石家庄人，研究员，博士，CCF会员，主要研究方向：数据挖掘、人工智能、计算机教育
孙威（1998—），男，山东枣庄人，博士研究生，CCF会员，主要研究方向：数据挖掘、时序因果学习。
基金资助:
中央高校基本科研业务费专项（科技领军人才团队项目）(2022JBQY009)

Abstract

Abstract:

Traffic prediction is a fundamental task in Intelligent Transportation System （ITS）， as accurate Traffic Flow Forecasting （TFF） can significantly improve the utilization efficiency of public resources. To address the limitations of insufficient utilization of contextual information， imbalanced graph fusion techniques， and consideration of only static spatial relationships in existing multi-graph neural network models， a TFF model based on Spatio-Temporal Multi-Graph Fusion （STMGF） was proposed. Firstly， different spatial correlations across different regions were extracted by the model through the fusion of spatial graphs， semantic graphs， and spatial-semantic graphs. Spatial attention mechanism and graph attention mechanism were utilized to dynamically learn the importance of different graph structures for different neighbors. Then， a multi-kernel temporal attention mechanism was employed to capture both local and global temporal dependencies. Finally， a multi-layer perceptron was utilized to predict traffic flow， obtaining the final prediction values. The validity of the model was verified on NYCTaxi dataset and NYCBike dataset. Experimental results showed that the Root Mean Square Errors （RMSE） of the proposed model STMGF were 8.46%， 2.70%， and 2.20% lower than those of Spatio-Temporal Graph Convolutional Network （STGCN）， Attention based Spatial-Temporal Graph Neural Network （ASTGNN）， and Meta-graph Convolutional Recurrent Network （MegaCRN）， respectively in the 36 steps forecast task of the NYCBike dataset.

Key words: multi-graph fusion, multi-kernel attention, spatial attention, graph attention, deep learning

摘要：

交通预测是智能交通系统（ITS）的核心任务，准确的交通流量预测（TFF）可以大幅提高公共资源的利用效率。针对现有多图神经网络模型对上下文信息使用不足、图融合方法不平衡和只考虑静态空间关系等问题，提出基于时空多图融合（STMGF）的TFF模型。首先，通过融合空间图、语义图和空间语义图提取不同区域的不同空间相关性，并利用空间注意力机制和图注意力机制融合不同的图结构以动态学习不同邻居的重要性；然后，使用多核时间注意力机制同时捕获局部时间依赖性和全局时间依赖性；最后，使用多层感知机预测交通流量，得到最终预测值。在NYCTaxi和NYCBike数据集验证模型的有效性。实验结果表明，在NYCBike数据集的36步预测任务中，与时空图卷积神经网络（STGCN）、基于时空注意力的图神经网络（ASTGNN）、元图卷积递归网络（MegaCRN）相比，所提模型的均方根误差（RMSE）分别降低了8.46%、2.70%和2.20%。

关键词: 多图融合, 多核注意力, 空间注意力, 图注意力, 深度学习

CLC Number:

TP181

Yanjie GU, Yingjun ZHANG, Xiaoqian LIU, Wei ZHOU, Wei SUN. Traffic flow forecasting via spatial-temporal multi-graph fusion[J]. Journal of Computer Applications, 2024, 44(8): 2618-2625.

顾焰杰, 张英俊, 刘晓倩, 周围, 孙威. 基于时空多图融合的交通流量预测[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2618-2625.

Figures/Tables 11

Fig. 1 Structure of STMGF model

Fig. 2 Multi-kernel temporal self-attention module

Fig. 3 Multi-graph fusion convolution module

Tab. 1 Basic information of experimental datasets

数据集名称	区域数	序列长度	时间间隔/min
NYCTaxi	75	17 520	30
NYCBike	128	4 392	60

Tab. 2 Performance comparison results on two traffic flow datasets

数据集	时间步	指标	STGCN	DCRNN	GWNET	AGCRN	ASTGNN	MegaCRN	STMGF
NYCBike	12	MAE	5.045	5.119	5.316	5.138	4.974	4.951	4.909
	12	RMSE	8.599	8.839	9.162	8.774	8.618	8.587	8.373
	18	MAE	5.238	5.229	5.493	5.27	5.105	5.088	5.036
	18	RMSE	9.145	9.085	9.587	9.903	8.801	8.788	8.622
	24	MAE	5.421	5.362	5.608	5.513	5.219	5.365	5.119
	24	RMSE	9.673	9.574	9.798	9.631	9.132	9.624	9.017
	36	MAE	6.092	5.823	6.124	5.888	5.718	5.696	5.628
	36	RMSE	11.021	10.480	10.936	10.448	10.370	10.315	10.088
NYCTaxi	12	MAE	17.163	16.528	16.892	16.513	16.203	16.195	16.114
	12	RMSE	33.567	33.032	32.651	32.368	31.545	31.570	31.561
	18	MAE	17.386	17.200	18.227	17.292	16.915	16.845	16.762
	18	RMSE	34.138	33.649	34.961	33.600	33.345	32.949	32.670
	24	MAE	18.212	18.449	18.756	18.174	17.338	17.305	17.278
	24	RMSE	35.742	34.521	36.375	35.653	34.359	34.210	34.085
	36	MAE	18.727	18.744	19.56	19.544	18.362	18.305	18.237
	36	RMSE	37.004	37.402	38.266	38.683	36.309	36.210	36.048

Fig. 4 Performance comparison result graphs on dataset NYCBike

Tab. 3 Experimental results of variant models with predicted step sizes of 12 and 18

模型	步长为12				步长为18
	NYCBike		NYCTaxi		NYCBike		NYCTaxi
	MAE	RMSE	MAE	RMSE	MAE	RMSE	MAE	RMSE
STMGF	4.909	8.373	16.114	31.561	5.036	8.622	16.762	32.670
STMGF⁃Ⅰ	5.013	8.490	16.377	31.910	5.223	9.216	17.563	35.390
STMGF⁃Ⅱ	5.245	9.078	16.727	32.562	5.809	10.272	19.157	36.097
STMGF⁃Ⅲ	5.360	9.218	16.897	33.147	5.594	9.769	18.489	35.756

Fig. 5 Results of NYCBike dataset with predicted step size of 12

Tab. 4 Experimental results of different layer number with predicted step size of 12

层数	NYCBike
层数	MAE	RMSE
4	4.990	8.608
3	4.909	8.373
2	4.948	8.517
1	5.304	8.917

Tab. 5 Experimental results of different nhead with prediction step size of 12

$n h e a d$	NYCBike
$n h e a d$	MAE	RMSE
2	4.972	8.532
4	4.909	8.373
8	4.997	8.548

Tab. 5 Experimental results of different nhead with prediction step size of 12

$n h e a d$	NYCBike
$n h e a d$	MAE	RMSE
2	4.972	8.532
4	4.909	8.373
8	4.997	8.548

Fig. 6 Influence of prediction length on prediciton effects on NYCBike dataset

References 29

1	LI Y， YU R， SHAHABI C， et al. Diffusion convolutional recurrent neural network： data-driven traffic forecasting［C/OL］// Proceedings of the 2018 International Conference on Learning Representations ［2023-08-01］. .
2	GUO S， LIN Y， FENG N， 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.
3	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 Intelligence. California： ijcai.org， 2019： 1907-1913.
4	SHAO W， JIN Z， WANG S， et al. Long-term spatiotemporal forecasting via dynamic multiple-graph attention［C］// Proceedings of the 31st International Joint Conference on Artificial Intelligence. California： ijcai.org， 2022： 2225-2232.
5	LI M， ZHU Z. Spatial-temporal fusion graph neural networks for traffic flow forecasting［J］. Proceedings of the AAAI Conference on Artificial Intelligence， 2021， 35（5）： 4189-4196.
6	WANG X， MA Y， WANG Y. Traffic flow prediction via spatial temporal graph neural network［C］// Proceedings of the Web Conference 2020. New York： ACM， 2020：1082-1092.
7	ZHENG C， FAN X， WANG C， et al. GMAN： a graph multi-attention network for traffic prediction［J］. Proceedings of the AAAI Conference on Artificial Intelligence， 2020， 34（1）： 1234-1241.
8	夏进，王正群，朱世明. 基于时间序列分解的交通流量预测模型［J］. 计算机应用， 2023， 43（4）：1129-1135.
	XIA J， WANG Z Q， ZHU S M. Traffic flow prediction model based on time series decomposition［J］. Journal of Computer Applications， 2023， 43（4）：1129-1135.
9	WANG C， ZHU Y， ZANG T， et al. Modeling inter-station relationships with attentive temporal graph convolutional network for air quality prediction［C］// Proceedings of the 14th ACM International Conference on Web Search and Data Mining. New York： ACM， 2021： 616-634.
10	TRIRAT P， YOON S， LEE J-G， et al. MG-TAR： multi-view graph convolutional networks for traffic accident risk prediction［J］. IEEE Transactions on Intelligent Transportation Systems， 2023， 24（4）：3779-3794.
11	LI H， JIN D， LI X， et al. DMGF-Net： an efficient dynamic multi-graph fusion network for traffic prediction［J］. ACM Transactions on Knowledge Discovery from Data， 2023， 17（7）： Article No. 97.
12	GE L， JIA Y， LI Q， et al. Dynamic multi-graph convolution recurrent neural network for traffic speed prediction［J］. Journal of Intelligent & Fuzzy Systems， 2023， 44（5）：7319-7332.
13	TAO S， ZHANG H， YANG F. Multiple information spatial-temporal attention based graph convolution network for traffic prediction［J］. Applied Soft Computing， 2023， 136：110052.
14	SONG C， LIN Y， GUO S， 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.
15	XU Y， LYU Y， XIONG G， et al. Adaptive feature fusion networks for origin-destination passenger flow prediction in metro systems［J］. IEEE Transactions on Intelligent Transportation Systems， 2023， 24（5）：5296-5312.
16	WANG B， ZHANG Y， SHI J， et al. Knowledge expansion and consolidation for continual traffic prediction with expanding graphs［J］. IEEE Transactions on Intelligent Transportation Systems， 2023， 24（7）：7190-7201.
17	HUO G， ZHANG Y， WANG B， et al. Hierarchical spatio-temporal graph convolutional networks and transformer network for traffic flow forecasting［J］. IEEE Transactions on Intelligent Transportation Systems， 2023， 24（4）：3855-3867.
18	XU Z， KANG Y， CAO Y. High-resolution urban flows forecasting with coarse-grained spatiotemporal data［J］. IEEE Transaction on Artificial Intelligence， 2023， 4（2）：315-327.
19	王海起，王志海，李留珂，等. 基于网格划分的城市短时交通流量时空预测模型［J］. 计算机应用， 2022， 42（7）：2274-2280.
	WANG H Q， WANG Z H， LI L K， et al. Spatial-temporal prediction model of urban short-term traffic flow based on grid division［J］. Journal of Computer Applications， 2023， 42（7）：2274-2280.
20	GENG X， LI Y， WANG L. Spatiotemporal multi-graph convolution network for ride-hailing demand forecasting［J］. Proceedings of the AAAI Conference on Artificial Intelligence， 2019， 36（1）： 3656-3663.
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. California： ijcai.org， 2018：3634-3640.
22	CHOI J， CHOI H， HWANG J， et al. Graph neural controlled differential equations for traffic forecasting［J］. Proceedings of the AAAI Conference on Artificial Intelligence， 2022， 36（6）：6367-6374.
23	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， 2022， 34（11）：5415-5428.
24	LI Q， HAN Z， WU X. Deeper insights into graph convolutional networks for semi-supervised learning［J］. Proceedings of the AAAI Conference on Artificial Intelligence， 2018， 32（1）：3538-3545.
25	VASWANI A， SHAZEER N， PARMAR N， et al. Attention is all you need［C］// Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook： Curran Associates Inc.， 2017：6000-6010.
26	JIANG J， HAN C， ZHAO 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.
27	LI S， JIN X， XUAN Y， et al. Enhancing the locality and breaking the memory bottleneck of transformer on time series forecasting［C］// Proceedings of the 33rd International Conference on Neural Information Processing Systems. Red Hook： Curran Associates Inc.， 2019： 5243-5253.
28	WANG J， JIANG J， JIANG W， et al. LibCity： an open library for traffic prediction［C］// Proceedings of the 29th International Conference on Advances in Geographic Information Systems. New York： ACM， 2021：145-148.
29	JIANG R， WANG Z， YONG J， et. al . Spatio-temporal meta-graph learning for traffic forecasting［J］. Proceedings of the AAAI Conference on Artificial Intelligence， 2023， 37（7）： 8078-8086.

[1]	Yunchuan HUANG, Yongquan JIANG, Juntao HUANG, Yan YANG. Molecular toxicity prediction based on meta graph isomorphism network [J]. Journal of Computer Applications, 2024, 44(9): 2964-2969.
[2]	Jing QIN, Zhiguang QIN, Fali LI, Yueheng PENG. Diagnosis of major depressive disorder based on probabilistic sparse self-attention neural network [J]. Journal of Computer Applications, 2024, 44(9): 2970-2974.
[3]	Xiyuan WANG, Zhancheng ZHANG, Shaokang XU, Baocheng ZHANG, Xiaoqing LUO, Fuyuan HU. Unsupervised cross-domain transfer network for 3D/2D registration in surgical navigation [J]. Journal of Computer Applications, 2024, 44(9): 2911-2918.
[4]	Hang YANG, Wanggen LI, Gensheng ZHANG, Zhige WANG, Xin KAI. Multi-layer information interactive fusion algorithm based on graph neural network for session-based recommendation [J]. Journal of Computer Applications, 2024, 44(9): 2719-2725.
[5]	Yexin PAN, Zhe YANG. Optimization model for small object detection based on multi-level feature bidirectional fusion [J]. Journal of Computer Applications, 2024, 44(9): 2871-2877.
[6]	Shunyong LI, Shiyi LI, Rui XU, Xingwang ZHAO. Incomplete multi-view clustering algorithm based on self-attention fusion [J]. Journal of Computer Applications, 2024, 44(9): 2696-2703.
[7]	Yuhan LIU, Genlin JI, Hongping ZHANG. Video pedestrian anomaly detection method based on skeleton graph and mixed attention [J]. Journal of Computer Applications, 2024, 44(8): 2551-2557.
[8]	Chenqian LI, Jun LIU. Ultrasound carotid plaque segmentation method based on semi-supervision and multi-scale cascaded attention [J]. Journal of Computer Applications, 2024, 44(8): 2604-2610.
[9]	Qianhong SHI, Yan YANG, Yongquan JIANG, Xiaocao OUYANG, Wubo FAN, Qiang CHEN, Tao JIANG, Yuan LI. Multi-granularity abrupt change fitting network for air quality prediction [J]. Journal of Computer Applications, 2024, 44(8): 2643-2650.
[10]	Zheng WU, Zhiyou CHENG, Zhentian WANG, Chuanjian WANG, Sheng WANG, Hui XU. Deep learning-based classification of head movement amplitude during patient anaesthesia resuscitation [J]. Journal of Computer Applications, 2024, 44(7): 2258-2263.
[11]	Huanhuan LI, Tianqiang HUANG, Xuemei DING, Haifeng LUO, Liqing HUANG. Public traffic demand prediction based on multi-scale spatial-temporal graph convolutional network [J]. Journal of Computer Applications, 2024, 44(7): 2065-2072.
[12]	Zhi ZHANG, Xin LI, Naifu YE, Kaixi HU. DKP： defending against model stealing attacks based on dark knowledge protection [J]. Journal of Computer Applications, 2024, 44(7): 2080-2086.
[13]	Yiqun ZHAO, Zhiyu ZHANG, Xue DONG. Anisotropic travel time computation method based on dense residual connection physical information neural networks [J]. Journal of Computer Applications, 2024, 44(7): 2310-2318.
[14]	Song XU, Wenbo ZHANG, Yifan WANG. Lightweight video salient object detection network based on spatiotemporal information [J]. Journal of Computer Applications, 2024, 44(7): 2192-2199.
[15]	Xun SUN, Ruifeng FENG, Yanru CHEN. Monocular 3D object detection method integrating depth and instance segmentation [J]. Journal of Computer Applications, 2024, 44(7): 2208-2215.

Traffic flow forecasting via spatial-temporal multi-graph fusion

基于时空多图融合的交通流量预测

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 11

References 29

Related Articles 15

Recommended Articles

Metrics