Public traffic demand prediction based on multi-scale spatial-temporal graph convolutional network

doi:10.11772/j.issn.1001-9081.2023071045

Journal of Computer Applications ›› 2024, Vol. 44 ›› Issue (7): 2065-2072.DOI: 10.11772/j.issn.1001-9081.2023071045

• Data science and technology • Previous Articles Next Articles

Public traffic demand prediction based on multi-scale spatial-temporal graph convolutional network

Huanhuan LI, Tianqiang HUANG(), Xuemei DING, Haifeng LUO, Liqing HUANG

College of Computer and Cyber Security，Fujian Normal University，Fuzhou Fujian 350108，China

Received:2023-08-02 Revised:2023-09-25 Accepted:2023-10-09 Online:2023-10-26 Published:2024-07-10
Contact: Tianqiang HUANG
About author:LI Huanhuan， born in 1997， M. S. candidate. Her research interests include deep learning， spatial-temporal data mining.
HUANG Tianqiang， born in 1971， Ph. D.， professor. His research interests include artificial intelligence， multimedia content security， big data analytics.
DING Xuemei， born in 1972， Ph. D.， professor. Her research interests include machine learning， anomaly detection， data science， intelligent computing.
LUO Haifeng， born in 1990， Ph. D.， lecturer. His research interests include intelligent processing of 3D point clouds， spatial-temporal data mining.
HUANG Liqing， born in 1991， Ph. D.， lecturer. Her research interests include video image processing， multimedia content security， artificial intelligence.
Supported by:
National Natural Science Foundation(62072106);Fujian Natural Science Foundation(2022J01188);Educational Research Project for Young and Middle-aged Teachers of Fujian Provincial Department of Education(JAT210051)

基于多尺度时空图卷积网络的交通出行需求预测

李欢欢, 黄添强(), 丁雪梅, 罗海峰, 黄丽清

福建师范大学计算机与网络空间安全学院，福州 350108

通讯作者: 黄添强
作者简介:李欢欢（1997—），女，贵州遵义人，硕士研究生，主要研究方向：深度学习、时空数据挖掘；
黄添强（1971—），男，福建莆田人，教授，博士，主要研究方向：人工智能、多媒体内容安全、大数据分析；
丁雪梅（1972—），女，黑龙江哈尔滨人，教授，博士，主要研究方向：机器学习、异常检测、数据科学、智能计算；
罗海峰（1990—），男，福建龙岩人，讲师，博士，主要研究方向：三维点云智能处理、时空数据挖掘；
黄丽清（1991—），女，福建莆田人，讲师，博士，主要研究方向：视频图像处理、多媒体内容安全、人工智能。
基金资助:
国家自然科学基金资助项目(62072106);福建省自然科学基金资助项目(2022J01188);福建省教育厅中青年教师教育科研项目(JAT210051)

Abstract

Abstract:

High-quality public traffic demand has become one of the major challenges for Intelligent Transportation Systems （ITS）. For public traffic demand prediction， most of existing models adopt graphs with fixed structure to describe the spatial correlation of traffic demand， ignoring that traffic demand has different spatial dependence at different scales. Thus， a Multi-scale Spatial-Temporal Graph Convolutional Network （MSTGCN） model was proposed for public traffic demand prediction. Firstly， global demand similarity graph and local demand similarity graph were constructed at global and local scales. Two graphs were used to capture long-term stable and short-term dynamic features of public traffic demand. Graph Convolutional Network （GCN） was introduced to extract global and local spatial information in two graphs； besides， attention mechanism was adopted to combine the two kinds of spatial information adaptively. Moreover， Gated Recurrent Unit （GRU） was used to capture time-varying features of public traffic demand. The experimental results show that the MSTGCN model achieves the Root Mean Squared Error （RMSE）， Mean Absolute Error （MAE）， and Pearson Correlation Coefficient （PCC） of 2.788 6， 1.737 1， and 0.799 2 on New York City （NYC） Bike dataset； and 9.573 4， 5.861 2， and 0.963 1 on NYC Taxi dataset. It proves that MSTGCN model can effectively mine multi-scale spatial-temporal features to accurately predict future public traffic demand.

Key words: public traffic demand prediction, Graph Convolutional Network (GCN), spatial-temporal data mining, attention mechanism, deep learning, Intelligent Transportation System (ITS)

摘要：

满足公众高质量出行需求是智能交通系统（ITS）的主要挑战之一。目前，针对公共交通出行需求预测问题，现有模型大多采用固定结构的图描述出行需求的空间相关性，忽略了出行需求在不同尺度下具有不同的空间依赖关系。针对上述问题，提出一种多尺度时空图卷积网络（MSTGCN）模型。该模型首先从全局尺度和局部尺度构建全局需求相似图和局部需求相似图，这2种图可以捕获公共交通出行需求长期内较为稳定的全局特征和短期内动态变化的局部特征。利用图卷积网络（GCN）提取2种图中的全局空间信息和局部空间信息，并引入注意力机制融合两种空间信息。为了拟合时间序列中潜藏的时间依赖关系，利用门控循环单元（GRU）捕捉公共交通需求的时变特征。采用纽约市出租车订单数据集和自行车订单数据集进行实验，结果表明MSTGCN模型在自行车订单数据集上均方根误差（RMSE）、平均绝对误差（MAE）和皮尔逊相关系数（PCC）达2.788 6、1.737 1、0.799 2，在出租车订单数据集上RMSE、MAE、PCC达9.573 4、5.861 2、0.963 1。可见，MSTGCN模型可以有效地挖掘公共交通出行需求的多尺度时空特性，对未来公共交通出行需求进行准确预测。

关键词: 公共交通出行需求预测, 图卷积网络, 时空数据挖掘, 注意力机制, 深度学习, 智能交通系统

CLC Number:

TP183

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.

李欢欢, 黄添强, 丁雪梅, 罗海峰, 黄丽清. 基于多尺度时空图卷积网络的交通出行需求预测[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2065-2072.

Figures/Tables 12

Fig. 1 Public traffic demand prediction based on MSTGCN model

Fig. 2 Samples of NYC Bike order

Fig. 3 Samples of NYC Taxi order

Fig. 4 Dividing study area into grids

Tab. 1 Prediction results of MSTGCN model with different hidden layer dimensions

数据集	维度	RMSE	MAE	PCC
自行车	32	3.216 5	1.932 0	0.720 3
	64	2.967 9	1.828 4	0.768 0
	128	2.822 6	1.753 2	0.790 6
	256	2.788 6	1.737 1	0.799 2
出租车	32	13.659 9	8.285 6	0.925 3
	64	11.042 5	6.694 5	0.952 4
	128	9.573 4	5.861 2	0.963 1
	256	9.827 6	5.888 7	0.963 8

Fig. 5 Loss curve of MSTGCN model on NYC Bike dataset

Fig. 6 Loss curve of MSTGCN model on NYC Taxi dataset

Tab. 2 Prediction results of different models on NYC Bike dataset

模型	自行车
模型	RMSE	MAE	PCC
HA	5.200 3	3.461 7	0.166 9
XGBoost	4.049 4	2.469 0	0.486 1
STGCN	3.604 2	2.760 5	0.731 6
DCRNN	3.209 4	1.895 4	0.722 7
STG2Seq	3.984 3	2.497 6	0.515 2
Graph WaveNet	3.294 3	1.991 1	0.700 3
CCRNN	2.8382	1.7404	0.7934
DG ²RNN	2.960 1	1.816 2	0.775 5
本文模型	2.788 6	1.737 1	0.799 2

Tab. 3 Prediction results of different models on NYC Taxi dataset

模型	出租车
模型	RMSE	MAE	PCC
HA	29.780 6	16.150 9	0.633 9
XGBoost	21.199 4	11.680 6	0.807 7
STGCN	22.648 9	18.455 1	0.915 6
DCRNN	14.792 6	8.427 4	0.912 2
STG2Seq	18.045 0	9.941 5	0.865 0
GraphWaveNet	13.072 9	8.103 7	0.932 2
CCRNN	9.5631	5.4979	0.9648
DG ²RNN	9.359 0	5.379 9	0.966 6
本文模型	9.573 4	5.861 2	0.963 1

Fig. 7 Ablation experiment results of MSTGCN model on NYC Bike and NYC Taxi datasets

Tab. 4 Prediction results with different k

数据集	$k$	RMSE	MAE	PCC
自行车	3	2.922 9	1.832 0	0.772 0
	5	2.851 0	1.750 9	0.788 9
	7	2.788 6	1.737 1	0.799 2
	9	2.850 8	1.746 8	0.789 5
出租车	3	18.154 6	10.895 0	0.865 1
	5	9.573 4	5.861 2	0.963 1
	7	10.601 4	6.426 2	0.957 2
	9	15.689 6	9.929 6	0.902 9

Tab. 4 Prediction results with different k

数据集	$k$	RMSE	MAE	PCC
自行车	3	2.922 9	1.832 0	0.772 0
	5	2.851 0	1.750 9	0.788 9
	7	2.788 6	1.737 1	0.799 2
	9	2.850 8	1.746 8	0.789 5
出租车	3	18.154 6	10.895 0	0.865 1
	5	9.573 4	5.861 2	0.963 1
	7	10.601 4	6.426 2	0.957 2
	9	15.689 6	9.929 6	0.902 9

Tab. 5 Prediction results with different β

数据集	$β$	RMSE	MAE	PCC
自行车	5	2.890 1	1.789 2	0.782 0
	10	2.876 4	1.780 0	0.784 2
	15	2.788 6	1.737 1	0.799 2
	20	3.088 3	1.908 5	0.745 5
出租车	5	9.573 4	5.861 2	0.963 1
	10	10.322 8	6.184 0	0.958 4
	15	10.200 6	6.155 5	0.959 6
	20	24.508 1	14.633 0	0.733 0

Tab. 5 Prediction results with different β

数据集	$β$	RMSE	MAE	PCC
自行车	5	2.890 1	1.789 2	0.782 0
	10	2.876 4	1.780 0	0.784 2
	15	2.788 6	1.737 1	0.799 2
	20	3.088 3	1.908 5	0.745 5
出租车	5	9.573 4	5.861 2	0.963 1
	10	10.322 8	6.184 0	0.958 4
	15	10.200 6	6.155 5	0.959 6
	20	24.508 1	14.633 0	0.733 0

References 25

1	XU J， RAHMATIZADEH R， BÖLÖNI L， et al. Real-time prediction of taxi demand using recurrent neural networks ［J］. IEEE Transactions on Intelligent Transportation Systems， 2018， 19（ 8）： 2572- 2581.
2	ZHANG J， ZHENG Y， QI D. Deep spatio-temporal residual networks for citywide crowd flows prediction ［C］// Proceedings of the 31 st AAAI Conference on Artificial Intelligence. Palo Alto： AAAI Press， 2017： 1655- 1661.
3	YAO H， WU F， KE J， et al. Deep multi-view spatial-temporal network for taxi demand prediction ［C］// Proceedings of the 32 nd AAAI Conference on Artificial Intelligence. Palo Alto： AAAI Press， 2018： 2588- 2595.
4	LI Y， YU R， SHAHABI C， et al. Diffusion convolutional recurrent neural network： data-driven traffic forecasting ［C/OL］// Proceedings of the 6th International Conference on Learning Representations. New York： PLMR ［ 2023-07-01］. .
5	周榆欣，邬群勇. CLAB模型：一种乘客出租出行需求短时预测的深度学习模型［J］. 地球信息科学学报， 2023， 25（ 1）： 77- 89.
	ZHOU Y X， WU Q Y. CLAB model： a deep learning model for short-term prediction of passenger rental travel demand ［J］. Journal of Geo-Information Science， 2023， 25（ 1）： 77- 89.
6	王博伟，邓君，吕斌. 基于WCGAN的出租车需求热点预测［J］. 计算机工程与应用， 2023， 59（ 12）： 293- 300.
	WANG B W， DENG J， LYU B. Hotspot forecast of taxi demand based on WCGAN ［J］. Computer Engineering and Applications， 2023， 59（ 12）： 293- 300.
7	陈柘，刘嘉华，赵斌，等. 基于GCN和TCN的多因素城市路网出租车需求预测［J］. 控制与决策， 2023， 38（ 4）： 1031- 1038.
	CHEN Z， LIU J H， ZHAO B， et al. Multi-factor taxi demand forecasting for urban road network based on GCN and TCN ［J］. Control and Decision， 2023， 38（ 4）： 1031- 1038.
8	董成祥，魏昕，张坤鹏，等. 基于图卷积网络的乘客打车需求预测［J］. 工业工程， 2022， 25（ 5）： 98- 105.
	DONG C X， WEI X， ZHANG K P， et al. Passenger ride-hailing demand prediction based on graph convolutional networks ［J］. Industrial Engineering Journal， 2022， 25（ 5）： 98- 105.
9	魏远，林彦，郭晟楠，等. 融合出发地与目的地时空相关性的城市区域间出租车需求预测［J］. 计算机应用， 2023， 43（ 7）： 2100- 2106.
	WEI Y， LIN Y， GUO S N， et al. Prediction of taxi demands between urban regions by fusing origin-destination spatial-temporal correlation ［J］. Journal of Computer Applications， 2023， 43（ 7）： 2100- 2106.
10	ZHANG D， LI J. Multi-view fusion neural network for traffic demand prediction ［J］. Information Sciences， 2023， 646： 119303.
11	黄昕，毛政元. 基于时空多图卷积网络的网约车乘客需求预测［J］. 地球信息科学学报， 2023， 25（ 2）： 311- 323.
	HUANG X， MAO Z Y. Prediction of passenger demand for online car-hailing based on spatio-temporal multi-graph convolution network ［J］. Journal of Geo-Information Science， 2023， 25（ 2）： 311- 323.
12	XU H， ZOU T， LIU M， et al. Adaptive spatiotemporal dependence learning for multi-mode transportation demand prediction ［J］. IEEE Transactions on Intelligent Transportation Systems， 2022， 23（ 10）： 18632- 18642.
13	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.
14	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. Palo Alto： AAAI Press， 2019： 1907- 1913.
15	YE J， SUN L， DU B， et al. Coupled layer-wise graph convolution for transportation demand prediction ［J］. Proceedings of the AAAI Conference on Artificial Intelligence， 2021， 35（ 5）： 4617- 4625.
16	SHANG C， CHEN J， BI J. Discrete graph structure learning for forecasting multiple time series ［EB/OL］. （ 2021-02-15）［ 2023-07-01］. .
17	YE J， LIU Z， DU B， et al. Learning the evolutionary and multi-scale graph structure for multivariate time series forecasting ［C］// Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. New York： ACM， 2022： 2296- 2306.
18	MOREIRA-MATIAS L， GAMA J， FERREIRA M， et al. Predicting taxi-passenger demand using streaming data ［J］. IEEE Transactions on Intelligent Transportation Systems， 2013， 14（ 3）： 1393- 1402.
19	TONG Y， CHEN Y， ZHOU Z， et al. The simpler the better： a unified approach to predicting original taxi demands based on large-scale online platforms ［C］// Proceedings of the 23 rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York： ACM， 2017： 1653- 1662.
20	WU C-H， J-M HO， LEE D-T. Travel-time prediction with support vector regression ［J］. IEEE Transactions on Intelligent Transportation Systems， 2004， 5（ 4）： 276- 281.
21	GONG Y， ZHANG Y. Research of short-term traffic volume prediction based on Kalman filtering ［C］// Proceedings of the 2013 6th International Conference on Intelligent Networks and Intelligent Systems. Piscataway： IEEE， 2013： 99- 102.
22	RODRIGUEZ A， LAIO A. Clustering by fast search and find of density peaks ［J］. Science， 2014， 344（ 6191）： 1492- 1496.
23	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. Palo Alto： AAAI Press， 2018： 3634- 3640.
24	BAI L， YAO L， KANHERE S S， et al. Stg2 seq： spatial-temporal graph to sequence model for multi-step passenger demand forecasting ［C］// Proceedings of the 28th International Joint Conference on Artificial Intelligence. Palo Alto： AAAI Press， 2019： 1981- 1987.
25	ZHAO J， CHEN C， LIAO C， et al. 2F-TP： learning flexible spatiotemporal dependency for flexible traffic prediction ［J］. IEEE Transactions on Intelligent Transportation Systems， 2023， 24（ 12）： 15379- 15391.

[1]	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.
[2]	Zhiqiang ZHAO, Peihong MA, Xinhong HEI. Crowd counting method based on dual attention mechanism [J]. Journal of Computer Applications, 2024, 44(9): 2886-2892.
[3]	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.
[4]	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.
[5]	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.
[6]	Liting LI, Bei HUA, Ruozhou HE, Kuang XU. Multivariate time series prediction model based on decoupled attention mechanism [J]. Journal of Computer Applications, 2024, 44(9): 2732-2738.
[7]	Guixiang XUE, Hui WANG, Weifeng ZHOU, Yu LIU, Yan LI. Port traffic flow prediction based on knowledge graph and spatio-temporal diffusion graph convolutional network [J]. Journal of Computer Applications, 2024, 44(9): 2952-2957.
[8]	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.
[9]	Chuanlin PANG, Rui TANG, Ruizhi ZHANG, Chuan LIU, Jia LIU, Shibo YUE. Distributed power allocation algorithm based on graph convolutional network for D2D communication systems [J]. Journal of Computer Applications, 2024, 44(9): 2855-2862.
[10]	Kaipeng XUE, Tao XU, Chunjie LIAO. Multimodal sentiment analysis network with self-supervision and multi-layer cross attention [J]. Journal of Computer Applications, 2024, 44(8): 2387-2392.
[11]	Pengqi GAO, Heming HUANG, Yonghong FAN. Fusion of coordinate and multi-head attention mechanisms for interactive speech emotion recognition [J]. Journal of Computer Applications, 2024, 44(8): 2400-2406.
[12]	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.
[13]	Zhonghua LI, Yunqi BAI, Xuejin WANG, Leilei HUANG, Chujun LIN, Shiyu LIAO. Low illumination face detection based on image enhancement [J]. Journal of Computer Applications, 2024, 44(8): 2588-2594.
[14]	Shangbin MO, Wenjun WANG, Ling DONG, Shengxiang GAO, Zhengtao YU. Single-channel speech enhancement based on multi-channel information aggregation and collaborative decoding [J]. Journal of Computer Applications, 2024, 44(8): 2611-2617.
[15]	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.

Public traffic demand prediction based on multi-scale spatial-temporal graph convolutional network

基于多尺度时空图卷积网络的交通出行需求预测

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 12

References 25

Related Articles 15

Recommended Articles

Metrics