Please wait a minute...
Data Analysis and Knowledge Discovery  2022, Vol. 6 Issue (11): 111-125    DOI: 10.11925/infotech.2096-3467.2022.0090
Current Issue | Archive | Adv Search |
Predicting Short-Term Urban Traffics Based on Causality Analysis Graph
Wang Jie1,Gao Yuan2(),Zhang Lei1,Ma Liwen3,Feng Jun1
1School of Information Science & Technology, Northwest University, Xi’an 710127, China
2School of Economics & Management, Northwest University, Xi’an 710127, China
3Network and Data Center, Northwest University, Xi’an 710127, China
Download: PDF (3057 KB)   HTML ( 16 ) 
Export: BibTeX | EndNote (RIS)      
Abstract  

[Objective] This paper examines the complex spatial interaction mechanism between regions, aiming to effectively predict short-term traffic flow. [Methods] Based on the graph neural network, we proposed a new predictive model, which integrated the regional functional similarity matrix and the causality matrix. Then, we developed a training strategy of “Mining traffic time series causal relationship → Extracting Spatio-temporal features → Predicting traffic flows”. Third, we predicted the traffic flows by capturing the spatio-temporal dependence characteristics of regional traffic. [Results] We tested the proposed model with Didi Chuxing data set from Chengdu. Compared with the optimal baseline model, the RMSE and MAE values were reduced by 3.098% and 4.783%, respectively. [Conclusions] The causal diagram for traffic sequence can simultaneously integrate the features of spatial distance relationships, road connectivity, and function similarities. With the help of causal relationships, the proposed model could effectively predict regional traffic flows.
Key words： Short-Term Traffic Flow Prediction      Traffic Time Series Cause and Effect Diagram      Spatio-Temporal Data      Graph Neural Network     
Received: 30 January 2022      Published: 13 January 2023
ZTFLH:  U491  
Fund:National Social Science Fund of China(20BTJ047)
Corresponding Authors: Gao Yuan     E-mail: Yuangao@nwu.edu.cn
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
Jie Wang
Yuan Gao
Lei Zhang
Liwen Ma
Jun Feng

Cite this article:

Wang Jie,Gao Yuan,Zhang Lei,Ma Liwen,Feng Jun. Predicting Short-Term Urban Traffics Based on Causality Analysis Graph. Data Analysis and Knowledge Discovery, 2022, 6(11): 111-125.

URL:

https://manu44.magtech.com.cn/Jwk_infotech_wk3/EN/10.11925/infotech.2096-3467.2022.0090     OR     https://manu44.magtech.com.cn/Jwk_infotech_wk3/EN/Y2022/V6/I11/111

Spatial Dependence of Urban Traffic Flow Between Regions
Causal Effects in Traffic of Urban Regional
Traffic Time-Series Directed Acyclic Graph
ST-CAG Framework Model
Graph Convolution Neural Network
Gated Recurrent Unit
方法 时间特征 空间特征 因果特征
ARIMA √
SARIMA √
SVR √
LSTM √
GRU √
ConvLSTM √ √
DCRNN √ √
T-GCN √ √
ST-CAG（本文） √ √ √
Comparison of Characteristics Considered by Various Models
The Visualization Results of Regions with Causal Relationship
Comparison Between Target Time Series and Its Cause / Non-cause Time Series
区域 v g r e e n v y e l l o w
v 227 0.847 0.642
v 388 0.816 0.922
Functional Similarity Between Different Regions
Difference Statistics for the Distribution of Each Type of POI Between Regions with Causality
Adjacency Matrix Heatmap Corresponding to TCG Generated under Different Threshold Combinations
方法 5分钟 10分钟 15分钟
MAE RMSE MAE RMSE MAE RMSE
ARIMA 29.105 32.827 29.301 32.982 29.511 33.010
SARIMA 28.235 32.297 28.239 32.298 28.240 32.298
SVR 12.079 17.195 12.582 17.524 12.915 17.957
LSTM 11.558 15.932 11.984 16.532 12.289 16.991
GRU 11.165 15.915 11.581 16.447 11.805 16.862
ConvLSTM 11.359 16.583 11.735 16.905 11.955 16.997
DCRNN 11.263 16.465 11.619 16.617 11.892 16.918
T-GCN 13.525 18.578 13.531 18.602 13.551 18.630
ST-CAG（本文） 10.631 15.422 10.955 15.951 11.361 16.419
Accuracy Between ST-CAG Model and Other Models in Different Prediction Time Lengths
Ablation Experiment
[1] Song C, Lin Y F, Guo S N, et al. Spatial-Temporal Synchronous Graph Convolutional Networks: A New Framework for Spatial-Temporal Network Data Forecasting[C]// Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(1): 914-921.
[2] Molavipour S, Bassi G, Čičić M, et al. Causality Graph of Vehicular Traffic Flow[OL]. arXiv Preprint, arXiv: 2011.11323.
[3] Lv M Q, Hong Z X, Chen L, et al. Temporal Multi-Graph Convolutional Network for Traffic Flow Prediction[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(6): 3337-3348.
doi: 10.1109/TITS.2020.2983763
[4] Zhang J B, Zheng Y, Qi D K. Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction[C]// Proceedings of the 31st AAAI Conference on Artificial Intelligence. 2017: 1655-1661.
[5] Pearl J, MacKenzie D. The Book of Why: The New Science of Cause and Effect[M]. New York: Basic Books, 2018.
[6] Williams B M, Hoel L A. Modeling and Forecasting Vehicular Traffic Flow as a Seasonal ARIMA Process: Theoretical Basis and Empirical Results[J]. Journal of Transportation Engineering, 2003, 129(6): 664-672.
doi: 10.1061/(ASCE)0733-947X(2003)129:6(664)
[7] Drucker H, Burges C J C, Kaufman L, et al. Support Vector Regression Machines[C]// Proceedings of the 9th International Conference on Neural Information Processing Systems. 1996: 155-161.
[8] Guo S N, Lin Y F, Li S J, et al. Deep Spatial-Temporal 3D Convolutional Neural Networks for Traffic Data Forecasting[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 20(10): 3913-3926.
doi: 10.1109/TITS.2019.2906365
[9] Li X C, Cheng Y, Cong G, et al. Discovering Pollution Sources and Propagation Patterns in Urban Area[C]// Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2017: 1863-1872.
[10] Zhao L, Song Y J, Zhang C, et al. T-GCN: A Temporal Graph Convolutional Network for Traffic Prediction[J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 21(9): 3848-3858.
doi: 10.1109/TITS.2019.2935152
[11] Bai L, Yao L N, Li C, et al. Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting[C]// Proceedings of the 34th International Conference on Neural Information Processing Systems. 2020: 17804-17815.
[12] Wu T L, Chen F, Wan Y. Graph Attention LSTM Network: A New Model for Traffic Flow Forecasting[C]// Proceedings of 2018 5th International Conference on Information Science and Control Engineering. 2018: 241-245.
[13] Cai L, Janowicz K, Mai G C, et al. Traffic Transformer: Capturing the Continuity and Periodicity of Time Series for Traffic Forecasting[J]. Transactions in GIS, 2020, 24(3): 736-755.
doi: 10.1111/tgis.12644
[14] Zhu J Y, Zhang C, Zhang H C, et al. pg-Causality: Identifying Spatiotemporal Causal Pathways for Air Pollutants with Urban Big Data[J]. IEEE Transactions on Big Data, 2018, 4(4): 571-585.
doi: 10.1109/TBDATA.2017.2723899
[15] Liu W, Zheng Y, Chawla S, et al. Discovering Spatio-Temporal Causal Interactions in Traffic Data Streams[C]// Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2011: 1010-1018.
[16] Chu V W, Wong R K, Liu W, et al. Causal Structure Discovery for Spatio-Temporal Data[C]// Proceedings of the 2014 International Conference on Database Systems for Advanced Applications. 2014: 236-250.
[17] Kapoor V, Saxena D, Raychoudhury V, et al. Real Time Building and Maintaining Causal Congestion Graph for Intelligent Traffic Management[C]// Proceedings of 2018 IEEE International Conference on Pervasive Computing and Communications Workshops. 2018: 770-775.
[18] Granger C W. Investigating Causal Relations by Econometric Models and Cross-Spectral Methods[J]. Econometrica, 1969, 37(2): 424-438.
doi: 10.2307/1912791
[19] Li L, Su X N, Wang Y W, et al. Robust Causal Dependence Mining in Big Data Network and Its Application to Traffic Flow Predictions[J]. Transportation Research Part C: Emerging Technologies, 2015, 58: 292-307.
doi: 10.1016/j.trc.2015.03.003
[20] Peters J, Janzing D, Schölkopf B. Elements of Causal Inference: Foundations and Learning Algorithms[M]. MA: MIT Press, 2017.
[21] Pfister N, Bühlmann P, Peters J. Invariant Causal Prediction for Sequential Data[J]. Journal of the American Statistical Association, 2019, 114(527): 1264-1276.
doi: 10.1080/01621459.2018.1491403
[22] Mastakouri A A, Schölkopf B, Janzing D. Necessary and Sufficient Conditions for Causal Feature Selection in Time Series with Latent Common Causes[C]// Proceedings of the 38th International Conference on Machine Learning. 2021: 7502-7511.
[23] 刘菊, 许珺, 蔡玲, 等. 基于出租车用户出行的功能区识别[J]. 地球信息科学学报, 2018, 20(11):1550-1561.
doi: 10.12085/dqxxkx.2018.180164
[23] (Liu Ju, Xu Jun, Cai Ling, et al. Identifying Functional Regions Based on the Spatio-Temporal Pattern of Taxi Trajectories[J]. Journal of Geo-Information Science, 2018, 20(11): 1550-1561.)
doi: 10.12085/dqxxkx.2018.180164
[24] Guo J P, Zhang W X, Fan W G, et al. Combining Geographical and Social Influences with Deep Learning for Personalized Point-of-Interest Recommendation[J]. Journal of Management Information Systems, 2018, 35(4): 1121-1153.
doi: 10.1080/07421222.2018.1523564
[25] Ho S L, Xie M, Goh T N. A Comparative Study of Neural Network and Box-Jenkins ARIMA Modeling in Time Series Prediction[J]. Computers & Industrial Engineering, 2002, 42(2-4): 371-375.
doi: 10.1016/S0360-8352(02)00036-0
[26] Hochreiter S, Schmidhuber J. Long Short-Term Memory[J]. Neural Computation, 1997, 9(8): 1735-1780.
doi: 10.1162/neco.1997.9.8.1735 pmid: 9377276
[27] Chung J, Gulcehre C, Cho K, et al. Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling[C]// Proceedings of NIPS 2014 Workshop on Deep Learning. 2014.
[28] Shi X J, Chen Z R, Wang H, et al. Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting[C]// Proceedings of the 28th International Conference on Neural Information Processing Systems - Volume 1. 2015: 802-810.
[29] Li Y G, Yu R, Shahabi C, et al. Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting[OL]. arXiv Preprint, arXiv:1707.01926.
[1] Cheng Quan, She Dexin. Drug Recommendation Based on Graph Neural Network with Patient Signs and Medication Data[J]. 数据分析与知识发现, 2022, 6(9): 113-124.
[2] Gu Yaowen,Zheng Si,Yang Fengchun,Li Jiao. GNN-MTB: An Anti-Mycobacterium Drug Virtual Screening Model Based on Graph Neural Network[J]. 数据分析与知识发现, 2022, 6(11): 93-102.
[3] Feng Xiaodong, Hui Kangxin. Topic Clustering for Social Media Texts with Heterogeneous Graph Neural Networks[J]. 数据分析与知识发现, 2022, 6(10): 9-19.
[4] Huang Xuejian, Liu Yuyang, Ma Tinghuai. Classification Model for Scholarly Articles Based on Improved Graph Neural Network[J]. 数据分析与知识发现, 2022, 6(10): 93-102.
[5] Gu Yaowen, Zhang Bowen, Zheng Si, Yang Fengchun, Li Jiao. Predicting Drug ADMET Properties Based on Graph Attention Network[J]. 数据分析与知识发现, 2021, 5(8): 76-85.
[6] Xuhui Li,Yang Liu. Review of Spatio-temporal Data Modeling Methods[J]. 数据分析与知识发现, 2019, 3(3): 1-13.
  Copyright © 2016 Data Analysis and Knowledge Discovery   Tel/Fax:(010)82626611-6626，82624938   E-mail:jishu@mail.las.ac.cn