MSASGCN :  Multi-Head Self-Attention Spatiotemporal Graph Convolutional Network for Traffic Flow Forecasting

Cao, Yang; Liu, Detian; Yin, Qizheng; Xue, Fei; Tang, Hengliang; Zhang, ed., Yong

doi:10.1155/2022/2811961

Title: MSASGCN : Multi-Head Self-Attention Spatiotemporal Graph Convolutional Network for Traffic Flow Forecasting

Journal Article · Fri Jun 17 00:00:00 EDT 2022 · Journal of Advanced Transportation

DOI:https://doi.org/10.1155/2022/2811961· OSTI ID:1872814

^[1]; Liu, Detian ^[1]; Yin, Qizheng ^[1]; Xue, Fei ^[1];

^[1]; Zhang, ed., Yong

School of Information, Beijing Wuzi University, Beijing 101149, China

Traffic flow forecasting is an essential task of an intelligent transportation system (ITS), closely related to intelligent transportation management and resource scheduling. Dynamic spatial-temporal dependencies in traffic data make traffic flow forecasting to be a challenging task. Most existing research cannot model dynamic spatial and temporal correlations to achieve well-forecasting performance. The multi-head self-attention mechanism is a valuable method to capture dynamic spatial-temporal correlations, and combining it with graph convolutional networks is a promising solution. Therefore, we propose a multi-head self-attention spatiotemporal graph convolutional network (MSASGCN) model. It can effectively capture local correlations and potential global correlations of spatial structures, can handle dynamic evolution of the road network, and, in the time dimension, can effectively capture dynamic temporal correlations. Experiments on two real datasets verify the stability of our proposed model, obtaining a better prediction performance than the baseline algorithms. The correlation metrics get significantly reduced compared with traditional time series prediction methods and deep learning methods without using graph neural networks, according to MAE and RMSE results. Compared with advanced traffic flow forecasting methods, our model also has a performance improvement and a more stable prediction performance. We also discuss some problems and challenges in traffic forecasting.

View Journal Article

Cite

Export

Save

Sponsoring Organization:: USDOE EM Office of Technology Innovation and Development (EM-30)

OSTI ID:: 1872814

Journal Information:: Journal of Advanced Transportation, Journal Name: Journal of Advanced Transportation Vol. 2022; ISSN 0197-6729

Publisher:: Hindawi Publishing CorporationCopyright Statement

Country of Publication:: Egypt

Language:: English

References (24)

Traffic Data Reconstruction via Adaptive Spatial-Temporal Correlations Wang, Yang; Zhang, Yong; Piao, Xinglin IEEE Transactions on Intelligent Transportation Systems, Vol. 20, Issue 4 https://doi.org/10.1109/tits.2018.2854968	journal	April 2019
Road Traffic Forecasting: Recent Advances and New Challenges Lana, Ibai; Del Ser, Javier; Velez, Manuel IEEE Intelligent Transportation Systems Magazine, Vol. 10, Issue 2 https://doi.org/10.1109/mits.2018.2806634	journal	July 2018
Neural Network for Graphs: A Contextual Constructive Approach Micheli, A. IEEE Transactions on Neural Networks, Vol. 20, Issue 3 https://doi.org/10.1109/tnn.2008.2010350	journal	March 2009
Optimized Graph Convolution Recurrent Neural Network for Traffic Prediction Guo, Kan; Hu, Yongli; Qian, Zhen IEEE Transactions on Intelligent Transportation Systems, Vol. 22, Issue 2 https://doi.org/10.1109/tits.2019.2963722	journal	February 2021
IGAGCN: Information geometry and attention-based spatiotemporal graph convolutional networks for traffic flow prediction An, Jiyao; Guo, Liang; Liu, Wei Neural Networks, Vol. 143 https://doi.org/10.1016/j.neunet.2021.05.035	journal	November 2021
CaEGCN: Cross-Attention Fusion based Enhanced Graph Convolutional Network for Clustering Huo, Guangyu; Zhang, Yong; Gao, Junbin IEEE Transactions on Knowledge and Data Engineering https://doi.org/10.1109/tkde.2021.3125020	journal	January 2021
A Low Rank Dynamic Mode Decomposition Model for Short-Term Traffic Flow Prediction Yu, Yadong; Zhang, Yong; Qian, Sean IEEE Transactions on Intelligent Transportation Systems, Vol. 22, Issue 10 https://doi.org/10.1109/tits.2020.2994910	journal	October 2021
Urban flow prediction from spatiotemporal data using machine learning: A survey Xie, Peng; Li, Tianrui; Liu, Jia Information Fusion, Vol. 59 https://doi.org/10.1016/j.inffus.2020.01.002	journal	July 2020
Freeway Performance Measurement System: Mining Loop Detector Data Chen, Chao; Petty, Karl; Skabardonis, Alexander Transportation Research Record: Journal of the Transportation Research Board, Vol. 1748, Issue 1 https://doi.org/10.3141/1748-12	journal	January 2001
A Novel Traffic Flow Forecasting Method Based on RNN-GCN and BRB Zhu, Hailong; Xie, Yawen; He, Wei Journal of Advanced Transportation, Vol. 2020 https://doi.org/10.1155/2020/7586154	journal	October 2020
Traffic Flow Prediction via Spatial Temporal Graph Neural Network Wang, Xiaoyang; Ma, Yao; Wang, Yiqi WWW '20: The Web Conference 2020, Proceedings of The Web Conference 2020 https://doi.org/10.1145/3366423.3380186	conference	April 2020
GMAN: A Graph Multi-Attention Network for Traffic Prediction Zheng, Chuanpan; Fan, Xiaoliang; Wang, Cheng Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34, Issue 01 https://doi.org/10.1609/aaai.v34i01.5477	journal	April 2020
A Survey on Modern Deep Neural Network for Traffic Prediction: Trends, Methods and Challenges Tedjopurnomo, David Alexander; Bao, Zhifeng; Zheng, Baihua IEEE Transactions on Knowledge and Data Engineering https://doi.org/10.1109/tkde.2020.3001195	journal	January 2020
Spatial-Temporal Synchronous Graph Convolutional Networks: A New Framework for Spatial-Temporal Network Data Forecasting Song, Chao; Lin, Youfang; Guo, Shengnan Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34, Issue 01 https://doi.org/10.1609/aaai.v34i01.5438	journal	April 2020
Cross-Node Federated Graph Neural Network for Spatio-Temporal Data Modeling Meng, Chuizheng; Rambhatla, Sirisha; Liu, Yan KDD '21: The 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining https://doi.org/10.1145/3447548.3467371	conference	August 2021
Multi-Range Attentive Bicomponent Graph Convolutional Network for Traffic Forecasting Chen, Weiqi; Chen, Ling; Xie, Yu Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34, Issue 04 https://doi.org/10.1609/aaai.v34i04.5758	journal	April 2020
Traffic flow prediction over muti-sensor data correlation with graph convolution network Li, Wei; Wang, Xin; Zhang, Yiwen Neurocomputing, Vol. 427 https://doi.org/10.1016/j.neucom.2020.11.032	journal	February 2021
How to Build a Graph-Based Deep Learning Architecture in Traffic Domain: A Survey Ye, Jiexia; Zhao, Juanjuan; Ye, Kejiang IEEE Transactions on Intelligent Transportation Systems https://doi.org/10.1109/TITS.2020.3043250	journal	January 2021
Long Short-Term Memory Hochreiter, Sepp; Schmidhuber, Jürgen Neural Computation, Vol. 9, Issue 8 https://doi.org/10.1162/neco.1997.9.8.1735	journal	November 1997
Artificial intelligence-based vehicular traffic flow prediction methods for supporting intelligent transportation systems Boukerche, Azzedine; Tao, Yanjie; Sun, Peng Computer Networks, Vol. 182 https://doi.org/10.1016/j.comnet.2020.107484	journal	December 2020
Managing Emergency Traffic Evacuation With a Partially Random Destination Allocation Strategy: A Computational-Experiment-Based Optimization Approach Lv, Yisheng; Zhang, Xiqiao; Kang, Wenwen IEEE Transactions on Intelligent Transportation Systems, Vol. 16, Issue 4 https://doi.org/10.1109/tits.2015.2399852	journal	August 2015
Attention Based Spatial-Temporal Graph Convolutional Networks for Traffic Flow Forecasting Guo, Shengnan; Lin, Youfang; Feng, Ning Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33 https://doi.org/10.1609/aaai.v33i01.3301922	journal	July 2019
GeoMAN: Multi-level Attention Networks for Geo-sensory Time Series Prediction Liang, Yuxuan; Ke, Songyu; Zhang, Junbo Twenty-Seventh International Joint Conference on Artificial Intelligence {IJCAI-18}, Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence https://doi.org/10.24963/ijcai.2018/476	conference	July 2018
Graph neural networks: A review of methods and applications Zhou, Jie; Cui, Ganqu; Hu, Shengding AI Open, Vol. 1 https://doi.org/10.1016/j.aiopen.2021.01.001	journal	January 2020

Similar Records

A General Spatiotemporal Imputation Framework for Missing Sensor Data

Conference · Thu Aug 31 00:00:00 EDT 2023 · OSTI ID:1872814

Tharzeen, Aabila; Munikoti, Sai; Prakash, Punit; +2 more

Ultra-Short-Term Spatiotemporal Forecasting of Renewable Resources: An Attention Temporal Convolutional Network Based Approach

Journal Article · Mon May 16 00:00:00 EDT 2022 · IEEE Transactions on Smart Grid · OSTI ID:1872814

Liang, Junkai; Tang, Wenyuan

Attend and Decode: 4D fMRI Task State Decoding Using Attention Models

Software · Fri May 07 00:00:00 EDT 2021 · OSTI ID:1872814

Ng, Brenda M.; Kaplan, Alan D.; Ray, Priyadip; +1 more

Title: MSASGCN : Multi-Head Self-Attention Spatiotemporal Graph Convolutional Network for Traffic Flow Forecasting

Citation Formats

References (24)

Similar Records

Related Subjects