ABSTRACT
This study introduces AS-STGCN, a novel traffic flow prediction model that incorporates an attention mechanism and a synchronized spatio-temporal graph convolutional network. In the field of traffic prediction, deep learning models (e.g., STGCN) have outperformed traditional methods, especially in capturing temporal and spatial correlations. AS-STGCN introduces a spatio-temporal attention mechanism and simultaneous convolution, which improves the prediction accuracy and demonstrates a unique capability in capturing dynamic spatio-temporal patterns in urban traffic networks. This research is of great significance in advancing the field of traffic flow prediction and providing a more comprehensive and accurate method for predicting urban traffic dynamics.
- Niepert, M., Ahmed, M., and Kutzkov, K. 2016. Learning Convolutional Neural Networks For Graphs. In International conference on machine learning, 2014–2023.Google Scholar
- Tao L, Kejia Z, Jingsong Y, 2023. A Spatio-Temporal Heterogeneity Data Accuracy Detection Method Fused by GCN and TCN 1 School of Computer Information Technology, Northeast Petroleum University ,Daqing, 163318, China; 2 School of Qinhuangdao, Northeast Petroleum University ,Qinhuangdao, 066004 ,China, 47(2).Google Scholar
- Billy M. Williams. 2001. Multivariate Vehicular Traffic Flow Prediction: Evaluation of ARIMAX Modeling. Transportation Research Record.Google Scholar
- Chandra, S. R. and Al-Deek, H. 2009. Prediction of Freeway Traffic Speeds and Volumes Using Vector Autoregressive Models. Journal of Intelligent Transportation Systems:Technology, Planning, and Operations, Vol. 13, No. 2, pp. 53-72.Google ScholarCross Ref
- YUAN Qing, ZHAI Shihong, WU Li, 2019. Blasting Vibration Velocity Prediction Based On Least Squares Support Vector Machine With Particle Swarm Optimization Algorithm. Geosystem Engineering, 22(5):279-288.Google ScholarCross Ref
- ATWOOD J, TOWSLEY D. 2016. Diffusion-convolutional neural networks. NIPS. Proceedings of the 30th International Conference on Neural Information Processing Systems.New York: Curran Associates Inc. 2001-2009.Google Scholar
- Zheng Zhao; Weihai Chen; Xingming Wu; Peter C. Y. Chen; Jingmeng Liu. 2017. Lstm Network: A Deep Learning Approach For Short-Term Traffic Forecast. IET Intelligent Transport Systems.Google Scholar
- LIPTON Z C, BERKOWITZ J, ELKAN C. 2015. A Critical Review Of Recurrent Neural Networks For Sequence Learning. ArXiv Preprint, DOI: arXiv:1506.00019.Google Scholar
- Jianli Z ,Zhongbo L ,Qiuxia S, 2022. Attention-Based Dynamic Spatial-Temporal Graph Convolutional Networks For Traffic Speed Forecasting. Expert Systems With Applications, 204Google Scholar
- YU Bing, YIN Hao-teng, ZHU Zhan-xing. 2018. Spatio-Temporal Graph Convolutional Networks:a Deep Learning Framework For Traffic Forecasting. ACM. Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence.New York: ACM: 3634-3640.Google Scholar
- GUO Sheng-nan, LIN You-fang, FENG Ning, 2019. Attention based spatial-temporal graph convolutional networks for traffic flow forecasting. Proceedings of the AAAI Conference on Artificial Intelligence, 33(1):922-929.Google ScholarDigital Library
- Yuguang C, Jintao H, Hongbin X, 2023. Road traffic flow prediction based on dynamic spatiotemporal graph attention network. Scientific reports, 13(1):Google Scholar
- Song C, Lin Y, Guo S, 2020. Spatial-Temporal Synchronous Graph Convolutional Networks: A New Framework for Spatial-Temporal Network Data Forecasting. Proceedings of the AAAI Conference on Artificial Intelligence, 34(01):Google ScholarCross Ref
- Edoardo N D, Paolo B, Jiajia L, 2022. Editorial: High-performance tensor computations in scientific computing and data science#13; Frontiers in Applied Mathematics and Statistics, 8.Google Scholar
- Chen T, Li M, Li Y, 2015. MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems. CoRR, abs/1512.01274Google Scholar
- J. Liu and W. Guan, 2004. Asummary of traffic flow forecasting methods. J. Highway Transp.Res. Develop., vol. 21, no.3, pp.82–85, Mar.Google Scholar
Recommendations
Traffic Flow Forecasting Using a Spatial-Temporal Attention Graph Convolutional Network Predictor
Spatial Data and IntelligenceAbstractTraffic flow forecasting is a hotspot in the field of the smart city. It is a highly nonlinear, complex, and dynamic problem affected by many factors. The traditional methods cannot well model the dynamic spatial-temporal correlations of long-...
Dynamic Spatial-Temporal Graph Convolutional GRU Network for Traffic Forecasting
ICSCC '21: Proceedings of the 2021 6th International Conference on Systems, Control and CommunicationsAccurate and real-time traffic state forecasting has become an important and challenging task. The correlations of temporal and spatial are important to the accuracy of traffic forecasting. We propose a novel deep learning framework, spatial-temporal ...
Spatial-Temporal Convolutional Graph Attention Networks for Citywide Traffic Flow Forecasting
CIKM '20: Proceedings of the 29th ACM International Conference on Information & Knowledge ManagementTraffic flow prediction plays an important role in many spatial-temporal data applications, e.g., traffic management and urban planning. Various deep learning techniques are developed to model the traffic dynamic patterns with different neural network ...
Comments