Node Connection Strength Matrix-Based Graph Convolution Network for Traffic Flow Prediction
IEEE Transactions on Vehicular Technology
Traffic flow prediction plays an integral role in intelligent transport systems, helping to manage and control urban traffic and improving the operational efficiency of road networks. Although the current mainstream traffic flow prediction models have achieved good accuracy, they cannot effectively utilize the unique characteristics of the traffic network where the importance of a node in the traffic network is positively correlated with the traffic flow through the node. Actually, the historical traffic properties of nodes will have a great influence on the future. With this background, in this paper, we propose a node connection strength index by network representation learning to utilize the historical traffic attributes of nodes. Then, we design a graph convolution network based on the node connection strength matrix to predict the traffic flow of the node. A novel Dynamics Extractor is designed to learn the various characteristics of the traffic flow. Experimental results demonstrate that the proposed scheme has a better performance by comparison with baseline methods.
Convolution, Deep learning, Feature extraction, Graph Convolution Network, Indexes, Network Representation Learning, Node Connection Strength, Predictive models, Representation learning, Task analysis, Traffic Flow Prediction
J. Chen, W. Wang, K. Yu, X. Hu, M. Cai and M. Guizani, "Node Connection Strength Matrix-Based Graph Convolution Network for Traffic Flow Prediction," in IEEE Transactions on Vehicular Technology, April 2023, doi: 10.1109/TVT.2023.3265300.