Xu, Yuanbo, Cai, Xiao, Wang, En, Liu, Wenbin, Yang, Yongjian, and Yang, Funing
• We use three different features to calculate the dynamic adjacency matrix correlated with the dynamic correlation matrix. • We design a novel deep learning-based framework to learn dynamic spatio-temporal dependencies. • We conduct experiments on two real-world datasets in predicting urban traffic flow and traffic speed, respectively. • We collect two cities' traffic data, and make predictions for traffic flow and speed, respectively. Moreover, we conduct ablation study to prove the effectiveness of each module. Accurate urban traffic prediction is a critical issue in Intelligent Transportation Systems (ITS). It is challenging since urban traffic usually indicates high dynamic spatio-temporal correlations, leading to uncertainty and complexity of traffic status. Since the transportation network is a graph structure practically, existing works have applied Graph Convolutional Network (GCN) on urban traffic prediction with a pre-defined adjacency matrix based on node distance or connectivity. However, in many urban traffic scenarios, spatio-temporal dependencies among traffic data usually change over time, so using a fixed adjacency matrix cannot describe the dynamic dependencies. To track the dynamic spatio-temporal dependencies among traffic data, we propose a novel deep learning framework, Dynamic Traffic Correlation-based Spatio-Temporal Graph Convolutional network (DTC-STGCN), to forecast traffic flow and speed accurately. DTC-STGCN extracts a dynamic adjacency matrix from different traffic characters to describe dynamic spatio-temporal correlations. Moreover, an attention and dynamic adjacency matrix-based GCNs framework is proposed to capture urban traffic dynamic spatial features, while a long-short-term memory network (LSTM) is used to capture urban traffic temporal features, respectively. Finally, we feed the spatio-temporal features generated by GCN and LSTM, with real road segments into a hybrid graph convolution framework to simultaneously model the dynamic spatial and temporal dependencies for traffic predictions. The experiments on two real-world datasets demonstrate that the proposed DTC-STGCN model consistently outperforms the state-of-the-art traffic prediction baselines on MAE and RMSE over 10%, and achieve a stable performance for two specific tasks (long-term traffic prediction and peak time prediction). And ablation study validates the effectiveness of dynamic adjacency matrix, attention mechanism, respectively. [ABSTRACT FROM AUTHOR]