Attention Mechanism Based on Temporal Graph Convolutional Neural Network for Traffic Flow Prediction

Abstract

In the field of transportation, accurate and real-time forecasting of traffic information is of great significance. However, Most of the existing traffic flow prediction methods lack the ability to model the dynamic spatial-temporal correlations. In order to obtain the satisfactory prediction results, We propose a new traffic prediction method based on neural network—a graph convolutional network (GCN) model based on the attention mechanism combined with gated recurrent unit (GRU). Specifically, the model uses an attention mechanism to obtain the weight information of each node at the input, and then uses GCN to learn complex topological structures to effectively capture spatial correlation, and finally uses GRU to learn the dynamics of traffic data change to capture time correlation. Applying the model to the experimental network dataset from the Traffic Performance Measurement System (PeMS) shows that our AT-GCN model can obtain spatial-temporal correlations from the traffic data, and has relatively good prediction effect.