A Novel Multiscale Dynamic Graph Convolutional Network for Traffic Data Cognition

This paper investigates traffic data cognitive modelling problem in real traffic scene by fully utilizing multiscale spatio-temporal dependence between multiple traffic nodes, along with a novel dynamic graph convolutional network. Most recently, the deep learning network model is weighed down by some practical problems focused on as follows: 1)The existing graph convolution operations typically aggregate information from the given k-hop neighbors; 2)How to model the similarity of traffic data patterns among these nodes given the spatio-temporal heterogeneity of traffic data. In this paper, we propose a novel hierarchical traffic data cognitive modelling framework called Multi-Scale Spatio-Temporal Dynamic Graph Convolutional Network architecture (MSST-DGCN). And, a multi-scale graph convolution module is firstly constructed to expand the receptive field of convolutional operations, by developing a novel sub-GCNs cumulative concatenation mechanism. Meanwhile, two specified dynamic graphs are designed to model the spatio-temporal correlation among these nodes from both a proximity and long-term perspective through a novel Gaussian calculation strategy, which are efficiently able to represent/cognize the dynamic similarity of traffic data patterns. Through a series of qualitative evaluations, the present model has the ability to perceive the traffic data pattern states of nodes. At last, two real world traffic datasets experiments are developed to show that the proposed approach achieves state-of-the-art traffic data cognitive performance.