01698033

Component

Traffic forecasting is a challenging task, due to the complicated spatial dependencies on roadway networks and the time-varying traffic patterns. To address this challenge, the authors learn the traffic network as a graph and propose a novel deep learning framework, High-Order Graph Convolutional Long Short-Term Memory Neural Network (HGC-LSTM), to learn the interactions between links in the traffic network and forecast the network-wide traffic state. The authors define the high-order traffic graph convolution based on the physical network topology. The proposed framework employs L1-norms on the graph convolution weights and L2-norms on the graph convolution features to identify the most influential links in the traffic network. The authors propose a novel Real-Time Branching Learning (RTBL) algorithm for the HGC-LSTM framework to accelerate the training process for spatio-temporal data. Experiments show that the authors HGC-LSTM network is able to capture the complex spatio-temporal dependencies efficiently present in a vehicle traffic network and consistently outperforms state-of-the-art baseline methods on two heterogeneous real-world traffic datasets. The visualization of graph convolution weights shows that the proposed framework can accurately recognize the most influential roadway segments in real-world traffic networks.

This paper was sponsored by TRB committee ABJ70 Standing Committee on Artificial Intelligence and Advanced Computing Applications.

19-05236

English

0000-0002-5780-4312

6p

2019

Transportation Research Board 98th Annual Meeting

Digital/other

Figures; References; Tables

Intelligent transportation systems; Machine learning; Neural networks; Traffic forecasting; Traffic speed

Data and Information Technology; Highways; Operations and Traffic Management

Transportation Research Board Annual Meeting 2019 Paper #19-05236

TRIS, TRB, ATRI

Dec 7 2018 9:44AM