English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Traffic forecasting is a problem of intelligent transportation systems (ITS)and crucial for individuals and public agencies. Therefore, researches paygreat attention to deal with the complex spatio-temporal dependencies oftraffic system for accurate forecasting. However, there are two challenges: 1)Most traffic forecasting studies mainly focus on modeling correlations ofneighboring sensors and ignore correlations of remote sensors, e.g., businessdistricts with similar spatio-temporal patterns; 2) Prior methods which usestatic adjacency matrix in graph convolutional networks (GCNs) are not enoughto reflect the dynamic spatial dependence in traffic system. Moreover,fine-grained methods which use self-attention to model dynamic correlations ofall sensors ignore hierarchical information in road networks and have quadraticcomputational complexity. In this paper, we propose a novel dynamic multi-graphconvolution recurrent network (DMGCRN) to tackle above issues, which can modelthe spatial correlations of distance, the spatial correlations of structure,and the temporal correlations simultaneously. We not only use thedistance-based graph to capture spatial information from nodes are close indistance but also construct a novel latent graph which encoded the structurecorrelations among roads to capture spatial information from nodes are similarin structure. Furthermore, we divide the neighbors of each sensor intocoarse-grained regions, and dynamically assign different weights to each regionat different times. Meanwhile, we integrate the dynamic multi-graph convolutionnetwork into the gated recurrent unit (GRU) to capture temporal dependence.Extensive experiments on three real-world traffic datasets demonstrate that ourproposed algorithm outperforms state-of-the-art baselines.

DMGCRN: Dynamic Multi-Graph Convolution Recurrent Network for Traffic Forecasting