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 highly challenging task owing to the dynamicalspatio-temporal dependencies of traffic flows. To handle this, we focus onmodeling the spatio-temporal dynamics and propose a network termed Edge SqueezeGraph Convolutional Network (ESGCN) to forecast traffic flow in multipleregions. ESGCN consists of two modules: W-module and ES module. W-module is afully node-wise convolutional network. It encodes the time-series of eachtraffic region separately and decomposes the time-series at various scales tocapture fine and coarse features. The ES module models the spatio-temporaldynamics using Graph Convolutional Network (GCN) and generates an AdaptiveAdjacency Matrix (AAM) with temporal features. To improve the accuracy of AAM,we introduce three key concepts. 1) Using edge features to directly capture thespatiotemporal flow representation among regions. 2) Applying an edge attentionmechanism to GCN to extract the AAM from the edge features. Here, the attentionmechanism can effectively determine important spatio-temporal adjacencyrelations. 3) Proposing a novel node contrastive loss to suppress obstructedconnections and emphasize related connections. Experimental results show thatESGCN achieves state-of-the-art performance by a large margin on fourreal-world datasets (PEMS03, 04, 07, and 08) with a low computational cost.

ESGCN: Edge Squeeze Attention Graph Convolutional Network for Traffic Flow Forecasting