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

Air pollution and carbon emissions caused by modern transportation areclosely related to global climate change. With the help of next-generationinformation technology such as Internet of Things (IoT) and ArtificialIntelligence (AI), accurate traffic flow prediction can effectively solveproblems such as traffic congestion and mitigate environmental pollution andclimate change. It further promotes the development of IntelligentTransportation Systems (ITS) and smart cities. However, the strong spatial andtemporal correlation of traffic data makes the task of accurate trafficforecasting a significant challenge. Existing methods are usually based ongraph neural networks using predefined spatial adjacency graphs of trafficnetworks to model spatial dependencies, ignoring the dynamic correlation ofrelationships between road nodes. In addition, they usually use independentSpatio-temporal components to capture Spatio-temporal dependencies and do noteffectively model global Spatio-temporal dependencies. This paper proposes anew Spatio-temporal Causal Graph Attention Network (STCGAT) for trafficprediction to address the above challenges. In STCGAT, we use a node embeddingapproach that can adaptively generate spatial adjacency subgraphs at each timestep without a priori geographic knowledge and fine-grained modeling of thetopology of dynamically generated graphs for different time steps. Meanwhile,we propose an efficient causal temporal correlation component that containsnode adaptive learning, graph convolution, and local and global causal temporalconvolution modules to learn local and global Spatio-temporal dependenciesjointly. Extensive experiments on four real, large traffic datasets show thatour model consistently outperforms all baseline models.

STCGAT: A Spatio-temporal Causal Graph Attention Network for traffic flow prediction in Intelligent Transportation Systems