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 prediction has been an active research topic in the domain ofspatial-temporal data mining. Accurate real-time traffic prediction isessential to improve the safety, stability, and versatility of smart citysystems, i.e., traffic control and optimal routing. The complex and highlydynamic spatial-temporal dependencies make effective predictions still facemany challenges. Recent studies have shown that spatial-temporal graph neuralnetworks exhibit great potential applied to traffic prediction, which combinessequential models with graph convolutional networks to jointly model temporaland spatial correlations. However, a survey study of graph learning,spatial-temporal graph models for traffic, as well as a fair comparison ofbaseline models are pending and unavoidable issues. In this paper, we firstprovide a systematic review of graph learning strategies and commonly usedgraph convolution algorithms. Then we conduct a comprehensive analysis of thestrengths and weaknesses of recently proposed spatial-temporal graph networkmodels. Furthermore, we build a study called STG4Traffic using the deeplearning framework PyTorch to establish a standardized and scalable benchmarkon two types of traffic datasets. We can evaluate their performance bypersonalizing the model settings with uniform metrics. Finally, we point outsome problems in the current study and discuss future directions. Source codesare available at https://github.com/trainingl/STG4Traffic.

STG4Traffic: A Survey and Benchmark of Spatial-Temporal Graph Neural Networks for Traffic Prediction