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 important in intelligent transportation systems ofwebs and beneficial to traffic safety, yet is very challenging because of thecomplex and dynamic spatio-temporal dependencies in real-world traffic systems.Prior methods use the pre-defined or learnable static graph to extract spatialcorrelations. However, the static graph-based methods fail to mine theevolution of the traffic network. Researchers subsequently generate the dynamicgraph for each time slice to reflect the changes of spatial correlations, butthey follow the paradigm of independently modeling spatio-temporaldependencies, ignoring the cross-time spatial influence. In this paper, wepropose a novel cross-time dynamic graph-based deep learning model, namedCDGNet, for traffic forecasting. The model is able to effectively capture thecross-time spatial dependence between each time slice and its historical timeslices by utilizing the cross-time dynamic graph. Meanwhile, we design a gatingmechanism to sparse the cross-time dynamic graph, which conforms to the sparsespatial correlations in the real world. Besides, we propose a novelencoder-decoder architecture to incorporate the cross-time dynamic graph-basedGCN for multi-step traffic forecasting. Experimental results on threereal-world public traffic datasets demonstrate that CDGNet outperforms thestate-of-the-art baselines. We additionally provide a qualitative study toanalyze the effectiveness of our architecture.

CDGNet: A Cross-Time Dynamic Graph-based Deep Learning Model for Traffic Forecasting