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

The prompt estimation of traffic incident impacts can guide commuters intheir trip planning and improve the resilience of transportation agencies'decision-making on resilience. However, it is more challenging than node-leveland graph-level forecasting tasks, as it requires extracting the anomalysubgraph or sub-time-series from dynamic graphs. In this paper, we proposeDG-Trans, a novel traffic incident impact prediction framework, to foresee theimpact of traffic incidents through dynamic graph learning. The proposedframework contains a dual-level spatial transformer and animportance-score-based temporal transformer, and the performance of thisframework is justified by two newly constructed benchmark datasets. Thedual-level spatial transformer removes unnecessary edges between nodes toisolate the affected subgraph from the other nodes. Meanwhile, theimportance-score-based temporal transformer identifies abnormal changes in nodefeatures, causing the predictions to rely more on measurement changes after theincident occurs. Therefore, DG-Trans is equipped with dual abilities thatextract spatiotemporal dependency and identify anomaly nodes affected byincidents while removing noise introduced by benign nodes. Extensiveexperiments on real-world datasets verify that DG-Trans outperforms theexisting state-of-the-art methods, especially in extracting spatiotemporaldependency patterns and predicting traffic accident impacts. It offerspromising potential for traffic incident management systems.

DG-Trans: Dual-level Graph Transformer for Spatiotemporal Incident Impact Prediction on Traffic Networks