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

Short-term route prediction on road networks allows us to anticipate thefuture trajectories of road users, enabling a plethora of intelligenttransportation applications such as dynamic traffic control or personalizedroute recommendation. Despite the recent advances in this area, existingmethods focus primarily on learning sequential patterns, neglecting theinherent spatial structure in road networks that can affect human routingdecisions. To fill the gap, this paper introduces RouteKG, a novel KnowledgeGraph-based framework for route prediction. Specifically, we construct aKnowledge Graph on the road network, thereby learning and leveraging spatialrelations, especially moving directions, which are crucial for humannavigation. Moreover, an n-ary tree-based algorithm is introduced toefficiently generate top-K routes in a batch mode, enhancing scalability andcomputational efficiency. To further optimize the prediction performance, arank refinement module is incorporated to fine-tune the candidate routerankings. The model performance is evaluated using two real-world vehicletrajectory datasets from two Chinese cities, Chengdu and Shanghai, undervarious practical scenarios. The results demonstrate a significant improvementin accuracy over baseline methods, with an average increase of 6.2%, 7.8%, and6.1% in top-1, 5, and 10 routes predictions, respectively. We further validateour model through a case study that utilizes the pretrained model as asimulator for real-time traffic flow estimation at the link level. The proposedRouteKG promises wide-ranging applications in vehicle navigation, trafficmanagement, and other intelligent transportation tasks.

RouteKG: A knowledge graph-based framework for route prediction on road networks