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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Urban ride-hailing demand prediction is a crucial but challenging task forintelligent transportation system construction. Predictable ride-hailing demandcan facilitate more reasonable vehicle scheduling and online car-hailingplatform dispatch. Conventional deep learning methods with no externalstructured data can be accomplished via hybrid models of CNNs and RNNs bymeshing plentiful pixel-level labeled data, but spatial data sparsity andlimited learning capabilities on temporal long-term dependencies are still twostriking bottlenecks. To address these limitations, we propose a new virtualgraph modeling method to focus on significant demand regions and a novel DeepMulti-View Spatiotemporal Virtual Graph Neural Network (DMVST-VGNN) tostrengthen learning capabilities of spatial dynamics and temporal long-termdependencies. Specifically, DMVST-VGNN integrates the structures of 1DConvolutional Neural Network, Multi Graph Attention Neural Network andTransformer layer, which correspond to short-term temporal dynamics view,spatial dynamics view and long-term temporal dynamics view respectively. Inthis paper, experiments are conducted on two large-scale New York City datasetsin fine-grained prediction scenes. And the experimental results demonstrateeffectiveness and superiority of DMVST-VGNN framework in significant citywideride-hailing demand prediction.

Deep Multi-View Spatiotemporal Virtual Graph Neural Network for Significant Citywide Ride-hailing Demand Prediction