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

Origin-Destination (OD) matrices record directional flow data between pairsof OD regions. The intricate spatiotemporal dependency in the matrices makesthe OD matrix forecasting (ODMF) problem not only intractable but alsonon-trivial. However, most of the related methods are designed for very shortsequence time series forecasting in specific application scenarios, whichcannot meet the requirements of the variation in scenarios and forecastinglength of practical applications. To address these issues, we propose aTransformer-like model named ODformer, with two salient characteristics: (i)the novel OD Attention mechanism, which captures special spatial dependenciesbetween OD pairs of the same origin (destination), greatly improves the abilityof the model to predict cross-application scenarios after combining with 2D-GCNthat captures spatial dependencies between OD regions. (ii) a PeriodSparseSelf-attention that effectively forecasts long sequence OD matrix series whileadapting to the periodic differences in different scenarios. Generousexperiments in three application backgrounds (i.e., transportation traffic, IPbackbone network traffic, crowd flow) show our method outperforms thestate-of-the-art methods.

ODformer: Spatial-Temporal Transformers for Long Sequence Origin-Destination Matrix Forecasting Against Cross Application Scenario