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/

Zendy Plus

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

Zendy Tools

Zendy Open

Spatiotemporal traffic data (STTD) displays complex correlational structures.Extensive advanced techniques have been designed to capture these structuresfor effective forecasting. However, because STTD is often massive in scale,practitioners need to strike a balance between effectiveness and efficiencyusing computationally efficient models. An alternative paradigm based onmultilayer perceptron (MLP) called MLP-Mixer has the potential for bothsimplicity and effectiveness. Taking inspiration from its success in otherdomains, we propose an adapted version, named NexuSQN, for STTD forecast atscale. We first identify the challenges faced when directly applying MLP-Mixersas seriesand window-wise multivaluedness. To distinguish between spatial andtemporal patterns, the concept of ST-contextualization is then proposed. Ourresults surprisingly show that this simple-yeteffective solution can rival SOTAbaselines when tested on several traffic benchmarks. Furthermore, NexuSQN hasdemonstrated its versatility across different domains, including energy andenvironment data, and has been deployed in a collaborative project with Baiduto predict congestion in megacities like Beijing and Shanghai. Our findingscontribute to the exploration of simple-yet-effective models for real-worldSTTD forecasting.

Contextualizing MLP-Mixers Spatiotemporally for Urban Data Forecast at Scale