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

Unsupervised Domain Adaptation (UDA) methods have been successful in reducinglabel dependency by minimizing the domain discrepancy between a labeled sourcedomain and an unlabeled target domain. However, these methods face challengeswhen dealing with Multivariate Time-Series (MTS) data. MTS data typicallyconsist of multiple sensors, each with its own unique distribution. Thischaracteristic makes it hard to adapt existing UDA methods, which mainly focuson aligning global features while overlooking the distribution discrepancies atthe sensor level, to reduce domain discrepancies for MTS data. To address thisissue, a practical domain adaptation scenario is formulated as MultivariateTime-Series Unsupervised Domain Adaptation (MTS-UDA). In this paper, we proposeSEnsor Alignment (SEA) for MTS-UDA, aiming to reduce domain discrepancy at boththe local and global sensor levels. At the local sensor level, we designendo-feature alignment, which aligns sensor features and their correlationsacross domains. To reduce domain discrepancy at the global sensor level, wedesign exo-feature alignment that enforces restrictions on global sensorfeatures. We further extend SEA to SEA++ by enhancing the endo-featurealignment. Particularly, we incorporate multi-graph-based high-order alignmentfor both sensor features and their correlations. Extensive empirical resultshave demonstrated the state-of-the-art performance of our SEA and SEA++ onpublic MTS datasets for MTS-UDA.

SEA++: Multi-Graph-based High-Order Sensor Alignment for Multivariate Time-Series Unsupervised Domain Adaptation