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

In practice, Wearable Human Activity Recognition (WHAR) models usually faceperformance degradation on the new user due to user variance. Unsuperviseddomain adaptation (UDA) becomes the natural solution to cross-user WHAR underannotation scarcity. Existing UDA models usually align samples across domainswithout differentiation, which ignores the difference among samples. In thispaper, we propose an unsupervised domain adaptation model with sample weightlearning (SWL-Adapt) for cross-user WHAR. SWL-Adapt calculates sample weightsaccording to the classification loss and domain discrimination loss of eachsample with a parameterized network. We introduce the meta-optimization basedupdate rule to learn this network end-to-end, which is guided bymeta-classification loss on the selected pseudo-labeled target samples.Therefore, this network can fit a weighting function according to thecross-user WHAR task at hand, which is superior to existing sampledifferentiation rules fixed for special scenarios. Extensive experiments onthree public WHAR datasets demonstrate that SWL-Adapt achieves thestate-of-the-art performance on the cross-user WHAR task, outperforming thebest baseline by an average of 3.1% and 5.3% in accuracy and macro F1 score,respectively.

SWL-Adapt: An Unsupervised Domain Adaptation Model with Sample Weight Learning for Cross-User Wearable Human Activity Recognition