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

Deep learning models have shown great promise in various healthcaremonitoring applications. However, most healthcare datasets with high-quality(gold-standard) labels are small-scale, as directly collecting ground truth isoften costly and time-consuming. As a result, models developed and validated onsmall-scale datasets often suffer from overfitting and do not generalize wellto unseen scenarios. At the same time, large amounts of imprecise(silver-standard) labeled data, annotated by approximate methods with the helpof modern wearables and in the absence of ground truth validation, are startingto emerge. However, due to measurement differences, this data displayssignificant label distribution shifts, which motivates the use of domainadaptation. To this end, we introduce UDAMA, a method with two key components:Unsupervised Domain Adaptation and Multidiscriminator Adversarial Training,where we pre-train on the silver-standard data and employ adversarialadaptation with the gold-standard data along with two domain discriminators. Inparticular, we showcase the practical potential of UDAMA by applying it toCardio-respiratory fitness (CRF) prediction. CRF is a crucial determinant ofmetabolic disease and mortality, and it presents labels with various levels ofnoise (goldand silver-standard), making it challenging to establish an accurateprediction model. Our results show promising performance by alleviatingdistribution shifts in various label shift settings. Additionally, by usingdata from two free-living cohort studies (Fenland and BBVS), we show that UDAMAconsistently outperforms up to 12% compared to competitive transfer learningand state-of-the-art domain adaptation models, paving the way for leveragingnoisy labeled data to improve fitness estimation at scale.

UDAMA: Unsupervised Domain Adaptation through Multi-discriminator Adversarial Training with Noisy Labels Improves Cardio-fitness Prediction