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

The recently-developed infant wearable MAIJU provides a means toautomatically evaluate infants' motor performance in an objective and scalablemanner in out-of-hospital settings. This information could be used fordevelopmental research and to support clinical decision-making, such asdetection of developmental problems and guiding of their therapeuticinterventions. MAIJU-based analyses rely fully on the classification ofinfant's posture and movement; it is hence essential to study ways to increasethe accuracy of such classifications, aiming to increase the reliability androbustness of the automated analysis. Here, we investigated how self-supervisedpre-training improves performance of the classifiers used for analyzing MAIJUrecordings, and we studied whether performance of the classifier models isaffected by context-selective quality-screening of pre-training data to excludeperiods of little infant movement or with missing sensors. Our experiments showthat i) pre-training the classifier with unlabeled data leads to a robustaccuracy increase of subsequent classification models, and ii) selectingcontext-relevant pre-training data leads to substantial further improvements inthe classifier performance.

Evaluation of self-supervised pre-training for automatic infant movement classification using wearable movement sensors