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

Oxygen consumption (VO$_2$) provides established clinical and physiologicalindicators of cardiorespiratory function and exercise capacity. However, VO$_2$monitoring is largely limited to specialized laboratory settings, making itswidespread monitoring elusive. Here, we investigate temporal prediction ofVO$_2$ from wearable sensors during cycle ergometer exercise using a temporalconvolutional network (TCN). Cardiorespiratory signals were acquired from asmart shirt with integrated textile sensors alongside ground-truth VO$_2$ froma metabolic system on twenty-two young healthy adults. Participants performedone ramp-incremental and three pseudorandom binary sequence exercise protocolsto assess a range of VO$_2$ dynamics. A TCN model was developed using causalconvolutions across an effective history length to model the time-dependentnature of VO$_2$. Optimal history length was determined through minimumvalidation loss across hyperparameter values. The best performing model encoded218 s history length (TCN-VO$_2$ A), with 187 s, 97 s, and 76 s yielding lessthan 3% deviation from the optimal validation loss. TCN-VO$_2$ A showed strongprediction accuracy (mean, 95% CI) across all exercise intensities (-22ml.min$^{-1}$, [-262, 218]), spanning transitions from low-moderate (-23ml.min$^{-1}$, [-250, 204]), low-high (14 ml.min$^{-1}$, [-252, 280]),ventilatory threshold-high (-49 ml.min$^{-1}$, [-274, 176]), and maximal (-32ml.min$^{-1}$, [-261, 197]) exercise. Second-by-second classification ofphysical activity across 16090 s of predicted VO$_2$ was able to discernbetween vigorous, moderate, and light activity with high accuracy (94.1%). Thissystem enables quantitative aerobic activity monitoring in non-laboratorysettings across a range of exercise intensities using wearable sensors formonitoring exercise prescription adherence and personal fitness.

Temporal convolutional networks predict dynamic oxygen uptake response from wearable sensors across exercise intensities