Temporal prediction of oxygen uptake dynamics from wearable sensors during low-, moderate-, and heavy-intensity exercise
share
Oxygen consumption (VO_2) provides established clinical and physiological indicators of cardiorespiratory function and exercise capacity. However, VO_2 monitoring is largely limited to specialized laboratory settings, making its widespread monitoring elusive. Here, we investigate temporal prediction of VO_2 from wearable sensors during cycle ergometer exercise using a temporal convolutional network (TCN). Cardiorespiratory signals were acquired from a smart shirt with integrated textile sensors alongside ground-truth VO_2 from a metabolic system on twenty-two young healthy adults. Participants performed one ramp-incremental and three pseudorandom binary sequence exercise protocols to assess a range of VO_2 dynamics. A TCN model was developed using causal convolutions across an effective history length to model the time-dependent nature of VO_2. Optimal history length was determined through minimum validation loss across hyperparameter values. The best performing model encoded 218 s history length (TCN-VO_2 A), with 187 s, 97 s, and 76 s yielding less than 3 prediction accuracy (mean, 95 ml.min^-1, [-262, 218]), spanning transitions from low-moderate (-23 ml.min^-1, [-250, 204]), low-heavy (14 ml.min^-1, [-252, 280]), ventilatory threshold-heavy (-49 ml.min^-1, [-274, 176]), and maximal (-32 ml.min^-1, [-261, 197]) exercise. Second-by-second classification of physical activity across 16090 s of predicted VO_2 was able to discern between vigorous, moderate, and light activity with high accuracy (94.1 system enables quantitative aerobic activity monitoring in non-laboratory settings across a range of exercise intensities using wearable sensors for monitoring exercise prescription adherence and personal fitness.
READ FULL TEXT
