Applying ubiquitous sensing to estimate perceived exertion based on cardiorespiratory features

Abstract Reliable monitoring of one’s response to exercise intensity is imperative effectively plan and manage training, but not always practical in impact sports settings. This study aimed evaluate if an inexpensive mobile cardio-respiratory system can achieve similar performance a metabolic cart estimating rated perceived exertion. Eight adult men volunteered perform treadmill tests under different conditions. Cardiorespiratory data were collected using instrumented oral-cavity device, as well their ratings Pearson correlation corrected for repeated measurements stepwise regression analysis used observe the relationship between cardiorespiratory features exertion determine proportion variance that could be explained by measurements. Minute ventilation was found most associated variable exertion, closely followed novel metric called audio minute volume, which device. A generalised linear model combining ventilation, heart rate respiration accounted 64% whilst with only volume 56%. Our indicates key during indoor running exercises. Audio also observed comparably lab-based research techniques offer potential real-world collection athlete’s physiological load estimation