eduzhai > Applied Sciences > Engineering >

Deep CHORES Estimating Hallmark Measures of Physical Activity Using Deep Learning

  • king
  • (0) Download
  • 20210505
  • Save

... pages left unread,continue reading

Document pages: 10 pages

Abstract: Wrist accelerometers for assessing hallmark measures of physical activity(PA) are rapidly growing with the advent of smartwatch technology. Given thegrowing popularity of wrist-worn accelerometers, there needs to be a rigorousevaluation for recognizing (PA) type and estimating energy expenditure (EE)across the lifespan. Participants (66 women, aged 20-89 yrs) performed abattery of 33 daily activities in a standardized laboratory setting while atri-axial accelerometer collected data from the right wrist. A portablemetabolic unit was worn to measure metabolic intensity. We built deep learningnetworks to extract spatial and temporal representations from the time-seriesdata, and used them to recognize PA type and estimate EE. The deep learningmodels resulted in high performance; the F1 score was: 0.82, 0.81, and 95 forrecognizing sedentary, locomotor, and lifestyle activities, respectively. Theroot mean square error was 1.1 (+ -0.13) for the estimation of EE.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×