Table 1.
Features selected for free-living models.
Table 2.
Leave one subject out cross-validation results for the free-living models and retrained lab model.
Fig 1.
Results for the free-living, retrained laboratory, and off the shelf laboratory models for the hip placement in the hold-out validation sample.
Error bars represent standard error.
Fig 2.
Results for the free-living, retrained laboratory, and off the shelf laboratory models for the wrist placement in the hold-out validation sample.
*Significantly different from the retrained Support Vector Machine (p < 0.05) and off the shelf lab Support Vector Machine (p < 0.05). Error bars represent standard error.
Fig 3.
Bland Altman plots depicting regression line and 95% prediction intervals for off the shelf laboratory, retrained laboratory, and free-living models for hip placement.
Y-axis values represent percent error (observed–predicted EE). X-axis values represent observed energy expenditure values (kcals).
Fig 4.
Bland Altman plots depicting regression line and 95% prediction intervals for off the shelf laboratory, retrained laboratory, and free-living models for wrist placement.
Y-axis values represent percent error (observed–predicted EE). X-axis values represent observed energy expenditure values (kcals).