Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Table 1.

Characteristics of the 19 subjects (16 male; 3 female).

More »

Table 1 Expand

Fig 1.

The Cortex Metamax 3B automated gas analysis system.

More »

Fig 1 Expand

Fig 2.

The 20 body joints of the human skeletal model.

More »

Fig 2 Expand

Fig 3.

Temporal alignment of the hip centre joints of the participants for the squatting activity.

More »

Fig 3 Expand

Fig 4.

The average oxygen consumption of the four fundamental movements.

More »

Fig 4 Expand

Table 2.

Steady-State Energy Expenditure over 1-minute period.

More »

Table 2 Expand

Table 3.

The mean mechanical work with posture cost for the four fundamental movements over 1-minute period.

More »

Table 3 Expand

Fig 5.

Scatter plots showing relationships among the total mechanical works of upper body, lower body, and centre of mass.

More »

Fig 5 Expand

Fig 6.

The RMSE and mean percentage errors of the predicted energy costs from KNNR for different values of k.

More »

Fig 6 Expand

Fig 7.

The predicted energies from the three algorithms versus the actual energies for the 3 feature types 1D, 6D, and 7D.

The blue diagonal line denotes the 45° line. The two diagonal blue dashed lines denote the ±10% error about the 45° line.

More »

Fig 7 Expand

Fig 8.

The Bland-Altman plots for 3 features types.

The differences between observed and predicted values from the three algorithms versus the actual observed energies for the 3 feature types 1D, 6D, and 7D. The solid line is the mean of the differences for the 3 features types, while the dotted lines denote ±2 standard deviations from the mean.

More »

Fig 8 Expand

Table 4.

The RMSE (in kJ), mean percentage errors, and concordance correlation coefficients (CCC) of the GPR, KNNR, and LINR algorithms for the three feature types.

The figures in bold denote the smallest RMSE, percentage errors, or the largest concordance correlation coefficients.

More »

Table 4 Expand

Table 5.

The paired t-test results on the three algorithms with the Null hypothesis ℋ0: the predicted energy values from the two algorithms being considered come from the same distribution.

More »

Table 5 Expand

Fig 9.

The predicted energies from GPR versus the actual energies for the individual fundamental movements.

The vertical error bars denote one standard deviation on either side of the mean. The results were obtained by using the LOOCV technique on all the movements together.

More »

Fig 9 Expand

Table 6.

The RMSE (in kJ) for the four activities standing jump (SJ), arm swing (AS), squat (SQ) and jumping jack (JJ).

More »

Table 6 Expand