Table 7.

Overall classification accuracy and k-statistic analysis.

Exercise type		Total score (model)	k statistic (interobserver variability)	k statistic (observer 1 – MLa model)	k statistic (observer 1 – knowledge-based model)
Sitting			0.68	0.69	0.58
	Sitting exercises 1 and 2	0.90 (Gaussian process)
	Sitting exercise 3	0.86 (Gaussian process)
Standing			0.79	0.77	0.61
	Standing exercises 1 and 2	0.853 (Gaussian process)
	Standing exercise 3 (progression level 0-1)	0.912 (kNNb)
	Standing exercise 3 (progression level 2)	0.8736 (SVMc linear)
	Standing exercise 3 (progression level 3)	0.905 (random forest)
	Standing exercise 4	0.918 (Gaussian process)
Walking			0.75	0.71	0.52
	Walking exercise 1	0.899 (random forest)
	Walking exercises 2 and 3	0.813 (kNN)

^aML: machine learning.

^bkNN: k-nearest neighbors.

^cSVM: support vector machine.