Detecting compensatory movements of stroke survivors using pressure distribution data and machine learning algorithms

Table 2 Classification performance of the k-NN and SVM classifiers in detecting compensation movements

		Back-and-forth reaching	Side-to-side reaching	Up-and-down reaching	Average
k-NN	Precision	0.984	0.988	0.996	0.989
	Recall	1.000	0.992	1.000	0.997
	F1-score	0.992	0.990	0.998	0.993
SVM	Precision	0.988	0.996	0.996	0.993
	Recall	1.000	0.979	1.000	0.993
	F1-score	0.994	0.987	0.998	0.993

ISSN: 1743-0003