A Novel Method for Hand Movement Recognition Based on Wavelet Packet Transform and Principal Component Analysis with Surface Electromyogram

Table 2

Average classification accuracy of five different dimensional feature spaces (by using PCA).

Classifier	The dimension of the feature space
	10 (%)	20 (%)	30 (%)	40 (%)	50 (%)
KNN	90.58	92.72	96.03	94.88	95.95
SVM	92.78	92.01	94.50	88.51	84.38
Bagging	86.66	88.36	90.08	89.34	89.69