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

Table 8

Average classification accuracy of hand movements for different window sizes.

Classifier	Window size (samples)
	200 (%)	250 (%)	300 (%)	350 (%)	400 (%)
KNN	76.58	83.25	88.53	92.14	96.03
SVM	76.34	82.66	87.16	91.28	94.50
Bagging	74.81	79.38	83.60	86.67	90.08