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

Table 1

Average classification accuracy of hand movements based on different wavelet basis functions.

Classifier	Wavelet basis function
	sym3 (%)	fk8 (%)	dmey (%)	db4 (%)	coif2 (%)
KNN	95.91	96.00	97.01	95.94	96.11
SVM	91.08	91.36	92.52	90.91	90.97
Bagging	93.21	94.21	94.89	93.68	93.81