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

Table 9

Comparison of the classification performance of the method proposed in this work with existing studies on the same data set.

Research	Decomposition	Feature	Dimensionality reduction	Classifier	Accuracy (%)
Akben et al. [14]	No	Correlation between histogram values	No	Cascaded-structure classifier	94.72
Iqbal et al. [17]	SVD	Singular values and the mean and VAR	PCA	KNN	86.71
Too et al. [32]	DWT	WL, MAV, EWL, and EMAV	No	NB	94.22
Bergil et al. [57]	Four-level symmetric WT	Energy, mean value, standard deviation, and entropy	PCA	KNN	94.96
Proposed method	WPT	MAV, RMS, MNF, and MDF	PCA	KNN	96.03