A Novel Feature Extraction Scheme for Myoelectric Signals Classification Using Higher Order Statistics

Author(s):  
K. Nazarpour ◽  
A.R. Sharafat ◽  
S.M. Firoozabadi
Author(s):  
RENHUAN YANG ◽  
AIGUO SONG ◽  
BAOGUO XU

Feature extraction plays an important role in brain-computer interface (BCI) systems. In order to characterize the motor imagery related rhythm and higher-order statistics information contained within the EEG signals, a novel feature extraction method based on harmonic wavelet transform and bispectrum is developed and applied to the recognition of right and left motor imageries for developing EEG-based BCI systems. The experimental results on the Graz BCI data set have shown that the separability of the two classes features extracted by the proposed method is notable. Its performance was evaluated by a linear discriminant analysis (LDA) classifier. The recognition accuracy of 90% was obtained. The recognition results have demonstrated the effectiveness of the proposed method. This method provides an effective way for EEG feature extraction in BCI system.


2017 ◽  
Vol 1 (15) ◽  
pp. 37-42
Author(s):  
J.M. Sierra-Fernández ◽  
J.J. González De La Rosa ◽  
A. Agüera-Pérez ◽  
J.C. Palomares Salas ◽  
O. Florencias-Oliveros

Sign in / Sign up

Export Citation Format

Share Document