EEG feature extraction and pattern classification based on motor imagery in brain-computer interface

Accurate classification of left and right hand motor imagery of EEG is an important issue in brain-computer interface (BCI). Here, discrete wavelet transform was firstly applied to extract the features of left and right hand motor imagery in EEG. Secondly, Fisher Linear Discriminant Analysis was used with two different threshold calculation methods and obtained good misclassification rate. We also used Support Vector Machine to compare the performance with Fisher Linear Discriminant Analysis. The final classification results showed that false classification rate by Support Vector Machine was the lowest and gained a ideal classification results.