The analysis of EEG (Electroencephalography) signals aims to create new interfaces for the development of useful systems and products by shedding light on the functioning of our brain and learning more about our brain. In this study, the motor imagery EEG data obtained from the publicly available BCI competition IV is classified using multi-resolution representation analyze method. The data set is cue based BCI paradigm consisted of four different motor imagery tasks obtained from nine subject; the imagination of movement of the left hand, right hand, both feet, and tongue. Initially, a new data set consists of left- and right-hand movements is formed from the EEG data set. Because the aim of this study is to classify the right- and left-hand movements. The proposed method involves an approach to extract the features from the new data set using fast finite shearlet transform (FFST). Mainly, coefficients of the FFST are attained applying the FFST to EEG data and then the coefficients are stored as features. For the dimensionality reduction and eliminating the redundant data, Principal component analyze (PCA) is employed for the feature selection. The final data set is served to the support vector machine (SVM) classifier to discriminate motor imagery EEG data.
Anahtar Kelimeler: EEG, Motor Imagery BCI Data, FFST, SVM
|
