Assessment of feature selection and classification methods for recognizing motor imagery tasks from electroencephalographic signals

Recognition of motor imagery tasks (MI) from electroencephalographic (EEG) signals is crucial for developing rehabilitation andmotor assisted devices based on brain-computer interfaces (BCI). Here we consider the challenge of learning a classifier, basedon relevant patterns of the EEG signals; this learning step typically involves both feature selection, as well as a base learningalgorithm. However, in many cases it is not clear what combination of these methods will yield the best classifier. This papercontributes a detailed assessment of feature selection techniques, viz. , squared Pearson’s correlation (R 2 ), principal componentanalysis (PCA), kernel principal component analysis (kPCA) and fast correlation-based filter (FCBF); and the learning algorithms:linear discriminant analysis (LDA), support vector machines (SVM), and Feed Forward Neural Network (NN). A systematicevaluation of the combinations of these methods was performed in three two-class classification scenarios: rest vs. movement,upper vs. lower limb movement and right vs. left hand movement. FCBF in combination with SVM achieved the best results witha classification accuracy of 81.45%, 77.23% and 68.71% in the three scenarios, respectively. Importantly, FCBF determines, basedon the feature set, whether a classifier can be learned, and if so, automatically identifies the subset of relevant and non-correlatedfeatures. This suggests that FCBF is a powerful method for BCI systems based on MI. Knowledge gained here about proceduralcombinations has the potential to produce useful BCI tool, that can provide effective motor control for the users.