Classification of EEG Motor Imagery Multi Class Signals Based on Cross Correlation

Many techniques are developed for improving the classification performance of motor imagery (MI) signals used in Brain computer interfacing (BCI). Still there is scope for improvement of performance using various techniques. In this paper, cross correlation (CC) technique has been used for features extraction from EEG signal and the final classification was done based on voting method which selects the best classifier among the five classifiers used for classification. Our approach was tested on public data set 2a from BCI competition IV. The results proved that our approach outperformed already existing approaches with 29.82% improvement in kappa values.