Classification of motor imagery ecog signals using support vector machine for brain computer interface

Although brain-computer interface (BCI) methods have been evolving quickly in recent decades, there still a number of unsolved difficulties, such as enhancement of motor imagery (MI) classification. The most commonly used signals in BCI investigations is electroencephalography(EEG) recordings. EEG has restricted tenacity and needs extensive training and has restricted stability. Over the past ten years, an expanding number of studies has discovered the use of electrocorticography (ECoG) activity extracting signals from the surface of the mind. ECoG has attracted considerable and expanding interest, because its mechanical characteristics should readily support robust and chronic implementations of BCI systems in humans. In this paper, we suggest a hybrid algorithm to advance the classification achievement rate of MI-based electrocorticography (ECoG) in BCIs. To verify the effectiveness of the suggested classifier, we restore the SVM classifier with the identical features extracted from the cross-correlation method for the classification. The performances of those procedures are assessed with classification correctness through a 10-fold cross-validation procedure. We furthermore consider the performance of the suggested procedure by comparing it with existing system.