Application of Transfer Learning in Optimized Filter-Bank Regularized CSP to Classification of EEG Signals with Small Dataset

Brain-Computer Interface (BCI) systems are being used by researchers in the field to connect the brain to physical devices, like Electroencephalography (EEG) signals. they are being extensively analyzed with respect to brain electrical activities. EEG is a low-cost brain cognition and imaging technique with high temporal resolutions that can be used to extract features from Motor Imagery tasks. The common spatial pattern (CSP) and its optimized algorithms are effective methods for discriminating and classifying EEG Signals. To classify motor imagery tasks in EEG signals, we must use the CSP algorithm to extract features and discriminate spatial patterns associated with movement activities in two-class motor imagery signals. Furthermore, owing to the amount of noise in EEG signals and the limited number of trials per subject, along with a penalty term in the denominator of the CSP cost function, we may optimize the conventional CSP algorithm. In this study, due to differences in each subject’s neural activities, we employed transfer learning which used the information for other subjects to regulate features of the subject. Additionally, BCI Competition III dataset IVa was analyzed. Furthermore, this study presents the optimized Filter Bank Regularized CSP algorithm with Transfer Learning to perform the classification of the electroencephalography (EEG) motor imagery signals. Moreover, to compare the efficiency of the proposed algorithm, the conventional CSP and the proposed optimized CSP have been weighed, and results for both methods are presented. The results at the end explain that the classification with 10-fold cross-validation in comparison with that of the proposed method achieves approximately 15% and 21% higher accuracy against the R-CSP and conventional CSP, respectively.