A Transfer Learning Algorithm Based on Linear Regression for Between-Subject Classification of EEG Data

摘要

Classification is the most important part of brain-computer interface (BCI) systems. Because the neural activities of different individuals are not identical, using the ordinary methods of subject-dependent classification, does not lead to high accuracy in betweensubject classification problems. As a result, in this study, we propose a novel method for classification that performs well in between-subject classification. In the proposed method, at first, the subject-dependent classifiers obtained from the train subjects are applied to the test trials to obtain a set of scores and labels for the trials. Using these scores and the real labels of the labeled test trials, linear regression is performed to find the proper linear combination of the subject-dependent classifiers that should be applied to test data. Finally, this linear combination of the classifiers’ scores is applied to test trials with unknown labels to obtain their labels. The data that we used in this study are Electroencephalogram (EEG) signals recorded during five mental tasks from nine participants with motor disabilities. Eventually, to demonstrate the performance of our proposed algorithm, we applied it to the data and compared the results with the results of the previously used methods. The algorithm that we suggested resulted in the best accuracy (72%) in comparison to other methods.