Comparison of Classifiers for the Transfer Learning of Affective Auditory P300-Based BCIs

The auditory P300-based BCI was improved by changing stimuli. However, the current method needed time for recording training data. The time can be saved by the subject-to-subject transfer learning. However, the suitable classifier for the learning remains unknown. As a first step, this study compared the classifiers for the transfer learning of the BCI. They were evaluated on the dataset of a five-class affective auditory P300-based BCI. EEG data from sixteen subjects were assigned for the training, then data from the other six subjects were used for the testing. Classifiers such as the linear support-vector machine (SVM lin.), the kernel SVM (SVM RBF), the quadratic discriminant analysis were applied and compared. As a result, the SVM lin. and the SVM RBF were suitable for this problem. The best mean classification accuracy was achieved by the SVM lin. (68.7%), and a subject showed 86% accuracy at best. These results suggest that some subjects can operate the BCI without recording his/her training data.