“…In order to train the feature extraction or classification model, the large-scale and high-quality datasets are used to obtain strong robustness and high classification accuracy for the new tasks. A lot of case-studies are surveyed in [29] showing how TL improves the cross-subject transfer and the practicality of real-world BCI applications for different features and tasks. [30][31][32], support vector machine (SVM) [32][33][34][35], naive Bayes (NB) [32], linear discriminant analysis (LDA) [36,37], convolutional neural networks (CNN) [38], deep belief network (DBN) [39], AdaBoost ensemble learning [40], lattice computing [31], and fuzzy logic-based classifiers [32,41,[43][44][45][46].…”