Application of neural network to brain-computer interface

Abstract

In this study, an neural-network-based system is proposed for the applications of brain-computer interface (BCI). Applying event-related brain potential (ERP) data acquired from the sensorimotor cortices, the system consists of three procedures, including enhanced active segment selection, feature extraction, and classification. Firstly, combined with the use of continuous wavelet transform (CWT) and Student's two-sample t-statistics, the 2D anisotropic Gaussian filter is proposed to further refine the active-segment selection. Multiresolution fractal features are then extracted from wavelet data by means of modified fractal dimension. Finally, support vector machine (SVM) is used for classification. Compared with other approaches on motor imagery data, the results indicate that the proposed method is promising in BCI applications.