Abstract
Electroencephalogram (EEG) classification is one of the most important research topics of Brain Computer Interface (BCI). In this paper, a novel method based on broad learning system and composite features (CF-Bls) is proposed to deal with EEG data. Firstly, EEG signals are divided into 1-second ‘frames’ and mapped into 2D images. Then, Gabor filters are used to extract the texture features of the EEG images. After that, we extract abstract convolution features from the Gabor texture features and the EEG images by a convolutional neural network, respectively. Finally, the dimension of abstract convolution features is reduced by PCA and then the features are classified by broad learning system (BLS). Experimental results show that the accuracy and Kappa coefficient of CF-BLS have been significantly improved, compared with the existing algorithms.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
