Jian Kui Feng1, Jing Jin1, Ian Daly2, Jiale Zhou1, Yugang Niu1, Xingyu Wang1, Andrzej Cichocki3,4,5. 1. Key Laboratory of Advanced Control and Optimization for Chemical Processes, Ministry of Education, East China University of Science and Technology, Shanghai, China. 2. Brain-Computer Interfacing and Neural Engineering Laboratory, School of Computer Science and Electronic Engineering, University of Essex, Colchester CO4 3SQ, UK. 3. Skolkowo Institute of Science and Technology (SKOLTECH), 143026 Moscow, Russia. 4. Systems Research Institute PAS, Warsaw, Poland. 5. Nicolaus Copernicus University (UMK), Torun, Poland.
Abstract
BACKGROUND: Due to the redundant information contained in multichannel electroencephalogram (EEG) signals, the classification accuracy of brain-computer interface (BCI) systems may deteriorate to a large extent. Channel selection methods can help to remove task-independent electroencephalogram (EEG) signals and hence improve the performance of BCI systems. However, in different frequency bands, brain areas associated with motor imagery are not exactly the same, which will result in the inability of traditional channel selection methods to extract effective EEG features. NEW METHOD: To address the above problem, this paper proposes a novel method based on common spatial pattern- (CSP-) rank channel selection for multifrequency band EEG (CSP-R-MF). It combines the multiband signal decomposition filtering and the CSP-rank channel selection methods to select significant channels, and then linear discriminant analysis (LDA) was used to calculate the classification accuracy. RESULTS: The results showed that our proposed CSP-R-MF method could significantly improve the average classification accuracy compared with the CSP-rank channel selection method.
BACKGROUND: Due to the redundant information contained in multichannel electroencephalogram (EEG) signals, the classification accuracy of brain-computer interface (BCI) systems may deteriorate to a large extent. Channel selection methods can help to remove task-independent electroencephalogram (EEG) signals and hence improve the performance of BCI systems. However, in different frequency bands, brain areas associated with motor imagery are not exactly the same, which will result in the inability of traditional channel selection methods to extract effective EEG features. NEW METHOD: To address the above problem, this paper proposes a novel method based on common spatial pattern- (CSP-) rank channel selection for multifrequency band EEG (CSP-R-MF). It combines the multiband signal decomposition filtering and the CSP-rank channel selection methods to select significant channels, and then linear discriminant analysis (LDA) was used to calculate the classification accuracy. RESULTS: The results showed that our proposed CSP-R-MF method could significantly improve the average classification accuracy compared with the CSP-rank channel selection method.
Authors: Jing Jin; Brendan Z Allison; Eric W Sellers; Clemens Brunner; Petar Horki; Xingyu Wang; Christa Neuper Journal: J Neural Eng Date: 2011-04-08 Impact factor: 5.379
Authors: Diego Collazos-Huertas; Julian Caicedo-Acosta; German A Castaño-Duque; Carlos D Acosta-Medina Journal: Front Neurosci Date: 2020-02-25 Impact factor: 4.677