Abstract
Most electroencephalography (EEG) based brain-computer interface (BCI) systems perform brain signal recording using all possible electrodes. Recent studies have shown that the performance of a BCI system can be enhanced by removing noisy or task-irrelevant electrodes. This paper presents an automated channel selection algorithm using genetic algorithms (GA) and Bayesian linear discriminant analysis (BLDA) for a P300 based BCI. The proposed method was implemented on data set II obtained from the third BCI competition (2005). It was found that the proposed algorithm outperforms other existing channel selection method in terms of character recognition rate. The character recognition rate is maintained at approximately 90% when the number of channels used is reduced from 64 to 8. This confirms the validity of stochastic based GA as an alternative channel selection method. The selected channels indicate that the task-relevant features are concentrated mainly on the parietal and occipital lobe which agrees well with previous findings.
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.
