Abstract
Brain-Computer Interfaces (BCIs) are aimed to help people suffering from severe disabilities by controlling an external device via brain activities. The major purpose of a BCI system is to decode the ongoing brain activities and translates them into output commands. EEG-based BCIs have been receiving a lot of attention due to their non-invasive nature. One of the major problems of BCI systems is their need for long training and calibration sessions. Subsequently, when a new subject is introduced to the BCI system, it takes a long time for the system to adapt the model parameters. In this study, an auto-adaptive BCI is proposed to address these issues. The method is based on an auto-adaptive calibration scheme which combines EEG data space adaptation, a weighting scheme, and a trial removal strategy. The proposed BCI framework reduces the effect of non-stationarities in EEG signals which affects session to session and subject to subject performance via building a model which adapts continuously to changes in brain signals. The proposed method was evaluated on a publicly available dataset. The results showed that the average classification accuracy increased from 75.8% to 86.92% by using the proposed method.
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.
