Abstract
Most EEG-based BCI systems make use of well-studied patterns of brain activity. However, those systems involve tasks that indirectly map to simple binary commands such as yes or no or require many weeks of biofeedback training. We hypothesized that signal processing and machine learning methods can be used to discriminate EEG in a direct yes/no BCI from a single session. Blind source separation (BSS) and spectral transformations of the EEG produced a 180-dimensional feature space. We used a modified genetic algorithm (GA) wrapped around a support vector machine (SVM) classifier to search the space of feature subsets. The GA-based search found feature subsets that outperform full feature sets and random feature subsets. Also, BSS transformations of the EEG outperformed the original time series, particularly in conjunction with a subset search of both spaces. The results suggest that BSS and feature selection can be used to improve the performance of even a direct, single-session BCI.
Highlights
IntroductionIf they want to use the brain-computer interfaces (BCI) to respond yes/no to questions, they have to remember that left-hand imagined movement corresponds to “yes,” and right-hand imagined movement corresponds to “no.” Other BCI research requires extensive subject biofeedback training in order for the subject to gain some degree of voluntary influence over EEG features such as slow cortical potentials [5] or 8–12 Hz rhythms [53]
Subjects may be required to imagine left- or right-hand movement in order to use the brain-computer interfaces (BCI) [3, 37, 39]. If they want to use the BCI to respond yes/no to questions, they have to remember that left-hand imagined movement corresponds to “yes,” and right-hand imagined movement corresponds to “no.” Other BCI research requires extensive subject biofeedback training in order for the subject to gain some degree of voluntary influence over EEG features such as slow cortical potentials [5] or 8–12 Hz rhythms [53]
Blind source separation of the EEG signals prior to their spectral power transformation leads to increased classification accuracy
Summary
If they want to use the BCI to respond yes/no to questions, they have to remember that left-hand imagined movement corresponds to “yes,” and right-hand imagined movement corresponds to “no.” Other BCI research requires extensive subject biofeedback training in order for the subject to gain some degree of voluntary influence over EEG features such as slow cortical potentials [5] or 8–12 Hz rhythms [53] For both the imagined movement and biofeedback scenarios, the mapping between what the subject does and the effect on the BCI is indirect. A single session is insufficient and the subject must undergo many weeks or months of training sessions
Sign-in/Register to view highlights & summary 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.
