Abstract
A major barrier for a broad applicability of brain-computer interfaces (BCIs) based on electroencephalography (EEG) is the large number of EEG sensor electrodes typically used. The necessity for this results from the fact that the relevant information for the BCI is often spread over the scalp in complex patterns that differ depending on subjects and application scenarios. Recently, a number of methods have been proposed to determine an individual optimal sensor selection. These methods have, however, rarely been compared against each other or against any type of baseline. In this paper, we review several selection approaches and propose one additional selection criterion based on the evaluation of the performance of a BCI system using a reduced set of sensors. We evaluate the methods in the context of a passive BCI system that is designed to detect a P300 event-related potential and compare the performance of the methods against randomly generated sensor constellations. For a realistic estimation of the reduced system's performance we transfer sensor constellations found on one experimental session to a different session for evaluation. We identified notable (and unanticipated) differences among the methods and could demonstrate that the best method in our setup is able to reduce the required number of sensors considerably. Though our application focuses on EEG data, all presented algorithms and evaluation schemes can be transferred to any binary classification task on sensor arrays.
Highlights
In recent years, the investigation and development of braincomputer interfaces (BCIs) based on the electroencephalogram (EEG) has gained a broad interest
The same is true for the SSNRAS and 2SVM selection heuristics: for more than 5 sensors, both curves lie close to the center of the random selection patches
For SSNRVS, the mean performance remains on the baseline level of using all sensors down to around 18 sensors and is remarkably better than any of the other heuristics
Summary
The investigation and development of braincomputer interfaces (BCIs) based on the electroencephalogram (EEG) has gained a broad interest This technology can be utilized in a wide range of applications. Passive systems can be used to surveil users and enhance the man-machine interaction in more subtle ways [3,4]. In both cases, specific patterns in the EEG signals are exploited to predict the mental state of the user. One major barrier for the usage of BCI systems in non-clinical applications is the complicated and time-consuming preparation This procedure involves placing a large number of EEG sensor electrodes on the user’s scalp and applying a conductive gel to each of them. We compare several sensor selection algorithms in the context of a passive BCI system that has the purpose of detecting a particular event-related potential (ERP) in single-trial [7]
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.
