Abstract
In brain-computer interface (BCI) applications the detection of neural processing as revealed by event-related potentials (ERPs) is a frequently used approach to regain communication for people unable to interact through any peripheral muscle control. However, the commonly used electroencephalography (EEG) provides signals of low signal-to-noise ratio, making the systems slow and inaccurate. As an alternative noninvasive recording technique, the magnetoencephalography (MEG) could provide more advantageous electrophysiological signals due to a higher number of sensors and the magnetic fields not being influenced by volume conduction. We investigated whether MEG provides higher accuracy in detecting event-related fields (ERFs) compared to detecting ERPs in simultaneously recorded EEG, both evoked by a covert attention task, and whether a combination of the modalities is advantageous. In our approach, a detection algorithm based on spatial filtering is used to identify ERP/ERF components in a data-driven manner. We found that MEG achieves higher decoding accuracy (DA) compared to EEG and that the combination of both further improves the performance significantly. However, MEG data showed poor performance in cross-subject classification, indicating that the algorithm's ability for transfer learning across subjects is better in EEG. Here we show that BCI control by covert attention is feasible with EEG and MEG using a data-driven spatial filter approach with a clear advantage of the MEG regarding DA but with a better transfer learning in EEG.
Highlights
In recent years high effort has been made in the development of brain-computer interfaces (BCI)
The three main types of brain signals applied for BCI control are the P300 potential, often used in so called matrix spellers (Farwell and Donchin, 1988), the μ-rhythm, an oscillation which is suppressed during motor execution and motor imagery (MI) (Wolpaw et al, 1991), and the steady-state visual evoked potential (SSVEP), which reflects oscillatory activity of the visual cortex driven by steady-state visual stimulation
Transfer Learning With the aim to reduce training time, we investigated the ability of transfer learning with either modality (MEG/EEG) by performing a leave-one-subject-out cross-validation, i.e., each trial is decoded by a classifier that was trained on all available data of subjects except the individual
Summary
In recent years high effort has been made in the development of brain-computer interfaces (BCI). Comparing BCI Control in EEG and MEG (Middendorf et al, 2000) Invasive techniques such as electrocorticography (ECoG) and local field potentials (LFP) provide superior signal quality compared to noninvasive techniques but bear critical shortcomings concerning long-term use and health risks (Schalk and Leuthardt, 2011). The magnetoencephalography (MEG) as another noninvasive technique has a better spatiotemporal resolution (Hämäläinen et al, 1993) but bears practical limitations for BCI use. It is considered an orthogonal complement of EEG, which provides additional value. In a recently published review article (Baillet, 2017) the authors emphasize the strength of MEG over EEG
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.
