Eye movement classi cation in aid of the cVEP speller
Keywords
Loading...
Authors
Issue Date
2021-06-25
Language
en
Document type
Journal Title
Journal ISSN
Volume Title
Publisher
Title
ISSN
Volume
Issue
Startpage
Endpage
DOI
Abstract
All electroencephalography-based Brain-Computer Interfaces have to deal
with signal artefacts produced by motor movements, such as jaw muscle
clenching and eye movement. Instead of attempting to remove or ignoring
these artefacts, recent studies have shown that meaningful information
can be extracted from them. Ocular artefacts in particular, possess distinct
features depending on the direction of the eye movement they originate
from. These features have been used to extract the direction of eye movement
using electrodes placed around the eyes, however recent studies have
shown that the extraction is also possible with signal from the frontal and
temporal electrodes of a standard 10-20 EEG cap. Information about the
direction is useful to visual modality BCIs that require classi cation of simultaneously
presented stimuli such as the code-modulated Visual Evoked
Potentials speller. The current paper proposes a pipeline that uses ocular
artefacts' direction and early stopping in order to increase the speed
and subsequently the characters spelled per minute of the code-modulated
Visual Evoked Potentials speller.
Description
Citation
Supervisor
Faculty
Faculteit der Sociale Wetenschappen