Exploring the impact of stimulus transparency in ERP-BCI under RSVP.
Loading...
Identifiers
Publication date
Reading date
Collaborators
Advisors
Tutors
Editors
Journal Title
Journal ISSN
Volume Title
Publisher
ACM Library Digital
Share
Department/Institute
Keywords
Abstract
Rapid serial visual presentation (RSVP) is currently one of the most
suitable paradigms for implementing a visual brain–computer interface
based on event-related potentials (ERP-BCI) for patients with
limited ocular motility. This paradigm presents stimuli centered
in the user’s field of vision, which may hinder the patient from
attending to other elements on the screen. A potential solution to
this could be the use of semi-transparent stimuli, allowing both the
stimulus and the background to be perceived. Therefore, the objective
of this study is to evaluate the impact of stimulus transparency
on ERP-BCI performance under the RSVP paradigm. Five participants
tested the ERP-BCI under RSVP using three different stimulus
transparencies with alpha channels set to 255 (C1), 85 (C2), and 28
(C3). The results showed the following average BCI classification
accuracies: C1, 70%; C2, 74.67%; and C3, 60.67%. Although the analyses
did not reveal significant differences, the results suggest that
the transparency level should be carefully manipulated to maintain
a balance between stimulus transparency and performance, with
C2 even exhibiting the highest accuracy among the conditions. This
finding should be considered by future ERP-BCI proposals aimed
at users who need gaze-independent systems.
Description
Política de acceso abierto tomada de: https://authors.acm.org/author-resources/author-rights
Bibliographic citation
Álvaro Fernández-Rodríguez, Chloé Álvarez, Celia Langin, Francisco Velasco-Álvarez, Theodore Letouze, Jean-Marc Andre, and Ricardo Ron-Angevin. 2024. Exploring the impact of stimulus transparency in ERP-BCI under RSVP. In Proceedings of the 17th International Conference on PErvasive Technologies Related to Assistive Environments (PETRA '24). Association for Computing Machinery, New York, NY, USA, 9–14. https://doi.org/10.1145/3652037.3652045











