Demo: cVEP-based brain-computer interface
in
Workshop: Foundation Models for the Brain and Body Workshop
Abstract
We present a code-modulated visually evoked potential (cVEP) [1] brain–computer interface (BCI) speller that enables users to produce text solely through their brain activity. In this demo, participants wear an EEG cap that records their brain activity while attending stimuli presented as a virtual keyboard displayed on a screen. Each key on the keyboard flashes according to a distinct binary code sequence. By attending to a specific key, participants modulate their brain responses in a way that can be detected and decoded. This demo illustrates a joint development between a decoding algorithm and an experimental protocol, where the rCCA decoding algorithm [2] infers the intended letter from the noisy EEG signals. The demo has also focussed on usability (1) by implementing the demo on the modular, open-source platform Dareplane [3], which is characerized by high flexibility for the experimenter and (2) reducing the hardware complexity of the technical setup by selecting an easy-to-apply EEG cap and a compact amplifier system [ANT]. Beyond its demonstration value, such a system has profound implications for assistive communication technologies, offering a potential way for paralysed patients to realize a novel communication pathway that is independent of motor abilities.
[1] Víctor Martínez-Cagigal et al., Brain–computer interfaces based on code-modulated visual evoked potentials (c-VEP): a literature review. Journal of Neural Engineering (2021) [2] Thielen, J., Marsman, P., Farquhar, J., & Desain, P. (2021). From full calibration to zero training for a code-modulated visual evoked potentials for brain–computer interface. Journal of Neural Engineering, 18(5), 056007 [3] Dold, M., Pereira, J., Sajonz, B., Coenen, V. A., Thielen, J., Janssen, M. L. F., & Tangermann, M. (2025). Dareplane: A modular open-source software platform for BCI research with application in closed-loop deep brain stimulation. Journal of Neural Engineering, 22(2), 026029. https://doi.org/10.1088/1741-2552/adbb20