Learning from label proportions for a visual matrix speller (ERP)
…calibrationless, visual speller ## Abstract Using traditional approaches, a brain-computer interface (BCI…
- Participants
- 13
- Size
- 9.43 GB
- Version
- vv1.0.4
- Updated
- Oct 16, 2026
18 results for "calibrationless BCI" · page 1 of 2 · ranked by relevance
…calibrationless, visual speller ## Abstract Using traditional approaches, a brain-computer interface (BCI…
EEG recordings from 12 healthy participants performing an offline 4-class reactive BCI task based on code-modulated visual evoked potentials (c-VEP). The dataset covers the 'Burst c-VEP' condition at 40% amplitude depth, in which short bursts of aperiodic flashes are presented at 2-4 flashes per second. It supports work on stimulus design, visual comfort, and CNN-based bitwise decoding with minimal calibration data.
EEG recordings from 24 healthy participants performing a visual P300 Brain-Computer Interface task based on the Brain Invaders video game. The experiment compared a P300 BCI with and without adaptive calibration using Riemannian geometry. Data were recorded with 16 wet electrodes at GIPSA-lab, Grenoble, in 2013, across 8 sessions per subject with randomised adaptive and non-adaptive runs.
EEG recordings from 12 healthy participants performing an offline 4-class code-modulated visual evoked potential (c-VEP) task with burst stimulation sequences at 100% amplitude depth. The dataset accompanies a study comparing burst c-VEP codes with m-sequences to improve classification accuracy, reduce calibration data and improve user experience in reactive brain-computer interfaces. Data were acquired with a 32-channel BrainProducts LiveAmp system at 500 Hz.
This dataset contains simultaneous EEG and eye-tracking recordings from 21 healthy participants performing a matrix-based single-character-presentation BCI spelling task. Calibration and copy-spelling sessions include event markers for target and non-target stimuli. It supports research on multimodal sensor fusion for EEG-based brain-computer interface typing systems.
EEG dataset of a 4-class code-modulated visual evoked potential (c-VEP) reactive brain-computer interface study with 12 healthy participants. This subset contains the m-sequence c-VEP condition at 100% amplitude depth, recorded with a 32-channel BrainProducts LiveAmp system at 500 Hz. The study compared burst and m-sequence codes at two amplitude depths, assessing classification accuracy with minimal calibration data and user experience.
EEG recordings from 12 healthy participants performing an offline 4-class code-modulated visual evoked potential (c-VEP) reactive BCI task. This subset contains the m-sequence condition at 40% amplitude depth, from a factorial study that compared burst and m-sequence codes at 100% and 40% modulation depth. The dataset supports evaluation of CNN-based decoding with minimal calibration data and of the visual comfort of reduced-intensity stimuli.
…10.82901/nemar.nm000290) # PROTEUS BCI Bordeaux — EEG/EMG Foundation Challenge 2026…
…SSVEP, BCI, spatial navigation, single-flicker, online BCI ## References J. Chen, D…
…Longitudinal motor-imagery BCI training for the Cybathlon 2016 BCI race; two…