BEETL Competition 2021 Motor Imagery Dataset B — transfer learning benchmark
…dataset generalization in brain-computer interfaces, this dataset supports benchmarking of transfer…
- Participants
- 2
- Size
- 1.99 GB
- Version
- vv1.0.5
- Updated
- Sep 29, 2026
35 results for "brain-computer interfaces" · page 3 of 4 · ranked by relevance
…dataset generalization in brain-computer interfaces, this dataset supports benchmarking of transfer…
EEG recordings from five participants with speech and/or physical impairments due to amyotrophic lateral sclerosis (ALS) who used a non-implantable communication brain-computer interface (cBCI) over multiple visits. Participants completed calibration and copy-spelling tasks with Matrix and RSVP layouts, in both customized and non-customized system configurations. Customization was iteratively adjusted based on typing performance, preferences, clinical observations, brain signal characteristics, and offline simulations. The data are organized in BIDS format.
[ paradigm with target (1000 Hz) and non-target (500 Hz) tones presented at varying stimulus onset asynchronies (60-600 ms). The data were collected to evaluate closed-loop Bayesian optimization and random search for selecting individually optimal stimulation speed in an auditory brain-computer interface. The dataset contains 31-channel EEG sampled at 1000 Hz, covering both an optimization part and a validation part.
This dataset contains 62-channel EEG recordings from 39 healthy, BCI-naive participants in a longitudinal motor imagery brain-computer interface study of sensory-guided human-machine joint learning. Participants performed online 1D and 2D cursor control with left-hand, right-hand, bilateral-hand and rest imagery across multiple sessions. The cohorts were joint learning with tactile guidance and EEGNet adaptation, a fixed BCI2000 decoder control, a tactile-only control, and an EEGNet control. The data are trial-segmented and were reorganized in BIDS format via MOABB.
EEG recordings from 19 healthy participants using a music-based brain-computer interface that lets users dynamically modulate music tempo through intentional control. Participants kinaesthetically imagined squeezing a ball with the right hand to increase tempo, or relaxed to decrease it. The paradigm comprised 9 runs, beginning with a calibration run of 30 trials in pairs of increase and decrease tempo trials.
[![DOI](https://img.shields.io/badge/DOI-10.82901%2Fnemar.on004973-blue…
Study D of the bigP3BCI collection, comprising 32-channel EEG recordings from 17 healthy participants using a P300-based speller with a 6x6 character grid and dynamic row-column stimulus presentation. Data were recorded in a single session per subject with online feedback, and events are labeled as target or non-target flashes. The dataset is a BIDS-formatted derivative of the PhysioNet bigP3BCI release, intended for machine learning and BCI benchmarking.
[![DOI](https://img.shields.io/badge/DOI-10.82901%2Fnemar.nm000340-blue…