OpenBMI SSVEP EEG dataset (Lee et al. 2019)
…org/10.82901/nemar.nm000273) # OpenBMI SSVEP EEG dataset (Lee et al…
- Participants
- 54
- Citations
- 103
- Size
- 72.4 GB
- Version
- vv1.0.8
- Updated
- Oct 8, 2026
49 results for "OpenBMI" · page 1 of 5 · ranked by relevance
…org/10.82901/nemar.nm000273) # OpenBMI SSVEP EEG dataset (Lee et al…
…EEG dataset and OpenBMI toolbox for three BCI paradigms: an investigation into…
…EEG dataset and OpenBMI toolbox for three BCI paradigms: an investigation into…
This dataset is Study O of bigP3BCI, a large open collection of P300-based brain-computer interface EEG recordings. It contains 32-channel EEG from 18 participants with ALS, each recorded over two sessions while using a 9x8 character speller with a supervised checkerboard stimulus paradigm. Target and non-target flashes are annotated with HED tags, and the data are formatted for machine learning and benchmarking.
This dataset contains EEG recordings from 24 healthy participants in Study S2 of bigP3BCI, a large open P300-based brain-computer interface collection. Participants used a 9x8 character grid speller with a house/tool stimulus paradigm, with target and non-target events annotated using HED. Data were recorded at 256 Hz from 32 channels and are provided in a machine-learning-ready BIDS format via MOABB.
This dataset is Study R of bigP3BCI, a large open P300-based brain-computer interface collection. It contains 32-channel EEG recorded from 20 participants over two sessions each, using a 9x8 multi-face speller grid with target and non-target flashes. The data are standardized in BIDS and prepared for machine learning and benchmarking of P300 speller decoding.
Study P of the bigP3BCI collection, an open, machine-learning-ready P300-based brain-computer interface dataset. It contains 32-channel EEG recorded at 256 Hz from 19 participants with ALS, each over two sessions, while they used a 9x8 character grid speller with predictive and non-predictive spelling paradigms. Target and non-target flash events are annotated with HED tags, and the data are reformatted from the original PhysioNet release into BIDS.
This dataset contains EEG recordings from 36 participants with amyotrophic lateral sclerosis (Study Q of the bigP3BCI collection) performing a P300-based speller task with a 6x6 character grid and color intensification. Data were recorded across three sessions per subject with 32 EEG channels at 256 Hz. It is a BIDS-formatted derivative of the PhysioNet bigP3BCI release, intended for machine learning and benchmarking of P300 brain-computer interfaces.
This dataset contains P300-based brain-computer interface EEG recordings from 20 healthy participants in Study G of the bigP3BCI collection. Participants used a 9x8 character grid speller with checkerboard/dynamic stimulus presentation. Sixteen EEG channels were recorded at 256 Hz, with target and non-target events annotated using HED. The data are a MOABB-derived BIDS version of the original PhysioNet bigP3BCI resource.
Study J of the bigP3BCI collection, which provides EEG recordings from 20 healthy participants using a P300-based speller. The task used a 9x8 character grid with a performance-based row-column paradigm, and 16 EEG channels were recorded at 256 Hz. Target and non-target flash events are annotated with HED tags, and the dataset supports machine-learning benchmarking of P300 brain-computer interfaces.