TimeSeries BIDS converted
[, ICA-based EOG…
…channel, BioMag Laboratory, Helsinki; tSSS, ICA; source-reconstructed to the 400-parcel…
…Bandpower, Covariance/Riemannian, ICA - **Frequency bands**: alpha=[8.0, 13.0] Hz…
A multi-paradigm motor-imagery EEG dataset recorded from healthy participants with a 64-channel Neuroscan system at 1000 Hz. Five body-part tasks (hand, foot, thumb, index finger, index-thumb pinch) were performed under a Classic Arrow paradigm and a Cue-Execution dual-stage paradigm. This BIDS release is a five-subject public sample of a 244-participant dataset, intended for brain-computer interface research on fine motor imagery.
Preprocessed 64-channel EEG recordings from 8 healthy participants performing imagined speech of three vowel phonemes (a, i, u) in response to auditory and visual cues. The dataset was re-packaged in BIDS format from the MOABB collection and supports decoding of imagined speech with Riemannian manifold features and relevance vector machine classification.
EEG recordings from an online study with twelve healthy participants using a visual matrix speller (P300 ERP) for copy-spelling. The study compared three unsupervised decoders: expectation-maximization, learning from label proportions, and their mixture (MIX). Recordings were made with 31 EEG channels at 1000 Hz. The data support research on calibration-free brain-computer interfaces based on event-related potentials.