emg2qwerty: A Large Dataset with Baselines for Touch Typing using Surface Electromyography
NEMAR Dataset nm000104: emg2qwerty - EMG-based typing detection
- Participants
- 108
- Citations
- 1
- Size
- 223 GB
- Version
- vv2.0.0
- Updated
- Jul 10, 2026
100 results for "classifier" · page 3 of 10 · ranked by relevance
NEMAR Dataset nm000104: emg2qwerty - EMG-based typing detection
…91.0% - **Binary Classifier Accuracy Synth Pop**: 69.25 - **Binary Classifier Accuracy…
EEG dataset from twenty-one participants performing a continuous feedback learning task in which they predicted the final level of an animated rising bar. Cues (gnomes) differed in how predictable the outcome was (highly predictable, somewhat predictable, unpredictable), enabling study of feedback processing under varying outcome uncertainty. Points were awarded according to the accuracy of each guess.
…Real-time adaptive classifier used during experiment, performance variable per subject ## BCI…
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.
…LDA, linear binary classifier - **Feature extraction**: spatio-temporal features, r2 coefficient, interval…
A visual event-related potential dataset of 124-channel EEG recorded from 10 healthy participants viewing photographs from six object categories (human body, human face, animal body, animal face, fruit/vegetable, inanimate object). It contains 5,184 trials, with 72 images per category shown for 500 ms with a 750 ms interstimulus interval. The data support research on neural object representations through single-trial EEG classification and representational similarity analysis, and are distributed in BIDS format via MOABB.
…cross_session ## Performance (Original Study) - **Classifier**: real-time adaptive RMDM classifier (calibration…
EEG recordings from 10 healthy participants performing an online P300 row-column speller task with a 6x6 character matrix. The study compared two stimulus types, Famous Faces and Inverting, in combination with language models for online classification. Data were recorded from 32 channels at 256 Hz across two sessions per subject with three runs each, and are annotated with HED tags.
…The remaining trials are user-driven movements whose labels are fbCCA classifier…