FRL Handwriting: Handwriting Decoding from Surface Electromyography
NEMAR Dataset nm000106: handwriting - Handwriting movement detection from EMG
- Participants
- 100
- Size
- 45.3 GB
- Version
- vv2.0.0
- Updated
- Jul 10, 2026
23 results for "Actigraphy" · page 1 of 3 · ranked by relevance
NEMAR Dataset nm000106: handwriting - Handwriting movement detection from EMG
…However, as the full actigraphy file is included in this data set…
EEG recordings from 20 healthy participants who wrote ten letters (a, d, e, f, j, n, o, s, t, v) with the right index finger after a visual cue. The dataset supports classification of handwritten characters, either directly from low-frequency and broadband EEG or with a two-step approach that first decodes continuous hand kinematics and then classifies the letter. It is intended for research on non-invasive brain-computer interfaces for communication.
…electroencephalogram outperforms manual scoring and actigraphy', Mikkelsen et al 2018, https://doi…
EEG recordings from children performing letter discrimination and visual search tasks involving the mirror-image letters b and d, collected in an embodied learning for literacy study. Each participant completed a pre-intervention discrimination task, an intervention-phase visual search task, and a post-intervention discrimination task. Participants were assigned to an intervention or control group, and events mark stimulus presentation of b and d letters, including practice trials.
EEG recordings of motor imagery and motor execution for six activities (raising and lowering each hand, standing and sitting) from 30 healthy participants over two sessions. Data were acquired with a 14-channel Emotiv EPOC X headset at 128 Hz. This BIDS re-release, produced via MOABB, exposes a 3-class imagery task (left hand, right hand, trunk) for brain-computer interface research. The distributed imagery files carry no per-repetition activity label, so only folder-level 3-class labels are available.
EEG recordings of kinesthetic motor imagery of a right-hand ball squeeze at three graded force levels (10%, 40% and 70% of maximal voluntary contraction) from 10 healthy participants. Data were acquired with a 14-channel Emotiv EPOC headset at 128 Hz, with five 5-second imagery cues per 40-second recording. The dataset supports characterization and classification of motor imagery force levels for brain-computer interface research. The associated paper (Journal of Neural Engineering, 2024) is by Martinez-Peon, Garcia-Hernandez, Benavides-Bravo and Parra-Vega.
EEG recordings from 12 healthy participants operating a gaze-independent rapid serial visual presentation (RSVP) P300 speller. Thirty symbols were shown one at a time at the center of the screen under three conditions (NoColor 116 ms SOA, Color 116 ms SOA, Color 83 ms SOA), each with calibration, copy-spelling and free-spelling phases. Online spelling reached a mean accuracy of 94.8% at 1.43 symbols/min, supporting use by patients with impaired oculo-motor control.
A BIDS-formatted subset of Kai Miller's library of human electrocorticographic (ECoG) data, covering six calibrated tasks: finger flexion, hand gestures, motor imagery, basic motor movement, and speech (verb generation and noun reading). It contains 111 recordings from 24 epilepsy patients with subdural electrode grids, recorded at 1 kHz at Harborview Hospital. The data are scaled to physical units and include events, channel metadata and electrode positions.
Raw EEG recorded during a modified Sternberg verbal working memory task. Participants either simply retained letters or mentally manipulated them by alphabetization, at three memory loads of 5, 6, or 7 letters. Event markers label the baseline, encoding, delay, probe, and response periods for each task and load condition.