{"success":true,"database":"eegdash","data":{"_id":"69de6d29897a7725c670234a","dataset_id":"nm000107","associated_paper_doi":null,"authors":["Patrick Kaifosh","Thomas R. Reardon","CTRL-labs at Reality Labs"],"bids_version":"1.11.0","canonical_name":null,"contact_info":null,"contributing_labs":null,"data_processed":false,"dataset_doi":"10.82901/nemar.nm000107","datatypes":["emg"],"demographics":{"subjects_count":100,"ages":[],"age_min":null,"age_max":null,"age_mean":null,"species":null,"sex_distribution":null,"handedness_distribution":null},"experimental_modalities":null,"external_links":{"source_url":"https://nemar.org/dataexplorer/detail/nm000107","osf_url":null,"github_url":null,"paper_url":null},"funding":["Meta Reality Labs"],"ingestion_fingerprint":"380f48b10436fe2be7e4bebb44047dcbc7a81c975cb7a9de4a66154f8d51641d","license":"CC-BY-NC 4.0","n_contributing_labs":null,"name":"FRL Wrist Control: Wrist Movement Decoding from Surface Electromyography","readme":"# wrist: Wrist Movement Control from EMG\n## Overview\n**Dataset**: wrist - Wrist posture and movement from wrist-based surface electromyography\n**Task**: 1D continuous cursor control via wrist flexion/extension\n**Participants**: 100 subjects\n**Sessions**: 100 total (1 per subject)\n**Publication**: Kaifosh et al., 2025 - \"A generic non-invasive neuromotor interface for human-computer interaction\" (Nature)\n### Purpose\nThis dataset captures wrist-based sEMG signals during wrist movements for continuous cursor control. Motion capture provides ground-truth wrist angles. The goal is to enable gesture-free control through wrist posture alone, demonstrating sEMG's ability to decode motor intent before visible movement occurs.\n## Dataset Details\n### Participants\n- **Sample size**: 100 participants\n- **Demographics**: Not available (marked as n/a)\n- **Recording side**: Dominant wrist\n- **Sessions**: 1 per participant\n### Hardware\n- **Device**: sEMG-RD (single wristband)\n- **Channels**: 16 (EMG0-EMG15)\n- **Sampling rate**: 2000 Hz\n- **Reference**: Bipolar differential\n- **Ground truth**: Motion capture wrist angles\n### Recording Protocol\n1. Participant wears sEMG-RD on dominant wrist\n2. Motion capture tracks wrist angles in real-time\n3. Participant controls horizontal cursor position with wrist flexion/extension\n4. Target acquisition task: Navigate to targets and hold for 500ms\n## Data Contents\n### Files per Session\n```\nsub-XXX/ses-XXX/emg/\n├── sub-XXX_ses-XXX_task-wrist_emg.edf\n├── sub-XXX_ses-XXX_task-wrist_emg.json\n├── sub-XXX_ses-XXX_task-wrist_channels.tsv\n├── sub-XXX_ses-XXX_task-wrist_events.tsv\n└── sub-XXX_ses-XXX_electrodes.tsv\n```\n### Events\n- **Stage boundaries**: Task phases and movement trials\n### Coordinate System\nSingle coordinate system at root (dominant wrist, percent units, no decimals)\n## Signal Processing\n**Note**: This dataset has significant data quality issues:\n- Duplicate timestamps found in many sessions (up to 88% duplicates)\n- Irregular sampling requiring resampling (up to 916% deviation)\n- Post-processing: Duplicate removal followed by resampling to regular 2000 Hz\n## Baseline Performance\n### Published Results (Kaifosh et al., 2025)\n**Offline Evaluation**:\n- Wrist angle velocity error: <13°/s\n- Error decreases with more training participants\n**Closed-loop Performance** (n=17 naive test users):\n- **Target acquisition time**: Median 1.51s (sEMG decoder)\n- **Dial-in time**: Time to re-acquire after premature exit\n- **Learning effects**: Improvement from practice to evaluation blocks\n**Comparison**:\n- Motion capture ground truth: 0.96s\n- MacBook trackpad: 0.68s\n- sEMG decoder: 1.51s (2.2× slower than trackpad)\n**Model architecture**: MPF features + LSTM\n## Key Findings\n- **Predictive signals**: sEMG precedes movement by tens of milliseconds\n- **Generic models work**: Out-of-the-box cross-user generalization\n- **Continuous control**: Demonstrates feasibility of gesture-free interfaces\n- **Room for improvement**: Performance gap vs traditional inputs\n## Use Cases\n- **Continuous control**: Cursor/pointer movement\n- **AR/VR navigation**: Hands-free interface\n- **Low-effort control**: Minimal visible movement required\n- **Predictive decoding**: Intent detection before motion completion\n## Known Limitations\n- Single degree of freedom (1D control only)\n- Single wrist (dominant hand)\n- Duplicate timestamps (data quality issue)\n- Performance below traditional inputs\n- Extension to 2D control not demonstrated\n## Citation\n```\nKaifosh, P., Reardon, T.R., & CTRL-labs at Reality Labs. (2025).\nA generic non-invasive neuromotor interface for human-computer interaction.\nNature, 645(8081), 702-711. https://doi.org/10.1038/s41586-025-09255-w\n```\n## Data Curator\n**Yahya Shirazi**\nSCCN (Swartz Center for Computational Neuroscience)\nINC (Institute for Neural Computation)\nUniversity of California San Diego\n## Version History\n**v1.0** (2025-10-01): Initial BIDS conversion\n---\n**BIDS Version**: 1.11 | **EMG-BIDS**: BEP-042 | **Updated**: Oct 1, 2025","recording_modality":["emg"],"senior_author":null,"sessions":["000","001"],"size_bytes":26685167982,"source":"nemar","storage":{"backend":"nemar","base":"s3://nemar/nm000107","raw_key":"dataset_description.json","dep_keys":["README.md","coordsystem.json","participants.json","participants.tsv","task-wrist_events.json"]},"study_design":null,"study_domain":null,"tasks":["wrist"],"timestamps":{"digested_at":"2026-04-30T14:08:25.833174+00:00","dataset_created_at":null,"dataset_modified_at":"2026-02-25T14:16:58Z"},"total_files":182,"author_year":"Kaifosh2025_107","name_source":"canonical","nchans_counts":[{"val":16,"count":182}],"computed_title":"FRL Wrist Control: Wrist Movement Decoding from Surface Electromyography","sfreq_counts":[{"val":2000.0,"count":182}],"stats_computed_at":"2026-05-01T13:49:34.660185+00:00","total_duration_s":277860.812}}