{"dataset":{"id":"49861","dataset_id":"nm000274","name":"BEETL Competition 2021 Motor Imagery Dataset B — transfer learning benchmark","description":"Beetl2021-B is a preprocessed EEG dataset from the NeurIPS 2021 BEETL competition, focused on transfer learning for motor imagery decoding. It contains 32-channel EEG recordings from 2 healthy subjects performing a 4-class motor imagery task (left hand, right hand, feet, rest) sampled at 200 Hz. The dataset is designed to benchmark transfer learning and domain adaptation algorithms addressing cross-subject and cross-dataset generalization challenges in brain-computer interfaces.","owner_user_id":19,"status":"active","github_repo":"nemarDatasets/nm000274","concept_doi":"10.82901/nemar.nm000274","latest_version_doi":"10.82901/nemar.nm000274.v1.0.5","created_at":"2026-06-20 19:52:12","updated_at":"2026-08-20 19:21:14","zenodo_concept_id":null,"is_sandbox":0,"visibility":"public","ezid_status":"public","enrichment_json":"{\n  \"version\": \"2.0\",\n  \"pipeline_stage\": \"validated\",\n  \"title\": \"BEETL Competition 2021 Motor Imagery Dataset B — transfer learning benchmark\",\n  \"description\": \"Beetl2021-B is a preprocessed EEG dataset from the NeurIPS 2021 BEETL competition, focused on transfer learning for motor imagery decoding. It contains 32-channel EEG recordings from 2 healthy subjects performing a 4-class motor imagery task (left hand, right hand, feet, rest) sampled at 200 Hz. The dataset is designed to benchmark transfer learning and domain adaptation algorithms addressing cross-subject and cross-dataset generalization challenges in brain-computer interfaces.\",\n  \"methods_description\": \"EEG data were acquired at 200 Hz using 32 channels positioned around the motor cortex (standard 1005 montage), with online bandpass filtering (1-100 Hz) during acquisition. Data were preprocessed with frequency-domain bandpass filtering (1-100 Hz) and segmented into 4-second trials. The motor imagery paradigm used visual cues for four classes: left hand, right hand, feet, and rest. Block-wise 5-fold cross-validation was employed for evaluation with cross-subject and cross-dataset assessment.\",\n  \"license\": \"CC-BY-4.0\",\n  \"dataset_type\": \"derivative\",\n  \"authors\": {\n    \"Xiaoxi Wei\": {},\n    \"A. Aldo Faisal\": {},\n    \"Moritz Grosse-Wentrup\": {},\n    \"Alexandre Gramfort\": {},\n    \"Sylvain Chevallier\": {},\n    \"Vinay Jayaram\": {},\n    \"Camille Jeunet\": {},\n    \"Stylianos Bakas\": {},\n    \"Siegfried Ludwig\": {},\n    \"Konstantinos Barmpas\": {},\n    \"Mehdi Bahri\": {},\n    \"Yannis Panagakis\": {},\n    \"Nikolaos Laskaris\": {},\n    \"Dimitrios A. Adamos\": {},\n    \"Stefanos Zafeiriou\": {},\n    \"William C. Duong\": {},\n    \"Stephen M. Gordon\": {},\n    \"Vernon J. Lawhern\": {},\n    \"Maciej Śliwowski\": {},\n    \"Vincent Rouanne\": {},\n    \"Piotr Tempczyk\": {}\n  },\n  \"keywords\": [\n    {\n      \"term\": \"EEG\"\n    },\n    {\n      \"term\": \"Brain-Computer Interfaces\",\n      \"subject_scheme\": \"MeSH\",\n      \"value_uri\": \"http://id.nlm.nih.gov/mesh/D062207\"\n    },\n    {\n      \"term\": \"motor imagery\"\n    },\n    {\n      \"term\": \"transfer learning\"\n    },\n    {\n      \"term\": \"domain adaptation\"\n    },\n    {\n      \"term\": \"Machine Learning\",\n      \"subject_scheme\": \"MeSH\",\n      \"value_uri\": \"http://id.nlm.nih.gov/mesh/D000069550\"\n    },\n    {\n      \"term\": \"cross-dataset generalization\"\n    }\n  ],\n  \"related_identifiers\": [\n    {\n      \"identifier\": \"10.48550/arXiv.2202.12950\",\n      \"identifier_type\": \"DOI\",\n      \"relation_type\": \"IsDescribedBy\"\n    },\n    {\n      \"identifier\": \"https://github.com/nemarDatasets/nm000274\",\n      \"identifier_type\": \"URL\",\n      \"relation_type\": \"IsDescribedBy\"\n    },\n    {\n      \"identifier\": \"https://nemar.org/dataset/nm000274\",\n      \"identifier_type\": \"URL\",\n      \"relation_type\": \"IsDescribedBy\"\n    }\n  ],\n  \"funding_references\": [\n    {\n      \"funder_name\": \"CEA NUMERICS program\"\n    },\n    {\n      \"funder_name\": \"Facebook Reality Labs\"\n    },\n    {\n      \"funder_name\": \"BCI Society\"\n    },\n    {\n      \"funder_name\": \"UKRI\",\n      \"award_number\": \"EP/V025449/1\",\n      \"award_title\": \"Turing AI Fellowship Grant\"\n    },\n    {\n      \"funder_name\": \"ANR\",\n      \"award_number\": \"ANR-20-CHIA-0016\",\n      \"award_title\": \"BrAIN AI chair\"\n    },\n    {\n      \"funder_name\": \"CEA\",\n      \"award_title\": \"NUMERICS program\"\n    },\n    {\n      \"funder_name\": \"European Union Horizon 2020\",\n      \"award_number\": \"800945\",\n      \"award_title\": \"Marie Sklodowska-Curie grant\"\n    }\n  ],\n  \"resource_type_general\": \"Dataset\",\n  \"resource_type_specific\": \"EEG Dataset\",\n  \"modalities\": [\n    \"eeg\"\n  ],\n  \"sizes\": [\n    \"2.1 GB (92 files)\"\n  ],\n  \"formats\": [\n    \".edf\",\n    \".json\",\n    \".md\",\n    \".npy\",\n    \".tsv\",\n    \".txt\",\n    \".yaml\",\n    \".yml\",\n    \".zip\"\n  ],\n  \"source_hash\": \"0a44e0a2e47178b80e1bf06c518ff9857af69f825be7c7b9cb46e162731233b3\"\n}","last_activity_at":"2026-08-16 13:38:15","source":null,"source_id":null,"subject_count":2,"modalities":"eeg","age_min":null,"age_max":null,"file_size":2135466246,"total_files":157,"tasks":"imagery","metadata_columns_error":null,"staleness_warn_stage":null,"staleness_admin_notified_at":null,"authors":"Xiaoxi Wei, A. Aldo Faisal, Moritz Grosse-Wentrup, Alexandre Gramfort, Sylvain Chevallier, Vinay Jayaram, Camille Jeunet, Stylianos Bakas, Siegfried Ludwig, Konstantinos Barmpas, Mehdi Bahri, Yannis Panagakis, Nikolaos Laskaris, Dimitrios A. Adamos, Stefanos Zafeiriou, William C. Duong, Stephen M. Gordon, Vernon J. Lawhern, Maciej Śliwowski, Vincent Rouanne, Piotr Tempczyk","license":"CC-BY-4.0","readme":"[![DOI](https://img.shields.io/badge/DOI-10.82901%2Fnemar.nm000274-blue)](https://doi.org/10.82901/nemar.nm000274)\n\n# BEETL Competition 2021 Motor Imagery Dataset B — transfer learning benchmark\n\n## Overview\n\nBeetl2021-B is a preprocessed EEG dataset from the NeurIPS 2021 BEETL competition focused on transfer learning for motor imagery decoding. The dataset contains 32-channel EEG recordings from 2 healthy subjects performing 4-class motor imagery tasks (left hand, right hand, feet, and rest) sampled at 200 Hz. Designed to address the critical challenge of cross-subject and cross-dataset generalization in brain-computer interfaces, this dataset supports benchmarking of transfer learning and domain adaptation algorithms for motor imagery classification.\n\n## Dataset Summary\n\n| Property | Value |\n|---|---|\n| Subjects | 2 |\n| Channels | 32 |\n| Classes | 4 |\n| Trial length | 4 s |\n| Sampling frequency | 200 Hz |\n| Sessions | 1 |\n| Total trials | 1590 |\n| Paradigm | MotorImagery |\n\n## Data Collection Methods\n\nEEG data acquired at 200 Hz sampling rate using 32 channels positioned around the motor cortex (standard 1005 montage). Online bandpass filtering (1-100 Hz) applied during acquisition. Data preprocessed with frequency-domain bandpass filtering (1-100 Hz) and organized into 4-second trials. Motor imagery paradigm with visual cues for four classes: left hand, right hand, feet, and rest. Block-wise 5-fold cross-validation employed for evaluation with cross-subject and cross-dataset assessment.\n\n## How to Access via MOABB\n\nInstall MOABB and load this dataset directly:\n\n```python\nfrom moabb.datasets import Beetl2021_B\nfrom moabb.paradigms import MotorImagery\nparadigm = MotorImagery()\n\ndataset = Beetl2021_B()\nX, y, metadata = paradigm.get_data(dataset)\n```\n\nFor more details see the [MOABB documentation](https://moabb.neurotechx.com/) and the\n[MOABB dataset page](https://moabb.neurotechx.com/docs/generated/moabb.datasets.Beetl2021_B.html).\n\n## Citation\n\nIf you use this dataset please cite the primary publication:\n\n> DOI: [10.48550/arXiv.2202.12950](https://doi.org/10.48550/arXiv.2202.12950)\n\n## NEMAR / MOABB Benchmark Collection\n\nThis BIDS-formatted dataset was converted from the original data using the\n[MOABB](https://moabb.neurotechx.com/) pipeline and re-hosted on\n[NEMAR](https://nemar.org/) as part of the MOABB benchmark collection.\nThe original data and license terms apply — see `dataset_description.json` for details.\n","bids_version":"1.9.0","sessions_count":1,"publish_date":null,"embedding_dirty":0,"license_tier":"attribution","zarr_status":"ready","zarr_converted_at":"2026-08-22 06:59:00","zarr_store_count":4,"zarr_index_etag":"6a62e4dc6dd4611da27a26dd5e08a81c","zarr_source_commit":"64feed5210ebea128a8484acd3027f9551ff2d7e","archive_status":"ready","archive_size":2066235007,"archive_retry_count":0,"records_status":"ready","archive_skip_reason":null,"zarr_errors":0,"zarr_failure_count":0,"zarr_deterministic":0,"zarr_failed_at":null,"num_dataset_citations":0,"num_datapaper_citations":2,"n_channels":32,"electrode_system":"10-10","has_hed":1,"hed_version":"8.4.0","is_exemplar":0,"bytes_present":2135376437,"data_complete":1,"withdrawn_at":null,"withdrawn_reason":null,"archive_complete":1,"archive_absent_files":0,"archive_declared_files":157,"zarr_pool_breaks":null,"total_recording_duration":2560,"recording_duration_min":480,"recording_duration_max":800,"recording_count":4,"recordings_unavailable":0,"recordings_measured":4,"channel_count_min":32,"channel_count_max":32,"sampling_frequency":200,"power_line_frequency":50,"eeg_reference":null,"placement_scheme":"10-05 system","sweep_stamps":"{\"enrichment_updated_at\":\"2026-08-20 19:20:27\",\"metadata_updated_at\":\"2026-08-20 19:21:12\",\"archive_checked_at\":\"2026-08-20 19:23:41\",\"zarr_checked_at\":null,\"records_checked_at\":\"2026-08-20 19:22:16\",\"citations_updated_at\":\"2026-09-08 03:00:51\",\"channel_montage_checked_at\":\"2026-06-28 23:02:55\",\"hed_checked_at\":\"2026-06-30 04:33:09\",\"data_checked_at\":null,\"availability_report_at\":\"2026-08-22 03:01:35\",\"recording_stats_at\":\"2026-09-02 11:32:08\",\"signal_defaults_at\":\"2026-09-02 11:50:58\"}","participants":2,"num_citations":2,"latest_version":"v1.0.5","zarr_verify_status":null,"zarr_verified_at":null,"owner_username":"bruaristimunha","owner_github":"bruAristimunha","file_size_formatted":"1.99 GB","zarr_data_failures":null,"zarr_index_url":"https://zarr.nemar.org/nm000274/zarr/index.json","attestation_deposit_type":null,"attestation_key_status":null,"attestation_deidentified":null,"attestation_no_duplicate":null,"attestation_upstream_source":null,"attestation_accepted_at":null}}