{"dataset":{"id":"47566","dataset_id":"nm000233","name":"BCI Competition 2020 Track 4 — Upper-limb grasping motor imagery","description":"BCIComp2020UpperLimb is a preprocessed EEG dataset from BCI Competition 2020 Track 4 containing motor imagery recordings of three grasping tasks (cylindrical, spherical, lumbrical) from 15 healthy subjects across three sessions. The dataset comprises 60-channel EEG data sampled at 250 Hz with 450 trials per subject (150 trials per session across 3 sessions), designed to evaluate session-to-session transfer learning in brain-computer interface applications. Data were preprocessed with 60 Hz notch filtering and cue-aligned epoching, with the 4-second motor imagery window extracted for analysis.","owner_user_id":19,"status":"active","github_repo":"nemarDatasets/nm000233","concept_doi":"10.82901/nemar.nm000233","latest_version_doi":"10.82901/nemar.nm000233.v1.0.3","created_at":"2026-06-19 23:06:15","updated_at":"2026-08-18 18:15:12","zenodo_concept_id":null,"is_sandbox":0,"visibility":"public","ezid_status":"public","enrichment_json":"{\n  \"version\": \"2.0\",\n  \"pipeline_stage\": \"enriched\",\n  \"title\": \"BCI Competition 2020 Track 4 — Upper-limb grasping motor imagery\",\n  \"description\": \"BCIComp2020UpperLimb is a preprocessed EEG dataset from BCI Competition 2020 Track 4 containing motor imagery recordings of three grasping tasks (cylindrical, spherical, lumbrical) from 15 healthy subjects across three sessions. The dataset comprises 60-channel EEG data sampled at 250 Hz with 450 trials per subject (150 trials per session across 3 sessions), designed to evaluate session-to-session transfer learning in brain-computer interface applications. Data were preprocessed with 60 Hz notch filtering and cue-aligned epoching, with the 4-second motor imagery window extracted for analysis.\",\n  \"methods_description\": \"EEG data were acquired using a BrainAmp system (BrainProducts GmbH) with 60 channels at 250 Hz sampling rate, referenced to FCz with Fpz as ground. Subjects performed cue-based motor imagery of three right-arm grasping tasks in three sessions separated by 7 days. Each trial consisted of a 3 s rest period, 3 s visual cue, and 4 s motor imagery window. Data were preprocessed with 60 Hz notch filtering and cue-aligned epoching.\",\n  \"license\": \"CC-BY-4.0\",\n  \"dataset_type\": \"derivative\",\n  \"authors\": {\n    \"Ji-Hoon Jeong\": {},\n    \"Jeong-Hyun Cho\": {},\n    \"Young-Eun Lee\": {},\n    \"Seo-Hyun Lee\": {},\n    \"Gi-Hwan Shin\": {},\n    \"Young-Seok Kweon\": {},\n    \"Jose del R. Millan\": {},\n    \"Klaus-Robert Muller\": {},\n    \"Seong-Whan Lee\": {}\n  },\n  \"keywords\": [\n    {\n      \"term\": \"motor imagery\"\n    },\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\": \"upper-limb grasping\"\n    },\n    {\n      \"term\": \"grasping\"\n    },\n    {\n      \"term\": \"transfer learning\"\n    },\n    {\n      \"term\": \"session-to-session transfer\"\n    },\n    {\n      \"term\": \"BCI competition\"\n    },\n    {\n      \"term\": \"MOABB\"\n    },\n    {\n      \"term\": \"preprocessing\"\n    },\n    {\n      \"term\": \"cylindrical grasp\"\n    },\n    {\n      \"term\": \"spherical grasp\"\n    },\n    {\n      \"term\": \"lumbrical grasp\"\n    }\n  ],\n  \"related_identifiers\": [\n    {\n      \"identifier\": \"10.3389/fnhum.2022.898300\",\n      \"identifier_type\": \"DOI\",\n      \"relation_type\": \"IsDerivedFrom\"\n    },\n    {\n      \"identifier\": \"https://github.com/nemarDatasets/nm000233\",\n      \"identifier_type\": \"URL\",\n      \"relation_type\": \"IsDescribedBy\"\n    },\n    {\n      \"identifier\": \"https://nemar.org/dataset/nm000233\",\n      \"identifier_type\": \"URL\",\n      \"relation_type\": \"IsDescribedBy\"\n    }\n  ],\n  \"resource_type_general\": \"Dataset\",\n  \"resource_type_specific\": \"EEG Dataset\",\n  \"modalities\": [\n    \"eeg\"\n  ],\n  \"sizes\": [\n    \"3.0 GB (58 files)\"\n  ],\n  \"formats\": [\n    \".edf\",\n    \".json\",\n    \".md\",\n    \".tsv\",\n    \".yaml\",\n    \".yml\"\n  ],\n  \"source_hash\": \"fd8dc4c5bfe28ecec2503966f6fad1794c2bb12991b44747daf116d62cdf5767\"\n}","last_activity_at":"2026-08-16 13:35:06","source":null,"source_id":null,"subject_count":14,"modalities":"eeg","age_min":null,"age_max":null,"file_size":2967900122,"total_files":488,"tasks":"imagery","metadata_columns_error":null,"staleness_warn_stage":null,"staleness_admin_notified_at":null,"authors":"Ji-Hoon Jeong, Jeong-Hyun Cho, Young-Eun Lee, Seo-Hyun Lee, Gi-Hwan Shin, Young-Seok Kweon, Jose del R. Millan, Klaus-Robert Muller, Seong-Whan Lee","license":"CC-BY-4.0","readme":"[![DOI](https://img.shields.io/badge/DOI-10.82901%2Fnemar.nm000233-blue)](https://doi.org/10.82901/nemar.nm000233)\n\n# BCI Competition 2020 Track 4 — Upper-limb grasping motor imagery\n\n## Overview\n\nBCIComp2020UpperLimb is a preprocessed derivative EEG dataset from BCI Competition 2020 Track 4 comprising motor imagery recordings of three grasping tasks (cylindrical, spherical, lumbrical) from 15 healthy subjects across three sessions. The dataset contains 60-channel EEG data sampled at 250 Hz with 450 trials per subject (150 trials per session). This is a processed version of the original BCI Competition 2020 data, designed to evaluate session-to-session transfer learning in brain-computer interface applications. Original 10 s trials (3 s rest, 3 s visual cue, 4 s motor imagery) have been preprocessed with 60 Hz notch filtering and cue-aligned epoching, with the 4 s motor imagery window extracted for analysis.\n\n## Dataset Summary\n\n| Property | Value |\n|---|---|\n| Subjects | 15 |\n| Channels | 60 |\n| Classes | 3 |\n| Trial length | 4 s |\n| Sampling frequency | 250 Hz |\n| Sessions | 3 |\n| Total trials | 6750 |\n| Paradigm | MotorImagery |\n\n## Data Collection Methods\n\nEEG data were acquired using a BrainAmp system (BrainProducts GmbH) with 60 channels at 250 Hz sampling rate, referenced to FCz with Fpz as ground. Subjects performed cue-based motor imagery of three right-arm grasping tasks in three sessions separated by 7 days. Each trial consisted of a 3 s rest period, 3 s visual cue, and 4 s motor imagery window. Data were preprocessed with 60 Hz notch filtering and cue-aligned epoching. The 4 s motor imagery window (corresponding to seconds 6-10 of each original 10 s trial) was extracted by the loader for analysis.\n\n## How to Access via MOABB\n\nInstall MOABB and load this dataset directly:\n\n```python\nfrom moabb.datasets import BCIComp2020UpperLimb\nfrom moabb.paradigms import MotorImagery\nparadigm = MotorImagery()\n\ndataset = BCIComp2020UpperLimb()\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.BCIComp2020UpperLimb.html).\n\n## Citation\n\nIf you use this dataset please cite the primary publication:\n\n> DOI: [10.3389/fnhum.2022.898300](https://doi.org/10.3389/fnhum.2022.898300)\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":3,"publish_date":null,"embedding_dirty":0,"license_tier":"attribution","zarr_status":"ready","zarr_converted_at":"2026-08-22 07:40:50","zarr_store_count":42,"zarr_index_etag":"d02c4abb4c5da3e899abc2dd6303d4cd","zarr_source_commit":"6df995bb138f5cf8570fee1a69f7d62284ff5e9b","archive_status":"ready","archive_size":2755922354,"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":73,"n_channels":60,"electrode_system":"10-10","has_hed":1,"hed_version":"8.4.0","is_exemplar":0,"bytes_present":2967202769,"data_complete":1,"withdrawn_at":null,"withdrawn_reason":null,"archive_complete":1,"archive_absent_files":0,"archive_declared_files":488,"zarr_pool_breaks":null,"total_recording_duration":27720,"recording_duration_min":660,"recording_duration_max":660,"recording_count":42,"recordings_unavailable":0,"recordings_measured":42,"channel_count_min":60,"channel_count_max":60,"sampling_frequency":250,"power_line_frequency":60,"eeg_reference":"FCz","placement_scheme":"10-05 system","sweep_stamps":"{\"enrichment_updated_at\":\"2026-08-18 18:15:02\",\"metadata_updated_at\":\"2026-08-18 18:15:02\",\"archive_checked_at\":\"2026-08-18 18:24:42\",\"zarr_checked_at\":null,\"records_checked_at\":\"2026-08-18 18:23:09\",\"citations_updated_at\":\"2026-09-08 03:00:47\",\"channel_montage_checked_at\":\"2026-06-28 22:59:29\",\"hed_checked_at\":\"2026-06-30 04:29:35\",\"data_checked_at\":null,\"availability_report_at\":\"2026-08-21 03:01:27\",\"recording_stats_at\":\"2026-09-02 11:31:58\",\"signal_defaults_at\":\"2026-09-02 11:46:56\"}","participants":14,"num_citations":73,"latest_version":"v1.0.3","zarr_verify_status":null,"zarr_verified_at":null,"owner_username":"bruaristimunha","owner_github":"bruAristimunha","file_size_formatted":"2.76 GB","zarr_data_failures":null,"zarr_index_url":"https://zarr.nemar.org/nm000233/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}}