{"dataset":{"id":"47103","dataset_id":"nm000177","name":"Multi-session longitudinal motor imagery EEG dataset (Kumar et al. 2024)","description":"This dataset comprises longitudinal motor imagery EEG recordings from 18 BCI-naive subjects across six sessions (one offline, five online), designed to study transfer learning and skill acquisition in brain-computer interfaces (BCIs). It compares two domain adaptation frameworks—Generic Recentering and Personally Assisted Recentering—for calibration-free BCI training using left/right hand motor imagery with visual feedback. Data were collected at 512 Hz with 22 EEG channels and analyzed using Riemannian geometry-based classifiers.","owner_user_id":19,"status":"active","github_repo":"nemarDatasets/nm000177","concept_doi":"10.82901/nemar.nm000177","latest_version_doi":"10.82901/nemar.nm000177.v1.0.4","created_at":"2026-06-19 17:29:07","updated_at":"2026-08-20 19:22:26","zenodo_concept_id":null,"is_sandbox":0,"visibility":"public","ezid_status":"public","enrichment_json":"{\n  \"version\": \"2.0\",\n  \"pipeline_stage\": \"enriched\",\n  \"title\": \"Multi-session longitudinal motor imagery EEG dataset (Kumar et al. 2024)\",\n  \"description\": \"This dataset comprises longitudinal motor imagery EEG recordings from 18 BCI-naive subjects across six sessions (one offline, five online), designed to study transfer learning and skill acquisition in brain-computer interfaces (BCIs). It compares two domain adaptation frameworks—Generic Recentering and Personally Assisted Recentering—for calibration-free BCI training using left/right hand motor imagery with visual feedback. Data were collected at 512 Hz with 22 EEG channels and analyzed using Riemannian geometry-based classifiers.\",\n  \"methods_description\": \"EEG data were recorded from 18 healthy subjects (mean age 23.22±3.59 years) across six sessions using ANT Neuro eego mylab hardware with 22 EEG channels and 3 EOG channels at 512 Hz. Subjects performed cue-based left/right hand motor imagery tasks with continuous visual feedback via bar-feedback runs and car racing games. Session 1 included 4 offline runs (80 trials); sessions 2-6 included 3-4 online runs each. Signals were bandpass filtered at 8-30 Hz using second-order Butterworth filters, and features were extracted as covariance matrices classified with a Riemannian Minimum Distance to Mean decoder.\",\n  \"license\": \"CC-BY-4.0\",\n  \"dataset_type\": \"derivative\",\n  \"authors\": {\n    \"Satyam Kumar\": {\n      \"orcid\": \"0000-0003-4817-1768\",\n      \"affiliations\": [\n        {\n          \"name\": \"Chandra Family Department of Electrical and Computer Engineering, The University of Texas at Austin , Austin, TX 78712 , USA\"\n        }\n      ]\n    },\n    \"Hussein Alawieh\": {\n      \"orcid\": \"0000-0002-2888-4958\",\n      \"affiliations\": [\n        {\n          \"name\": \"Chandra Family Department of Electrical and Computer Engineering, The University of Texas at Austin , Austin, TX 78712 , USA\"\n        }\n      ]\n    },\n    \"Frigyes Samuel Racz\": {\n      \"orcid\": \"0000-0001-9077-498X\",\n      \"affiliations\": [\n        {\n          \"name\": \"Department of Neurology, The University of Texas at Austin , Austin, TX 78712 , USA\"\n        },\n        {\n          \"name\": \"Mulva Clinic for the Neurosciences, The University of Texas at Austin , Austin, TX 78712 , USA\"\n        }\n      ]\n    },\n    \"Rawan Fakhreddine\": {\n      \"orcid\": \"0000-0002-6012-4019\",\n      \"affiliations\": [\n        {\n          \"name\": \"Chandra Family Department of Electrical and Computer Engineering, The University of Texas at Austin , Austin, TX 78712 , USA\"\n        }\n      ]\n    },\n    \"Jose del R. Millan\": {\n      \"orcid\": \"0000-0001-5819-1522\",\n      \"affiliations\": [\n        {\n          \"name\": \"Chandra Family Department of Electrical and Computer Engineering, The University of Texas at Austin , Austin, TX 78712 , USA\"\n        },\n        {\n          \"name\": \"Department of Neurology, The University of Texas at Austin , Austin, TX 78712 , USA\"\n        },\n        {\n          \"name\": \"Mulva Clinic for the Neurosciences, The University of Texas at Austin , Austin, TX 78712 , USA\"\n        },\n        {\n          \"name\": \"Departement of Biomedical Engineering, The University of Texas at Austin , Austin, TX 78712 , USA\"\n        }\n      ]\n    }\n  },\n  \"keywords\": [\n    {\n      \"term\": \"EEG\"\n    },\n    {\n      \"term\": \"motor imagery\"\n    },\n    {\n      \"term\": \"Brain-Computer Interfaces\",\n      \"subject_scheme\": \"MeSH\",\n      \"scheme_uri\": \"https://id.nlm.nih.gov/mesh/\",\n      \"value_uri\": \"http://id.nlm.nih.gov/mesh/D062207\"\n    },\n    {\n      \"term\": \"transfer learning\"\n    },\n    {\n      \"term\": \"domain adaptation\"\n    },\n    {\n      \"term\": \"Riemannian geometry\"\n    },\n    {\n      \"term\": \"longitudinal training\"\n    },\n    {\n      \"term\": \"BCI skill acquisition\"\n    }\n  ],\n  \"related_identifiers\": [\n    {\n      \"identifier\": \"10.1093/pnasnexus/pgae076\",\n      \"identifier_type\": \"DOI\",\n      \"relation_type\": \"IsDerivedFrom\"\n    },\n    {\n      \"identifier\": \"https://github.com/nemarDatasets/nm000177\",\n      \"identifier_type\": \"URL\",\n      \"relation_type\": \"IsDescribedBy\"\n    },\n    {\n      \"identifier\": \"10.5281/zenodo.10694880\",\n      \"identifier_type\": \"DOI\",\n      \"relation_type\": \"IsVersionOf\"\n    },\n    {\n      \"identifier\": \"https://nemar.org/dataset/nm000177\",\n      \"identifier_type\": \"URL\",\n      \"relation_type\": \"IsDescribedBy\"\n    }\n  ],\n  \"funding_references\": [\n    {\n      \"funder_name\": \"Coleman Fung Foundation\"\n    },\n    {\n      \"funder_name\": \"Sinclair Foundation\"\n    }\n  ],\n  \"resource_type_general\": \"Dataset\",\n  \"resource_type_specific\": \"EEG Dataset\",\n  \"modalities\": [\n    \"eeg\"\n  ],\n  \"sizes\": [\n    \"15.5 GB (1174 files)\"\n  ],\n  \"formats\": [\n    \".edf\",\n    \".gdf\",\n    \".json\",\n    \".md\",\n    \".tsv\",\n    \".txt\",\n    \".yaml\",\n    \".yml\"\n  ],\n  \"source_hash\": \"48446033110d430bcfc2f92c207fe446e327a011e05ddf4b277f91dfcde44c6b\"\n}","last_activity_at":"2026-08-16 14:10:27","source":null,"source_id":null,"subject_count":18,"modalities":"eeg","age_min":2020,"age_max":2020,"file_size":15492967507,"total_files":3976,"tasks":"imagery","metadata_columns_error":null,"staleness_warn_stage":null,"staleness_admin_notified_at":null,"authors":"Satyam Kumar, Hussein Alawieh, Frigyes Samuel Racz, Rawan Fakhreddine, Jose del R. Millan","license":"CC-BY-4.0","readme":"[![DOI](https://img.shields.io/badge/DOI-10.82901%2Fnemar.nm000177-blue)](https://doi.org/10.82901/nemar.nm000177)\n\n# Multi-session longitudinal motor imagery EEG dataset (Kumar et al. 2024)\n\n## Overview\n\nA longitudinal motor imagery EEG dataset from 18 BCI-naive subjects across 6 sessions (1 offline + 5 online) demonstrating transfer learning for brain-computer interface skill acquisition. The study compares two domain adaptation frameworks—Generic Recentering (unsupervised) and Personally Assisted Recentering (supervised)—for calibration-free BCI training using left/right hand motor imagery with visual feedback. Data were acquired at 512 Hz using 22 EEG channels and processed with Riemannian geometry-based classifiers.\n\n## Dataset Summary\n\n| Property | Value |\n|---|---|\n| Subjects | 18 |\n| Channels | 22 |\n| Classes | 2 |\n| Trial length | 5 s |\n| Sampling frequency | 512 Hz |\n| Sessions | 6 |\n| Total trials | 7156 |\n| Paradigm | MotorImagery |\n\n## Data Collection Methods\n\nEEG data were recorded from 18 healthy subjects (age mean=23.22±3.59 years) across 6 sessions using ANT Neuro eego mylab hardware with 22 EEG channels and 3 EOG channels at 512 Hz sampling rate. Subjects performed cue-based left/right hand motor imagery tasks with continuous visual feedback across bar-feedback runs and car racing games. Session 1 consisted of 4 offline runs (80 trials); sessions 2-6 included 3-4 online runs each. EEG signals were bandpass filtered at 8-30 Hz using second-order Butterworth filters. Features were extracted as covariance matrices and classified using Riemannian Minimum Distance to Mean decoder.\n\n## How to Access via MOABB\n\nInstall MOABB and load this dataset directly:\n\n```python\nfrom moabb.datasets import Kumar2024\nfrom moabb.paradigms import MotorImagery\nparadigm = MotorImagery()\n\ndataset = Kumar2024()\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.Kumar2024.html).\n\n## Citation\n\nIf you use this dataset please cite the primary publication:\n\n> DOI: [10.1093/pnasnexus/pgae076](https://doi.org/10.1093/pnasnexus/pgae076)\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":6,"publish_date":null,"embedding_dirty":0,"license_tier":"attribution","zarr_status":"failed","zarr_converted_at":null,"zarr_store_count":null,"zarr_index_etag":null,"zarr_source_commit":null,"archive_status":"ready","archive_size":10435325501,"archive_retry_count":0,"records_status":"ready","archive_skip_reason":null,"zarr_errors":360,"zarr_failure_count":360,"zarr_deterministic":1,"zarr_failed_at":"2026-08-22 07:48:00","num_dataset_citations":0,"num_datapaper_citations":49,"n_channels":22,"electrode_system":"10-10","has_hed":1,"hed_version":"8.4.0","is_exemplar":0,"bytes_present":15486841124,"data_complete":1,"withdrawn_at":null,"withdrawn_reason":null,"archive_complete":1,"archive_absent_files":0,"archive_declared_files":3976,"zarr_pool_breaks":null,"total_recording_duration":null,"recording_duration_min":null,"recording_duration_max":null,"recording_count":null,"recordings_unavailable":null,"recordings_measured":null,"channel_count_min":null,"channel_count_max":null,"sampling_frequency":512,"power_line_frequency":60,"eeg_reference":"CPz","placement_scheme":"10-20 system","sweep_stamps":"{\"enrichment_updated_at\":\"2026-08-20 19:21:44\",\"metadata_updated_at\":\"2026-08-20 19:22:25\",\"archive_checked_at\":\"2026-08-20 19:32:57\",\"zarr_checked_at\":null,\"records_checked_at\":\"2026-08-20 19:23:22\",\"citations_updated_at\":\"2026-09-08 03:00:47\",\"channel_montage_checked_at\":\"2026-06-28 22:55:28\",\"hed_checked_at\":\"2026-06-30 04:15:27\",\"data_checked_at\":null,\"availability_report_at\":\"2026-08-21 03:00:19\",\"recording_stats_at\":null,\"signal_defaults_at\":\"2026-09-02 11:41:39\"}","participants":18,"num_citations":49,"latest_version":"v1.0.4","zarr_verify_status":null,"zarr_verified_at":null,"owner_username":"bruaristimunha","owner_github":"bruAristimunha","file_size_formatted":"14.43 GB","zarr_data_failures":{"count":360,"detail_ref":"zarr/index.json","compacted_by":"migration_0074"},"zarr_index_url":null,"attestation_deposit_type":null,"attestation_key_status":null,"attestation_deidentified":null,"attestation_no_duplicate":null,"attestation_upstream_source":null,"attestation_accepted_at":null}}