{"schema_version":"0.3.0","doc_type":"dataset","dataset_id":"nm000199","name":"Learning from label proportions for a visual matrix speller (ERP)","description":"This dataset comprises event-related potential (ERP) recordings from 13 healthy subjects performing a visual matrix speller task using a calibrationless brain-computer interface approach. The study introduces learning from label proportions (LLP), an unsupervised classification method that exploits known target/non-target stimulus ratios to enable online BCI operation without prior calibration. Subjects performed copy-spelling tasks using a 6×7 character grid across three sessions, achieving 84.5% character accuracy without labeled training data.","source":"nemar","recording_modality":["EEG"],"bids_version":null,"license":"CC-BY-4.0","authors":[{"name":"David Hübner","name_type":"Personal","orcid":"0000-0003-4085-9154"},{"name":"Thibault Verhoeven","name_type":"Personal"},{"name":"Konstantin Schmid","name_type":"Personal"},{"name":"Klaus-Robert Müller","name_type":"Personal"},{"name":"Michael Tangermann","name_type":"Personal"},{"name":"Pieter-Jan Kindermans","name_type":"Personal"}],"keywords":[{"term":"Brain-Computer Interfaces","subject_scheme":"MeSH","scheme_uri":"https://id.nlm.nih.gov/mesh/","value_uri":"http://id.nlm.nih.gov/mesh/D062207"},{"term":"Event-Related Potentials, P300","subject_scheme":"MeSH","scheme_uri":"https://id.nlm.nih.gov/mesh/","value_uri":"http://id.nlm.nih.gov/mesh/D018913"},{"term":"P300"},{"term":"EEG"},{"term":"unsupervised learning"},{"term":"visual speller"},{"term":"learning from label proportions"}],"related_identifiers":[{"identifier":"10.1371/journal.pone.0175856","identifier_type":"DOI","relation_type":"IsDerivedFrom"},{"identifier":"10.5281/zenodo.192684","identifier_type":"DOI","relation_type":"References"},{"identifier":"https://github.com/nemarDatasets/nm000199","identifier_type":"URL","relation_type":"IsDescribedBy"},{"identifier":"10.21105/joss.01896","identifier_type":"DOI","relation_type":"References"},{"identifier":"https://nemar.org/dataset/nm000199","identifier_type":"URL","relation_type":"IsDescribedBy"}],"contributors":[],"dates":[],"rights":[{"rights":"CC-BY-4.0","rights_uri":null,"rights_identifier":"CC-BY-4.0","rights_identifier_scheme":"SPDX"}],"language":null,"funding":[{"funder_name":"Special Research Fund from Ghent University","award_number":null,"award_title":null,"funder_identifier":null,"funder_identifier_type":null,"award_uri":null},{"funder_name":"DFG","award_number":"EXC 1086","award_title":"BrainLinks-BrainTools Cluster of Excellence","funder_identifier":null,"funder_identifier_type":null,"award_uri":null},{"funder_name":"bwHPC","award_number":"INST 39/963-1 FUGG","award_title":null,"funder_identifier":null,"funder_identifier_type":null,"award_uri":null},{"funder_name":"European Union","award_number":"657679","award_title":"Marie Sklodowska-Curie grant (Horizon 2020)","funder_identifier":null,"funder_identifier_type":null,"award_uri":null},{"funder_name":"Ghent University","award_number":null,"award_title":"Special Research Fund","funder_identifier":null,"funder_identifier_type":null,"award_uri":null},{"funder_name":"Korean National Research Foundation","award_number":"2012-005741","award_title":"BK21 program","funder_identifier":null,"funder_identifier_type":null,"award_uri":null}],"tasks":["p300"],"datatypes":["eeg"],"sessions":["0","1","2"],"sessions_count":3,"demographics":{"subjects_count":13,"age_min":26,"age_max":26},"data_summary":{"total_files":2595,"size_bytes":5528956671,"size_human":"5.15 GB"},"provenance":{"latest_snapshot":"v1.0.2","publish_date":"2026-08-18 21:11:11"},"external_links":{"dataset_doi":"10.82901/nemar.nm000199","github_url":"https://github.com/nemarDatasets/nm000199"},"extensions":{"nemar":{"versions":[{"version":"v1.0.2","doi":"10.82901/nemar.nm000199.v1.0.2","created_at":"2026-08-18 21:11:11","manifest_url":"/nm000199/v1.0.2/manifest.json"},{"version":"v1.0.1","doi":"10.82901/nemar.nm000199.v1.0.1","created_at":"2026-08-12 16:10:52","manifest_url":"/nm000199/v1.0.1/manifest.json"},{"version":"v1.0.0","doi":"10.82901/nemar.nm000199.v1.0.0","created_at":"2026-06-02 01:43:50","manifest_url":"/nm000199/v1.0.0/manifest.json"}],"bids_index":{"version":"v1.0.2","subjects":{"sub-1":{"sessions":["0","1","2"],"modalities":{"eeg":{"tasks":{"p300":{"runs":["0","1","2","3","4","5","6","7","8"]}}}}},"sub-10":{"sessions":["0","1","2"],"modalities":{"eeg":{"tasks":{"p300":{"runs":["0","1","2","3","4","5","6","7","8"]}}}}},"sub-11":{"sessions":["0","1","2"],"modalities":{"eeg":{"tasks":{"p300":{"runs":["0","1","2","3","4","5","6","7","8"]}}}}},"sub-12":{"sessions":["0","1","2"],"modalities":{"eeg":{"tasks":{"p300":{"runs":["0","1","2","3","4","5","6","7","8"]}}}}},"sub-13":{"sessions":["0","1","2"],"modalities":{"eeg":{"tasks":{"p300":{"runs":["0","1","2","3","4","5","6","7","8"]}}}}},"sub-2":{"sessions":["0","1","2"],"modalities":{"eeg":{"tasks":{"p300":{"runs":["0","1","2","3","4","5","6","7","8"]}}}}},"sub-3":{"sessions":["0","1","2"],"modalities":{"eeg":{"tasks":{"p300":{"runs":["0","1","2","3","4","5","6","7","8"]}}}}},"sub-4":{"sessions":["0","1","2"],"modalities":{"eeg":{"tasks":{"p300":{"runs":["0","1","2","3","4","5","6","7","8"]}}}}},"sub-5":{"sessions":["0","1","2"],"modalities":{"eeg":{"tasks":{"p300":{"runs":["0","1","2","3","4","5","6","7","8"]}}}}},"sub-6":{"sessions":["0","2"],"modalities":{"eeg":{"tasks":{"p300":{"runs":["0","1","2","3","4","5","6","7","8"]}}}}},"sub-7":{"sessions":["0","1","2"],"modalities":{"eeg":{"tasks":{"p300":{"runs":["0","1","2","3","4","5","6","7","8"]}}}}},"sub-8":{"sessions":["0","1","2"],"modalities":{"eeg":{"tasks":{"p300":{"runs":["0","1","2","3","4","5","6","7","8"]}}}}},"sub-9":{"sessions":["0","1","2"],"modalities":{"eeg":{"tasks":{"p300":{"runs":["0","1","2","3","4","5","6","7","8"]}}}}}}},"pipeline_stage":"validated","data_complete":1,"bytes_present":5519920801}}}