{"success":true,"database":"eegdash","data":{"_id":"69d16e05897a7725c66f4c9c","dataset_id":"nm000199","associated_paper_doi":null,"authors":["David Hübner","Thibault Verhoeven","Konstantin Schmid","Klaus-Robert Müller","Michael Tangermann","Pieter-Jan Kindermans"],"bids_version":"1.9.0","contact_info":null,"contributing_labs":null,"data_processed":false,"dataset_doi":null,"datatypes":["eeg"],"demographics":{"subjects_count":13,"ages":[26,26,26,26,26,26,26,26,26,26,26,26,26],"age_min":26,"age_max":26,"age_mean":26.0,"species":null,"sex_distribution":null,"handedness_distribution":null},"experimental_modalities":null,"external_links":{"source_url":"https://nemar.org/dataexplorer/detail/nm000199","osf_url":null,"github_url":null,"paper_url":null},"funding":["BrainLinks-BrainTools Cluster of Excellence funded by the German Research Foundation (DFG), grant number EXC 1086","bwHPC initiative, grant INST 39/963-1 FUGG","European Union's Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement No 657679","Special Research Fund from Ghent University","BK21 program funded by Korean National Research Foundation grant No. 2012-005741"],"ingestion_fingerprint":"a00aae7367171bcf779bba9155c2ef43458d910b8e1e1a9696f792bf02b6df02","license":"CC-BY-4.0","n_contributing_labs":null,"name":"Learning from label proportions for a visual matrix speller (ERP)","readme":"# Learning from label proportions for a visual matrix speller (ERP)\nLearning from label proportions for a visual matrix speller (ERP) dataset from Hübner et al 2017 [1]_.\n## Dataset Overview\n- **Code**: Huebner2017\n- **Paradigm**: p300\n- **DOI**: 10.1371/journal.pone.0175856\n- **Subjects**: 13\n- **Sessions per subject**: 3\n- **Events**: Target=10002, NonTarget=10001\n- **Trial interval**: [-0.2, 0.7] s\n- **Runs per session**: 9\n- **Session IDs**: session_1\n- **File format**: BrainVision\n## Acquisition\n- **Sampling rate**: 1000.0 Hz\n- **Number of channels**: 31\n- **Channel types**: eeg=31, misc=6\n- **Channel names**: C3, C4, CP1, CP2, CP5, CP6, Cz, EOGvu, F10, F3, F4, F7, F8, F9, FC1, FC2, FC5, FC6, Fp1, Fp2, Fz, O1, O2, P10, P3, P4, P7, P8, P9, Pz, T7, T8, x_EMGl, x_GSR, x_Optic, x_Pulse, x_Respi\n- **Montage**: standard_1020\n- **Hardware**: BrainAmp DC\n- **Reference**: nose\n- **Ground**: FCz\n- **Sensor type**: passive Ag/AgCl\n- **Line frequency**: 50.0 Hz\n- **Impedance threshold**: 20.0 kOhm\n- **Cap manufacturer**: EasyCap\n- **Auxiliary channels**: EOG (1 ch, vertical), pulse, respiration\n## Participants\n- **Number of subjects**: 13\n- **Health status**: healthy\n- **Age**: mean=26.0, std=1.5\n- **Gender distribution**: female=5, male=8\n- **BCI experience**: mostly naive\n- **Species**: human\n## Experimental Protocol\n- **Paradigm**: p300\n- **Number of classes**: 2\n- **Class labels**: Target, NonTarget\n- **Trial duration**: 25.0 s\n- **Study design**: Visual ERP speller copy-spelling task using a 6x7 grid with learning from label proportions (LLP) classifier. Two sequences with different target/non-target ratios: sequence 1 (3 targets/8 stimuli), sequence 2 (2 targets/18 stimuli). Unsupervised calibrationless approach.\n- **Feedback type**: visual\n- **Stimulus type**: character matrix\n- **Stimulus modalities**: visual\n- **Primary modality**: visual\n- **Synchronicity**: synchronous\n- **Mode**: online\n- **Training/test split**: False\n- **Instructions**: Copy-spelling task: subjects spelled the sentence 'FRANZY JAGT IM KOMPLETT VERWAHRLOSTEN TAXI QUER DURCH FREIBURG' three times\n- **Stimulus presentation**: soa_ms=250, stimulus_duration_ms=100, grid_size=6x7, highlighting_method=salient (brightness enhancement, rotation, enlargement, trichromatic grid overlay), viewing_distance_cm=80, screen_size_inches=24\n## HED Event Annotations\nSchema: HED 8.4.0 | Browse: https://www.hedtags.org/hed-schema-browser\n```\n  Target\n    ├─ Sensory-event\n    ├─ Experimental-stimulus\n    ├─ Visual-presentation\n    └─ Target\n  NonTarget\n    ├─ Sensory-event\n    ├─ Experimental-stimulus\n    ├─ Visual-presentation\n    └─ Non-target\n```\n## Paradigm-Specific Parameters\n- **Detected paradigm**: p300\n- **Number of targets**: 42\n- **Stimulus onset asynchrony**: 250.0 ms\n## Data Structure\n- **Trials**: 12852\n- **Trials context**: 68 highlighting events per character, 63 characters per sentence, 3 sentences = 68*63*3 = 12852 EEG epochs per subject. Each epoch is a Target (10002) or NonTarget (10001) event.\n## Preprocessing\n- **Data state**: raw\n- **Preprocessing applied**: False\n## Signal Processing\n- **Classifiers**: LLP (Learning from Label Proportions), shrinkage-LDA, EM-algorithm\n- **Feature extraction**: mean amplitude per time interval\n- **Frequency bands**: analyzed=[0.5, 8.0] Hz\n## Cross-Validation\n- **Method**: 5-fold chronological cross-validation\n- **Folds**: 5\n- **Evaluation type**: within_subject\n## Performance (Original Study)\n- **Accuracy**: 84.5%\n- **Auc**: 0.975\n- **Online Spelling Accuracy**: 84.5\n- **Post Hoc Spelling Accuracy**: 95.0\n- **Accuracy After Rampup**: 90.2\n- **Supervised Auc**: 0.975\n- **Max Spelling Speed Chars Per Min**: 2.4\n## BCI Application\n- **Applications**: speller, communication\n- **Environment**: laboratory\n- **Online feedback**: True\n## Tags\n- **Pathology**: Healthy\n- **Modality**: Visual\n- **Type**: Research\n## Documentation\n- **DOI**: 10.1371/journal.pone.0175856\n- **License**: CC-BY-4.0\n- **Investigators**: David Hübner, Thibault Verhoeven, Konstantin Schmid, Klaus-Robert Müller, Michael Tangermann, Pieter-Jan Kindermans\n- **Senior author**: Michael Tangermann\n- **Contact**: david.huebner@blbt.uni-freiburg.de; michael.tangermann@blbt.uni-freiburg.de; p.kindermans@tu-berlin.de\n- **Institution**: Albert-Ludwigs-University\n- **Department**: Brain State Decoding Lab, Cluster of Excellence BrainLinks-BrainTools, Department of Computer Science\n- **Address**: Freiburg, Germany\n- **Country**: DE\n- **Repository**: Zenodo\n- **Data URL**: http://doi.org/10.5281/zenodo.192684\n- **Publication year**: 2017\n- **Funding**: BrainLinks-BrainTools Cluster of Excellence funded by the German Research Foundation (DFG), grant number EXC 1086; bwHPC initiative, grant INST 39/963-1 FUGG; European Union's Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement No 657679; Special Research Fund from Ghent University; BK21 program funded by Korean National Research Foundation grant No. 2012-005741\n- **Ethics approval**: Ethics Committee of the University Medical Center Freiburg; Declaration of Helsinki\n- **Keywords**: brain-computer interface, BCI, event-related potentials, ERP, P300, learning from label proportions, LLP, unsupervised learning, calibrationless, visual speller\n## Abstract\nUsing traditional approaches, a brain-computer interface (BCI) requires the collection of calibration data for new subjects prior to online use. This work introduces learning from label proportions (LLP) to the BCI community as a new unsupervised, and easy-to-implement classification approach for ERP-based BCIs. The LLP estimates the mean target and non-target responses based on known proportions of these two classes in different groups of the data. We present a visual ERP speller to meet the requirements of LLP. For evaluation, we ran simulations on artificially created data sets and conducted an online BCI study with 13 subjects performing a copy-spelling task. Theoretical considerations show that LLP is guaranteed to minimize the loss function similar to a corresponding supervised classifier. LLP performed well in simulations and in the online application, where 84.5% of characters were spelled correctly on average without prior calibration.\n## Methodology\nThe experiment used a modified visual ERP speller with a 6×7 grid. Two distinct stimulus sequences with different target/non-target ratios were used: sequence 1 had 3 targets in 8 stimuli, sequence 2 had 2 targets in 18 stimuli. Each trial consisted of 4 sequences of length 8 and 2 sequences of length 18, totaling 68 highlighting events per character. The LLP algorithm exploited these known proportions to reconstruct mean target and non-target ERP responses without requiring labeled data. The classifier was reset at the start of each sentence and retrained after each character. Subjects spelled a German pangram sentence three times. One subject (S2) had prior EEG experience; others were naive. Sessions lasted about 3 hours including setup. Participants were compensated 8 Euros per hour.\n## References\nHübner, D., Verhoeven, T., Schmid, K., Müller, K. R., Tangermann, M., & Kindermans, P. J. (2017) Learning from label proportions in brain-computer interfaces: Online unsupervised learning with guarantees. PLOS ONE 12(4): e0175856. https://doi.org/10.1371/journal.pone.0175856\n.. versionadded:: 0.4.5\nAppelhoff, S., Sanderson, M., Brooks, T., Vliet, M., Quentin, R., Holdgraf, C., Chaumon, M., Mikulan, E., Tavabi, K., Hochenberger, R., Welke, D., Brunner, C., Rockhill, A., Larson, E., Gramfort, A. and Jas, M. (2019). MNE-BIDS: Organizing electrophysiological data into the BIDS format and facilitating their analysis. Journal of Open Source Software 4: (1896). https://doi.org/10.21105/joss.01896\nPernet, C. R., Appelhoff, S., Gorgolewski, K. J., Flandin, G., Phillips, C., Delorme, A., Oostenveld, R. (2019). EEG-BIDS, an extension to the brain imaging data structure for electroencephalography. Scientific Data, 6, 103. https://doi.org/10.1038/s41597-019-0104-8\n---\nGenerated by MOABB 1.5.0 (Mother of All BCI Benchmarks)\nhttps://github.com/NeuroTechX/moabb","recording_modality":["eeg"],"senior_author":null,"sessions":["0","1","2"],"size_bytes":5528187066,"source":"nemar","storage":{"backend":"nemar","base":"s3://nemar/nm000199","raw_key":"dataset_description.json","dep_keys":["README.md","participants.json","participants.tsv"]},"study_design":null,"study_domain":null,"tasks":["p300"],"timestamps":{"digested_at":"2026-04-30T14:08:59.678968+00:00","dataset_created_at":null,"dataset_modified_at":"2026-03-24T01:08:22Z"},"total_files":342,"computed_title":"Learning from label proportions for a visual matrix speller (ERP)","nchans_counts":[{"val":31,"count":342}],"sfreq_counts":[{"val":1000.0,"count":342}],"stats_computed_at":"2026-05-01T13:49:34.645596+00:00","total_duration_s":59076.717,"tagger_meta":{"config_hash":"3557b68bca409f28","metadata_hash":"2976b0b029bd7cda","model":"openai/gpt-5.2","tagged_at":"2026-04-07T09:32:40.872789+00:00"},"tags":{"pathology":["Healthy"],"modality":["Visual"],"type":["Attention"],"confidence":{"pathology":0.9,"modality":0.9,"type":0.75},"reasoning":{"few_shot_analysis":"Most similar few-shot convention is the Cross-modal Oddball Task example (Parkinson's; Multisensory; Clinical/Intervention), which shows that an oddball-like target vs non-target ERP paradigm is treated as an attention/ERP cognitive-control style task rather than motor (responses are incidental) and that modality follows the stimulus channel(s). The TBI auditory oddball example further reinforces mapping “oddball/target tones” paradigms to an ERP/target-detection construct with Auditory modality driven by the stimulus. This dataset is a P300 speller (a visual oddball-style ERP with Target vs NonTarget flashes), so we follow the same convention: stimulus channel = Visual; construct = attentional target detection (Attention) rather than motor.","metadata_analysis":"Key population and task facts explicitly stated in metadata:\n- Population: \"Health status: healthy\" and also an explicit tag \"Pathology\": \"Healthy\".\n- Paradigm/task: \"Paradigm: p300\" and \"Events: Target=10002, NonTarget=10001\".\n- Stimulus modality: \"Stimulus modalities: visual\" and \"Primary modality: visual\".\n- Task description: \"Visual ERP speller copy-spelling task using a 6x7 grid\" and \"Stimulus type: character matrix\" with \"highlighting_method=salient\".","paper_abstract_analysis":"The included abstract text in the README reinforces that this is an ERP-based BCI speller with unsupervised classification: \"an online BCI study with 13 subjects performing a copy-spelling task\" and \"We present a visual ERP speller\" and \"ERP-based BCIs\". This supports an attention/target-detection ERP interpretation (P300 speller) and confirms Visual stimulation.","evidence_alignment_check":"Pathology:\n- Metadata says: \"Health status: healthy\" (and tag \"Pathology\": \"Healthy\").\n- Few-shot pattern suggests: Use the recruited clinical group when explicitly stated; otherwise Healthy.\n- Alignment: ALIGN (explicitly healthy).\n\nModality:\n- Metadata says: \"Stimulus modalities: visual\" and \"Primary modality: visual\" and \"visual matrix speller\".\n- Few-shot pattern suggests: Modality follows stimulus channel (e.g., oddball cues -> auditory/visual/multisensory).\n- Alignment: ALIGN (clearly Visual stimuli).\n\nType:\n- Metadata says: \"Paradigm: p300\", \"Events: Target... NonTarget...\", and \"Visual ERP speller copy-spelling task\".\n- Few-shot pattern suggests: Target vs non-target ERP/oddball paradigms primarily index attentional selection/target detection (even if there are responses/feedback).\n- Alignment: ALIGN (P300 speller is an attended-target ERP paradigm).","decision_summary":"Top-2 comparative selection:\n\n1) Pathology\n- Candidate A: Healthy\n  Evidence: \"Health status: healthy\"; tag \"Pathology\": \"Healthy\"; participants described as \"Subjects: 13\" with no disorder mentioned.\n- Candidate B: Unknown\n  Evidence: Only plausible if no health info were given, but health is explicitly stated.\n- Decision: Healthy (metadata explicitly states healthy). Alignment: aligned.\n\n2) Modality\n- Candidate A: Visual\n  Evidence: \"Stimulus modalities: visual\"; \"Primary modality: visual\"; \"visual matrix speller\" / \"character matrix\".\n- Candidate B: Multisensory\n  Evidence: Not supported (no auditory/tactile stimuli described).\n- Decision: Visual. Alignment: aligned.\n\n3) Type\n- Candidate A: Attention\n  Evidence: \"Paradigm: p300\" with \"Target... NonTarget\" events implies attended-target detection; speller requires focusing attention on target character flashes; few-shot oddball convention maps target/non-target ERP paradigms to attention-related constructs.\n- Candidate B: Perception\n  Evidence: Could be argued as visual target detection/discrimination, but the canonical P300 effect is primarily attentional/oddball selection rather than sensory perception per se.\n- Decision: Attention (stronger match to P300 oddball/speller purpose). Alignment: aligned.\n\nConfidence justifications:\n- Pathology 0.9: supported by 2 explicit metadata statements (\"Health status: healthy\"; tag \"Pathology\": \"Healthy\") plus consistent absence of clinical recruitment.\n- Modality 0.9: supported by 3 explicit metadata statements (\"Stimulus modalities: visual\"; \"Primary modality: visual\"; \"visual matrix speller\"/\"character matrix\") and clear few-shot convention.\n- Type 0.75: supported by explicit \"Paradigm: p300\" and \"Target/NonTarget\" plus strong few-shot analog to oddball/ERP conventions, but the word \"attention\" is not directly stated."}},"canonical_name":null,"name_confidence":0.78,"name_meta":{"suggested_at":"2026-04-14T10:18:35.343Z","model":"openai/gpt-5.2 + openai/gpt-5.4-mini + deterministic_fallback"},"name_source":"canonical","author_year":"Hubner2017"}}