{"id":"W4302299739","doi":"10.1007/s00521-022-07861-7","title":"Motor imagery classification using sparse nonnegative matrix factorization and convolutional neural networks","year":2022,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":14,"is_retracted":false,"has_abstract":false,"ca_institutions":"Brandon University","funders":"","keywords":"Computer science; Motor imagery; Artificial intelligence; Pattern recognition (psychology); Non-negative matrix factorization; Brain–computer interface; Convolutional neural network; Electroencephalography; Matrix decomposition; Feature extraction; SIGNAL (programming language); Feature vector; Feature (linguistics); Speech recognition","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001175937,0.0001440646,0.0001303015,0.0000852345,0.00126576,0.0001379789,0.0001592086,0.00003259466,0.00001086634],"category_scores_gemma":[0.00003017067,0.0001493878,0.00003354771,0.0003127075,0.0001497755,0.0001512112,0.0002486609,0.000280905,0.000001146457],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004602734,"about_ca_system_score_gemma":0.00001668431,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001578814,"about_ca_topic_score_gemma":5.181906e-7,"domain_scores_codex":[0.9987116,0.0001658479,0.0002424754,0.0004832481,0.0001820071,0.0002148604],"domain_scores_gemma":[0.9991599,0.0003954834,0.0001780662,0.0001473938,0.00004143513,0.00007770006],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007987214,0.0002775663,0.01094737,0.00005894322,0.00001864206,0.000007271305,0.001104964,0.2959385,0.6296828,0.02098384,0.0004993393,0.04040091],"study_design_scores_gemma":[0.0001894863,0.0000505972,0.006792483,0.000004342921,0.00001052162,0.00009181903,0.0001392621,0.990625,0.0009567284,0.0002893873,0.0006984491,0.0001518802],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8475469,0.0001178459,0.1510642,0.0004277953,0.0001919786,0.0004036081,0.0000461737,0.0001443035,0.00005720556],"genre_scores_gemma":[0.9983819,0.000007461808,0.0007805957,0.0004275398,0.0002526548,0.00004355741,0.00002495251,0.00001511182,0.00006626753],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6946866,"threshold_uncertainty_score":0.9735333,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05163060591790608,"score_gpt":0.306669372578011,"score_spread":0.2550387666601049,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}