{"id":"W2980817514","doi":"10.1088/1741-2552/ab4dba","title":"Subject-specific EEG channel selection using non-negative matrix factorization for lower-limb motor imagery recognition","year":2019,"lang":"en","type":"article","venue":"Journal of Neural Engineering","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Electroencephalography; Brain–computer interface; Overfitting; Motor imagery; Computer science; Pattern recognition (psychology); Artificial intelligence; False positive paradox; Channel (broadcasting); Speech recognition; Artificial neural network; Psychology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001384792,0.0001578408,0.0002152249,0.0002930911,0.00006167631,0.0001101063,0.0001334201,0.00006112632,0.00001394687],"category_scores_gemma":[0.0001725096,0.000143436,0.0001516504,0.0002501651,0.000009299537,0.0008087778,0.00002012096,0.0002476919,0.000007310633],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001124484,"about_ca_system_score_gemma":0.00002019145,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001462311,"about_ca_topic_score_gemma":1.161952e-7,"domain_scores_codex":[0.9989882,0.00002688875,0.0003621042,0.0001869653,0.0002084709,0.0002273755],"domain_scores_gemma":[0.9991034,0.0003196377,0.0002877715,0.00006440852,0.0001602207,0.0000645964],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001576753,0.00002294974,0.00001944852,0.00004584834,0.000007040624,0.000006154894,0.000106507,0.07012426,0.9289551,0.000002784717,0.00003775481,0.0005145223],"study_design_scores_gemma":[0.0003895939,0.0006475328,0.0003850796,0.0001011859,0.000008935264,0.0001718972,0.00002188655,0.4362325,0.5617687,0.00003434069,0.0001033778,0.0001349352],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.846624,0.00002324414,0.1503502,0.0000404805,0.002686894,0.0002260562,0.00001041926,0.00002880879,0.000009932243],"genre_scores_gemma":[0.9965658,0.00002135778,0.002724286,0.00003417425,0.0005598429,0.000002597006,0.000001058056,0.00003133717,0.00005953143],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3671864,"threshold_uncertainty_score":0.5849152,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03328612604941493,"score_gpt":0.2650823076848022,"score_spread":0.2317961816353872,"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."}}