{"id":"W4293863318","doi":"10.1109/siu55565.2022.9864700","title":"Unsupervised Adaptation of DNN for Brain-Computer Interface Spellers","year":2022,"lang":"en","type":"article","venue":"2022 30th Signal Processing and Communications Applications Conference (SIU)","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Stantec (Canada)","funders":"","keywords":"Computer science; Brain–computer interface; Adaptation (eye); Interface (matter); Artificial intelligence; Human–computer interaction; Speech recognition; Machine learning; Neuroscience; Electroencephalography; Psychology; Operating system","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008829454,0.001551829,0.0006543576,0.0006158556,0.0003492496,0.0004185464,0.001295209,0.0008478056,0.001565693],"category_scores_gemma":[0.002354926,0.000357736,0.0007609008,0.0007031075,0.000416018,0.0008131411,0.0006648587,0.001901547,0.001113151],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009176141,"about_ca_system_score_gemma":0.00137457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0189344,"about_ca_topic_score_gemma":0.02619746,"domain_scores_codex":[0.999443,0.0001156887,0.00003174041,0.0002026434,0.000129746,0.00007719405],"domain_scores_gemma":[0.9994221,0.0001701371,0.00003815746,0.00006832333,0.0002694222,0.00003203435],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003025138,0.000306104,0.00179775,0.0001895519,0.0001740071,0.0001970515,0.00009983987,0.3231744,0.02624566,0.001590628,0.01112652,0.6347959],"study_design_scores_gemma":[0.000006523633,0.00002818517,0.0006172077,0.000007729589,0.00001343149,0.00002045238,0.000009207556,0.9915063,0.006285446,0.0004757611,0.001019709,0.00001003025],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1398305,0.00329429,0.8392017,0.0004149962,0.0005668253,0.0002528349,0.001138643,0.008708828,0.006591283],"genre_scores_gemma":[0.7075571,0.001546028,0.2730173,0.0005108427,0.0001725142,0.000328795,0.005184169,0.0006044075,0.01107878],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0189344,"threshold_uncertainty_score":0.03764838,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06782995270244851,"score_gpt":0.3080195424644242,"score_spread":0.2401895897619757,"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."}}