{"id":"W7106337766","doi":"10.1117/12.3091338","title":"Emotion recognition based on 3D-EEGU-Net and differential entropy features for small sample EEG and embedded applications","year":2025,"lang":"","type":"article","venue":"","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Petro-Canada","funders":"","keywords":"Sample entropy; Emotion recognition; Pattern recognition (psychology); Differential entropy; Electroencephalography; Entropy (arrow of time); Feature extraction; Emotion classification; Sample (material)","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":[0.0001495015,0.0005258183,0.0003085163,0.0004446662,0.0001222922,0.0003749689,0.0004360419,0.0002225451,0.00253313],"category_scores_gemma":[0.0004652195,0.0001584553,0.000349955,0.0003282812,0.0001150805,0.000496861,0.0004381243,0.000238987,0.0004688851],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001712141,"about_ca_system_score_gemma":0.0001458329,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001048406,"about_ca_topic_score_gemma":0.001983177,"domain_scores_codex":[0.9999201,0.00001107268,0.000005864505,0.00002405596,0.00002904341,0.000009859128],"domain_scores_gemma":[0.9999177,0.00002330273,0.0000112091,0.00001065867,0.0000295475,0.000007479682],"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":[0.0007241751,0.0001664521,0.004692892,0.000152179,0.00009159579,0.000373197,0.00008467252,0.04413263,0.1007207,0.001937197,0.006259254,0.840665],"study_design_scores_gemma":[0.0000217631,0.0001586836,0.006409294,0.00001165687,0.00002993623,0.0002440633,0.00004707303,0.9520123,0.03648038,0.001600651,0.002962835,0.00002137649],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08745129,0.0004956637,0.904999,0.0001672322,0.000140289,0.000105854,0.0005413793,0.003460553,0.002638765],"genre_scores_gemma":[0.7253295,0.0004612921,0.2679765,0.0001706724,0.00006273229,0.0002426515,0.00115335,0.0001133384,0.004489949],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00253313,"threshold_uncertainty_score":0.008474171,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02720358880108783,"score_gpt":0.3040386961713124,"score_spread":0.2768351073702246,"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."}}