{"id":"W4316039214","doi":"10.3390/s23020915","title":"Comprehensive Analysis of Feature Extraction Methods for Emotion Recognition from Multichannel EEG Recordings","year":2023,"lang":"en","type":"article","venue":"Sensors","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":64,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"Ministry of Education, India; Nanyang Technological University; Ministry of Education - Singapore","keywords":"Electroencephalography; Pattern recognition (psychology); Support vector machine; Artificial intelligence; Feature extraction; Computer science; Random forest; Emotion classification; Speech recognition; Valence (chemistry); Decision tree; Arousal; Psychology","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":[0.002310056,0.0009230939,0.0006826073,0.002183982,0.0002402538,0.0006723304,0.0003997813,0.0004276787,0.0008896624],"category_scores_gemma":[0.004921665,0.0001575462,0.00097669,0.001406969,0.0001698544,0.0009437415,0.0003342986,0.0004174552,0.0004229685],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002605245,"about_ca_system_score_gemma":0.000367375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001039417,"about_ca_topic_score_gemma":0.001006842,"domain_scores_codex":[0.9989889,0.0001890723,0.0001085683,0.0002028051,0.0004644106,0.00004609004],"domain_scores_gemma":[0.9978351,0.001027053,0.0002175064,0.0001910077,0.0006986752,0.00003055954],"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":[0.0001654958,0.0001443684,0.005676033,0.0006677237,0.0003098386,0.00009586917,0.00009366203,0.007982728,0.05101066,0.0008897061,0.002038187,0.9309257],"study_design_scores_gemma":[0.0001086853,0.001512355,0.2515016,0.0006943601,0.0009132237,0.00194656,0.0003664451,0.516617,0.1848309,0.005742756,0.03547401,0.0002921285],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.150413,0.01941694,0.8234232,0.0006987414,0.0002566013,0.0003270268,0.001208543,0.001578213,0.002677721],"genre_scores_gemma":[0.5414243,0.01442672,0.4364326,0.0002108254,0.00026635,0.0006704721,0.003774597,0.0001992722,0.002594791],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002310056,"threshold_uncertainty_score":0.01221687,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09390747083917547,"score_gpt":0.3846114742050371,"score_spread":0.2907040033658617,"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."}}