{"id":"W2103184652","doi":"10.1109/mci.2013.2247823","title":"Learning deep physiological models of affect","year":2013,"lang":"en","type":"article","venue":"IEEE Computational Intelligence Magazine","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":287,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Computer science; Artificial intelligence; Feature extraction; Feature selection; Machine learning; Affect (linguistics); Feature (linguistics); Task (project management); Artificial neural network; Selection (genetic algorithm); Process (computing); Pattern recognition (psychology); Engineering; 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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000128013,0.000120323,0.0001717836,0.0001032254,0.00005102321,0.00001511789,0.0001253089,0.00008646003,0.004763864],"category_scores_gemma":[0.00003818402,0.0001057805,0.00009102457,0.0001818008,0.0001126182,0.0001227811,0.00002052474,0.0001911525,0.004621364],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001523907,"about_ca_system_score_gemma":0.00001217744,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002064247,"about_ca_topic_score_gemma":0.000001742081,"domain_scores_codex":[0.9989511,0.0001480844,0.0003076271,0.0002416654,0.0001716055,0.0001799223],"domain_scores_gemma":[0.9991698,0.0002485534,0.0001269402,0.000092173,0.0002968282,0.00006570861],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003057937,0.0003397582,0.0001849178,0.0000233077,0.00006256456,0.000004264033,0.0009064691,0.8643788,0.00317347,0.02395009,0.00356679,0.103379],"study_design_scores_gemma":[0.0002879708,0.0007073542,0.03378071,0.00004795939,0.00002007521,0.00004041578,0.0005039987,0.7465033,0.001559928,0.2160951,0.0001499092,0.0003032805],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3370562,0.00007388519,0.6409802,0.0001369292,0.0004743504,0.0002456411,0.000003055233,0.00008511152,0.02094463],"genre_scores_gemma":[0.99422,0.00001059938,0.004039222,0.0002120487,0.0001019023,0.00004385396,0.00005327916,0.00001197132,0.001307102],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6571638,"threshold_uncertainty_score":0.9961537,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07589555127085217,"score_gpt":0.3399300142601346,"score_spread":0.2640344629892824,"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."}}