{"id":"W3005055041","doi":"10.1109/taffc.2020.3014842","title":"Self-Supervised ECG Representation Learning for Emotion Recognition","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Affective Computing","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":368,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology); Transfer of learning; Convolutional neural network; Emotion classification; Multi-task learning; Supervised learning; Machine learning; Transformation (genetics); Feature learning; Task (project management); Deep learning; Artificial neural network; Speech recognition; Engineering","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":[0.0008612752,0.0009262798,0.0007123275,0.0004589455,0.0001804799,0.0006097063,0.00142379,0.0009380557,0.002121673],"category_scores_gemma":[0.001944617,0.000280235,0.0008953256,0.0004186157,0.000301438,0.0008530834,0.0008919618,0.001267819,0.001264737],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004084839,"about_ca_system_score_gemma":0.0003774229,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009604595,"about_ca_topic_score_gemma":0.001597182,"domain_scores_codex":[0.9994233,0.000140934,0.00003080159,0.0002197344,0.0001194174,0.00006582514],"domain_scores_gemma":[0.9993081,0.0001947205,0.00008667991,0.0001712245,0.0001990943,0.000040115],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004630285,0.0007945281,0.003643623,0.0001556603,0.0002228104,0.0001813951,0.0001250932,0.1383642,0.04947921,0.003417697,0.01509055,0.7880622],"study_design_scores_gemma":[0.00001362778,0.00007040099,0.0009644254,0.000005496029,0.00001674648,0.00005015192,0.000009930331,0.9854845,0.009873696,0.002432129,0.001068767,0.00001009632],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02751713,0.0002774336,0.9672629,0.0002949654,0.0001136343,0.0000856088,0.0002951368,0.002606863,0.001546215],"genre_scores_gemma":[0.6144721,0.0003332971,0.3735355,0.000586748,0.0002879302,0.0002527004,0.00256185,0.0003000337,0.007669789],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002121673,"threshold_uncertainty_score":0.007097721,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06766507257346926,"score_gpt":0.3295969809081446,"score_spread":0.2619319083346753,"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."}}