{"id":"W4290705532","doi":"10.3390/bioengineering9080374","title":"Contrastive Self-Supervised Learning for Stress Detection from ECG Data","year":2022,"lang":"en","type":"article","venue":"Bioengineering","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Artificial intelligence; Leverage (statistics); Machine learning; Stress test; Stress (linguistics); Pattern recognition (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":[0.003285396,0.00114917,0.001330248,0.001187097,0.0003350776,0.0007017637,0.001824159,0.001323585,0.0009995021],"category_scores_gemma":[0.006358926,0.0003767589,0.001128664,0.000838275,0.0006824944,0.0009580462,0.001039503,0.001596974,0.0008971175],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005917568,"about_ca_system_score_gemma":0.0006525553,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001795636,"about_ca_topic_score_gemma":0.002924548,"domain_scores_codex":[0.9981791,0.0006150883,0.0001238319,0.0006610811,0.0003099286,0.000110929],"domain_scores_gemma":[0.9962361,0.002052585,0.0004056365,0.0004552251,0.0007380891,0.0001122825],"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":[0.0005993425,0.001148188,0.01165501,0.0003950705,0.0003279142,0.0002335865,0.0002638029,0.1598458,0.01643505,0.002292754,0.008415937,0.7983876],"study_design_scores_gemma":[0.00001666473,0.000141699,0.00231449,0.00001934976,0.00002377309,0.00006812954,0.0000198283,0.9907507,0.003277309,0.002479564,0.0008722867,0.00001614702],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05464188,0.00161427,0.9384081,0.0004280233,0.0001567998,0.0001977114,0.0003968709,0.002684781,0.001471481],"genre_scores_gemma":[0.7565531,0.0006454249,0.2358997,0.0006776431,0.000402805,0.0003927234,0.001926844,0.0002226447,0.003279249],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003285396,"threshold_uncertainty_score":0.01737505,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04143503529972602,"score_gpt":0.2819643327142773,"score_spread":0.2405292974145513,"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."}}