{"id":"W4390063329","doi":"10.1016/j.buildenv.2023.111129","title":"Bayesian meta-learning for personalized thermal comfort modeling","year":2023,"lang":"en","type":"article","venue":"Building and Environment","topic":"Building Energy and Comfort Optimization","field":"Engineering","cited_by":17,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Thermal comfort; Artificial neural network; ASHRAE 90.1; Computer science; Machine learning; Artificial intelligence; Bayesian network; Latent variable; Dynamic Bayesian network; Bayesian probability; Data mining; Meteorology; Geography","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":[0.002792245,0.001252917,0.002824795,0.001168996,0.0005501122,0.001427368,0.002491868,0.002502143,0.00366153],"category_scores_gemma":[0.00660762,0.001643682,0.002010563,0.001326434,0.0009152667,0.00203511,0.001404408,0.002803933,0.0007864682],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001539882,"about_ca_system_score_gemma":0.001274352,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01134204,"about_ca_topic_score_gemma":0.01321631,"domain_scores_codex":[0.9989082,0.0005446924,0.0000433068,0.0002128069,0.0001767296,0.0001142631],"domain_scores_gemma":[0.9971524,0.002240536,0.0001494139,0.0001538231,0.0002224342,0.00008135136],"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":[0.00002853694,0.00002821836,0.0001479591,0.00001927039,0.00004311942,0.000009771013,0.0000142071,0.986576,0.0001004513,0.003818124,0.0004122113,0.008802094],"study_design_scores_gemma":[0.000002969408,0.000004817647,0.00002533503,0.000003486344,0.000005295501,0.000001801588,0.000001219448,0.9969749,0.00003676427,0.002853481,0.00008775411,0.000002144908],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01153072,0.0005883379,0.9853913,0.0003185152,0.00004337426,0.00002772804,0.0001889652,0.0003561776,0.001554884],"genre_scores_gemma":[0.7926512,0.0007227022,0.1964076,0.0005203179,0.0001906348,0.0003697625,0.0008065586,0.0002829617,0.00804818],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01134204,"threshold_uncertainty_score":0.02255207,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02367627497028466,"score_gpt":0.2092435491371666,"score_spread":0.185567274166882,"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."}}