{"id":"W3085438608","doi":"10.1016/j.enbuild.2021.110836","title":"Identifying grey-box thermal models with Bayesian neural networks","year":2021,"lang":"en","type":"preprint","venue":"Energy and Buildings","topic":"Building Energy and Comfort Optimization","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Thermostat; Computer science; Thermal comfort; Bayesian probability; Black box; Artificial neural network; Bayesian inference; Building automation; Building energy simulation; Data mining; Machine learning; Energy (signal processing); Artificial intelligence; Engineering; Statistics; Meteorology; Mathematics; Mechanical engineering; Geography; Energy performance","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001961746,0.001063932,0.001820612,0.0009018935,0.0003835486,0.001266235,0.001434042,0.002340012,0.003030285],"category_scores_gemma":[0.00908964,0.001795247,0.0009893586,0.000924423,0.001325099,0.002094901,0.001361691,0.001768785,0.0004878031],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001173678,"about_ca_system_score_gemma":0.0009431964,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01146278,"about_ca_topic_score_gemma":0.01072176,"domain_scores_codex":[0.9992933,0.0003526022,0.00002629584,0.0001506578,0.0001008277,0.00007623566],"domain_scores_gemma":[0.9959415,0.003366982,0.0002851403,0.0001161558,0.0002170284,0.0000731685],"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":[0.000018249,0.000008054761,0.0001356324,0.00001091583,0.00001220935,0.000005381016,0.000006739677,0.994795,0.00008019828,0.002439857,0.0000869264,0.002400844],"study_design_scores_gemma":[0.000001495214,0.000001339402,0.00002655697,0.00000197116,0.000001229814,7.838469e-7,7.173712e-7,0.9971406,0.00002712253,0.002774182,0.00002254327,0.000001481449],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03536747,0.0003325207,0.9615862,0.0002555007,0.00002793543,0.00002710251,0.0001381605,0.0002408177,0.002024316],"genre_scores_gemma":[0.911615,0.0004183406,0.07988266,0.0001365247,0.000079914,0.0001774713,0.0004535775,0.0001459198,0.007090556],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01146278,"threshold_uncertainty_score":0.0227921,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009129687801699074,"score_gpt":0.1885240356154654,"score_spread":0.1793943478137663,"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."}}