{"id":"W4392628999","doi":"10.26868/25222708.2023.1398","title":"Predicting energy consumption and thermal comfort in buildings using a hybrid machine learning and building performance simulation approach","year":2023,"lang":"en","type":"article","venue":"Building Simulation Conference proceedings","topic":"Building Energy and Comfort Optimization","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Boosting (machine learning); Gradient boosting; Computer science; Thermal comfort; Machine learning; Energy consumption; Predictive power; Artificial intelligence; Predictive modelling; Regression analysis; Support vector machine; Efficient energy use; Regression; Power consumption; Power (physics); Engineering; Random forest; Mathematics; Statistics","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005363559,0.00035439,0.0003312112,0.0006506372,0.0003835294,0.0002610381,0.0001230337,0.0001804543,0.00001172243],"category_scores_gemma":[0.0000941251,0.0004057956,0.00003502568,0.0006300868,0.00007974828,0.00106715,0.0001269967,0.0003711546,4.652903e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001124602,"about_ca_system_score_gemma":0.00002037186,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004930755,"about_ca_topic_score_gemma":0.000001953941,"domain_scores_codex":[0.9981726,0.00002237195,0.0005074296,0.0005166747,0.0002922333,0.0004887348],"domain_scores_gemma":[0.9993538,0.0001689578,0.0001658109,0.00008093888,0.000121266,0.0001092325],"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":[0.00002551191,0.000008694765,0.1590226,0.0002037058,0.00001762603,9.311906e-7,0.0003567998,0.8223276,0.008679212,0.001209936,0.000001095815,0.008146225],"study_design_scores_gemma":[0.0006366195,0.00003406834,0.006041411,0.0002778968,0.00002897768,0.00001558138,0.00007975363,0.9904824,0.001624472,0.0002057338,0.0001552413,0.0004177784],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8793232,0.0001840023,0.1192425,0.000008736957,0.00008912438,0.0002004503,0.000004048066,0.000811744,0.0001361788],"genre_scores_gemma":[0.9914209,0.000363454,0.00793726,0.00001582695,0.00008556042,0.00003467096,0.00004089063,0.00007743601,0.00002404122],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1681548,"threshold_uncertainty_score":0.9998394,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02560170673231937,"score_gpt":0.2503576957127219,"score_spread":0.2247559889804025,"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."}}