{"id":"W4295682146","doi":"10.32920/ryerson.14654265.v2","title":"Building Energy Surrogate Modelling – a Feature Selection Methodology","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Building Energy and Comfort Optimization","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Toronto Metropolitan University; Sciencetech (Canada)","funders":"","keywords":"Lasso (programming language); Feature selection; Selection (genetic algorithm); Computer science; Model building; Building model; Set (abstract data type); Surrogate model; Energy (signal processing); Feature (linguistics); Building energy simulation; Regression analysis; Data mining; Artificial intelligence; Machine learning; Statistics; Energy performance; Simulation; Mathematics","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":[0.001855441,0.0009503089,0.001021041,0.0006323158,0.0002665107,0.0008289188,0.0008512443,0.0007419547,0.00124371],"category_scores_gemma":[0.003946242,0.0003870809,0.001239814,0.0007944851,0.0003855086,0.0006477078,0.000676881,0.0009389744,0.0004382099],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002804681,"about_ca_system_score_gemma":0.0006665222,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00112973,"about_ca_topic_score_gemma":0.0007318858,"domain_scores_codex":[0.9992045,0.0003975119,0.00003739412,0.00009706126,0.0002179906,0.00004556508],"domain_scores_gemma":[0.9987556,0.0006944521,0.0001340179,0.0001585637,0.0002309459,0.00002636589],"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":[0.00008412617,0.00007182384,0.001212902,0.000076974,0.0001079558,0.00007837189,0.00003095301,0.9189357,0.004997255,0.009999758,0.001267812,0.06313651],"study_design_scores_gemma":[0.000004275801,0.00003149255,0.0001726111,0.00000454911,0.00000576089,0.00001391068,0.000002467743,0.9962385,0.0009191766,0.002097045,0.0005057629,0.000004500024],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01611447,0.0001018327,0.9824204,0.0001143437,0.00002200439,0.00003546944,0.0001448233,0.0003434547,0.0007031665],"genre_scores_gemma":[0.6548126,0.0004641636,0.339634,0.0001187993,0.00009165551,0.0004734073,0.001246844,0.0001663733,0.002992158],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.001855441,"threshold_uncertainty_score":0.009812653,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04212332844738793,"score_gpt":0.2604183708140977,"score_spread":0.2182950423667098,"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."}}