{"id":"W4368367694","doi":"10.1007/s12273-023-1005-5","title":"Unsupervised learning of load signatures to estimate energy-related building features using surrogate modelling techniques","year":2023,"lang":"en","type":"article","venue":"Building Simulation","topic":"Building Energy and Comfort Optimization","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"National Research Council Canada; Carleton University","funders":"","keywords":"Footprint; Energy (signal processing); Cooling load; Scalability; Computer science; Archetype; Set (abstract data type); Data mining; Building envelope; Reliability engineering; Engineering; Artificial intelligence; Machine learning; Air conditioning; Mechanical engineering; 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":[0.000379819,0.0002696576,0.0002887578,0.0005470704,0.0002087391,0.00006415982,0.0001808719,0.0002621557,0.000009988502],"category_scores_gemma":[0.00007743022,0.0003043453,0.00009711625,0.001311986,0.00002033689,0.0002956173,0.00006772175,0.0002485989,0.000001061735],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001620331,"about_ca_system_score_gemma":0.00002760372,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009732802,"about_ca_topic_score_gemma":0.000003254337,"domain_scores_codex":[0.9984715,0.00005144106,0.0004389709,0.0003082449,0.0003500335,0.0003798208],"domain_scores_gemma":[0.9992773,0.0001711785,0.0001023383,0.0002100719,0.000158432,0.00008065753],"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":[0.00001724099,0.000006834941,0.0001042026,0.00005247736,0.00003974065,0.000002766649,0.0001936126,0.908181,0.08404745,0.003555656,0.00002261896,0.003776429],"study_design_scores_gemma":[0.0001731832,0.00002391033,0.00006210716,0.0002790347,0.00003201147,0.000001572258,0.00001330063,0.9248893,0.07283982,0.001089437,0.0003012331,0.0002951002],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4822594,0.0001403506,0.5158502,0.000008128147,0.0001575244,0.00009711192,0.000001963183,0.001374255,0.0001111033],"genre_scores_gemma":[0.9339948,0.00003215969,0.06566791,0.00001140185,0.00006435459,0.00001256772,0.00003992538,0.00009755925,0.00007926114],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4517355,"threshold_uncertainty_score":0.9999409,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01552179662722731,"score_gpt":0.2780370569745892,"score_spread":0.2625152603473619,"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."}}