{"id":"W4386432631","doi":"10.1007/978-981-19-9822-5_26","title":"A Weight Clustering-Based Pattern Recognition Method for Improving Building’s Cooling Load Prediction Reliability","year":2023,"lang":"en","type":"book-chapter","venue":"Environmental science and engineering","topic":"Building Energy and Comfort Optimization","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Cluster analysis; Cooling load; Outlier; HVAC; Mean absolute percentage error; Computer science; Artificial neural network; Reliability (semiconductor); Sensitivity (control systems); Data mining; Artificial intelligence; Pattern recognition (psychology); Machine learning; Engineering; Air conditioning","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":[0.0003687459,0.0007524015,0.000631152,0.0009007616,0.0003600905,0.0004234486,0.001138823,0.0005602724,0.002058922],"category_scores_gemma":[0.001048467,0.0003022037,0.0005837796,0.001238123,0.0002615579,0.0006089746,0.0003925109,0.0007289377,0.0008931847],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004225524,"about_ca_system_score_gemma":0.000512887,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009253178,"about_ca_topic_score_gemma":0.01095344,"domain_scores_codex":[0.9996943,0.00002834623,0.00001919361,0.00008614516,0.0001448403,0.00002715962],"domain_scores_gemma":[0.9993742,0.0001220858,0.00003705821,0.00006641666,0.0003857167,0.00001452985],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001580905,0.000129912,0.001186347,0.00007180872,0.0000819484,0.00005675826,0.00005112983,0.1152405,0.04459662,0.001468428,0.005059858,0.8318987],"study_design_scores_gemma":[0.000005101213,0.00003582034,0.00106476,0.000004506826,0.00002042674,0.00004099353,0.000009159951,0.9883235,0.008909783,0.0005729413,0.001002846,0.00001026439],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01970346,0.000274204,0.9773094,0.00005865955,0.00009196419,0.00003042068,0.00008717764,0.001331705,0.001113026],"genre_scores_gemma":[0.3483937,0.0003466901,0.6419451,0.0001149504,0.00008568777,0.000119436,0.0005721768,0.0002755826,0.008146722],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009253178,"threshold_uncertainty_score":0.01839864,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008436614585619109,"score_gpt":0.1873009303624402,"score_spread":0.178864315776821,"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."}}