{"id":"W4403342446","doi":"10.1080/23744731.2024.2411161","title":"Unsupervised identification of zone-level anomalies in VAV terminal units utilizing autoencoders and PCA","year":2024,"lang":"en","type":"article","venue":"Science and Technology for the Built Environment","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Terminal (telecommunication); Identification (biology); Computer science; Pattern recognition (psychology); Artificial intelligence; Telecommunications","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005775492,0.00007271439,0.00007512543,0.0003247425,0.0002493816,0.0000708628,0.0005310419,0.00005348035,0.000001237295],"category_scores_gemma":[0.00002471027,0.00005516248,0.00001170006,0.0009177464,0.001022269,0.0002494133,0.0002648066,0.00008041249,0.000001383803],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003814026,"about_ca_system_score_gemma":0.00005032282,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001870311,"about_ca_topic_score_gemma":0.000006348288,"domain_scores_codex":[0.9991726,0.000006073238,0.0001805591,0.000347072,0.0001383314,0.0001553418],"domain_scores_gemma":[0.9995078,0.00005186921,0.00004490343,0.0003517569,0.00002214515,0.00002146103],"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":[0.000002880295,0.00003355892,0.0008033132,0.00003939696,0.000008110754,0.000001849257,0.000532698,0.00004937135,0.1483421,0.2688149,0.00002892663,0.5813429],"study_design_scores_gemma":[0.000276538,0.000303509,0.01916229,0.00007467775,0.00002926828,0.00009902255,0.001867746,0.5432166,0.3430942,0.07610831,0.01546794,0.0002999188],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3033148,0.0009284355,0.6904745,0.004664744,0.00005535204,0.0003961022,0.000006928145,0.0001236459,0.00003548157],"genre_scores_gemma":[0.9872694,0.000373593,0.01208885,0.00002400133,0.00000374836,0.0001452822,3.678973e-7,0.000003331041,0.0000914466],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6839545,"threshold_uncertainty_score":0.3766595,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03117438431933174,"score_gpt":0.2626768848542758,"score_spread":0.231502500534944,"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."}}