{"id":"W4383682053","doi":"10.35490/ec3.2023.213","title":"Machine learning-based fault detection and preliminary diagnosis for terminal air-handling units","year":2023,"lang":"en","type":"article","venue":"Computing in construction","topic":"Elevator Systems and Control","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Fuseforward (Canada); Toronto Metropolitan University","funders":"","keywords":"Cluster analysis; Fault detection and isolation; Computer science; Unsupervised learning; Terminal (telecommunication); Fault (geology); Artificial intelligence; Noise (video); Cluster (spacecraft); Data mining; Machine learning; Pattern recognition (psychology); Telecommunications","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":[0.0002697547,0.0004274647,0.0003553826,0.0009710102,0.0003445952,0.000389509,0.0004416087,0.0003186651,0.0008836695],"category_scores_gemma":[0.001127589,0.0001355117,0.00025997,0.0005188751,0.0002492862,0.0004253938,0.0002841314,0.0002983044,0.0003761508],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006147027,"about_ca_system_score_gemma":0.0006141333,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006879815,"about_ca_topic_score_gemma":0.01072767,"domain_scores_codex":[0.9997768,0.00003619149,0.00001587786,0.00005041375,0.000091055,0.00002969329],"domain_scores_gemma":[0.9995798,0.0001288482,0.00008417979,0.0000398673,0.0001472272,0.00001999354],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007169865,0.0003729053,0.03531941,0.0001681509,0.00006207827,0.0002215806,0.0001789458,0.3308008,0.06221115,0.001715396,0.003650479,0.5645822],"study_design_scores_gemma":[0.00001024639,0.0001655892,0.01774537,0.000007323513,0.00001435051,0.00005643696,0.00005551813,0.962348,0.01803671,0.000677288,0.0008693408,0.0000137936],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4114695,0.0003174478,0.5826502,0.0002521685,0.00006169207,0.0001225086,0.0003258474,0.002120246,0.002680267],"genre_scores_gemma":[0.9598435,0.00005514393,0.03875554,0.00001644451,0.00001057807,0.00003015578,0.0002582488,0.00001272209,0.001017799],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006879815,"threshold_uncertainty_score":0.0136795,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01136110813927283,"score_gpt":0.2165786434849941,"score_spread":0.2052175353457212,"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."}}