{"id":"W2973371466","doi":"10.1109/coase.2019.8843058","title":"A Deep Learning Approach for Heating and Cooling Equipment Monitoring","year":2019,"lang":"en","type":"article","venue":"","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Anomaly detection; Outlier; Chiller; Deep learning; Computer science; Artificial intelligence; Condition monitoring; Fault detection and isolation; Stage (stratigraphy); Machine learning; Engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.000125914,0.00007580918,0.0001119032,0.00003481097,0.00005560462,0.00004839004,0.00002830811,0.00003711425,0.000007416918],"category_scores_gemma":[0.000009060441,0.00007205237,0.00002608398,0.00004058122,0.000002539623,0.00005920088,0.000009794328,0.00007984952,0.000007731263],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003056684,"about_ca_system_score_gemma":0.00000146119,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001697774,"about_ca_topic_score_gemma":7.96464e-7,"domain_scores_codex":[0.9995483,0.000007632273,0.0001177295,0.000107077,0.00006005605,0.0001592508],"domain_scores_gemma":[0.9998483,0.00003583709,0.00001209842,0.00005400849,0.00001183846,0.00003793566],"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":[0.00001519553,0.000004974603,0.006251865,0.0003044785,0.00004977123,1.949708e-7,0.0006901486,0.9183061,0.03619402,0.0001588983,0.000005892573,0.03801854],"study_design_scores_gemma":[0.0004129597,0.00002825957,0.0001836291,0.00001845998,0.000003909899,0.000003874175,0.001405125,0.9950456,0.00181481,0.00000300133,0.0009854614,0.00009489688],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6447178,0.0005988167,0.3398643,0.000003276433,0.0004402676,0.0003985851,1.560104e-7,0.0004483119,0.01352841],"genre_scores_gemma":[0.9944467,0.000008256081,0.004668128,0.000004324455,0.0001288273,0.00006460112,9.130378e-7,0.00002006544,0.0006581729],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3497289,"threshold_uncertainty_score":0.293821,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01050218516698876,"score_gpt":0.2210762691024384,"score_spread":0.2105740839354497,"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."}}