{"id":"W4403722312","doi":"10.1109/tase.2024.3481211","title":"Latent Code Description for Unsupervised AHU Fault Detection Using Adaptive Adversarial Autoencoder","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Automation Science and Engineering","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Autoencoder; Fault detection and isolation; Adversarial system; Computer science; Artificial intelligence; Code (set theory); Fault (geology); Pattern recognition (psychology); Unsupervised learning; Deep learning; Geology; Programming language","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":[0.0006905576,0.000956514,0.0006311369,0.0006049253,0.000248981,0.0005398309,0.001112845,0.0006941808,0.001235001],"category_scores_gemma":[0.002966363,0.0003692537,0.0007086131,0.0004087969,0.0005473968,0.0009636768,0.00106076,0.001703725,0.0006332998],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005919712,"about_ca_system_score_gemma":0.0008193483,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004658916,"about_ca_topic_score_gemma":0.005813598,"domain_scores_codex":[0.9994664,0.0001170328,0.00003110811,0.0001327857,0.000184173,0.00006855755],"domain_scores_gemma":[0.9987563,0.000568378,0.0001434354,0.0001572875,0.0003288879,0.00004567478],"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":[0.0001355032,0.00007342932,0.002041604,0.000073175,0.00005909948,0.0001213186,0.00008165807,0.7743984,0.008401142,0.004622499,0.002500438,0.2074917],"study_design_scores_gemma":[0.000001359434,0.000008532264,0.00009060241,0.000002377178,0.00000177468,0.00001217266,0.000003086058,0.9980106,0.0009313474,0.0007822338,0.0001534249,0.000002552963],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02049211,0.0001976885,0.9770681,0.0001321074,0.00003353524,0.00003136621,0.0001072547,0.001219983,0.0007178559],"genre_scores_gemma":[0.7243088,0.0002598011,0.2683677,0.0003254395,0.00006483751,0.0001798498,0.001318442,0.0002668501,0.004908245],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004658916,"threshold_uncertainty_score":0.009263575,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02531744880413578,"score_gpt":0.2394429703611142,"score_spread":0.2141255215569784,"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."}}