{"id":"W4296640192","doi":"10.1016/j.buildenv.2022.109620","title":"Unsupervised outlier detection using neural network-based mixtures of probabilistic principal component analyzers for building chiller fault diagnosis","year":2022,"lang":"en","type":"article","venue":"Building and Environment","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Outlier; Anomaly detection; Principal component analysis; Computer science; Probabilistic logic; Fault detection and isolation; Artificial neural network; Data mining; Chiller boiler system; Artificial intelligence; Fault (geology); Pattern recognition (psychology); Engineering; Water chiller","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009150595,0.0007354271,0.0007807594,0.001363366,0.0003893863,0.000687591,0.0009116782,0.0006155528,0.0005279885],"category_scores_gemma":[0.003108229,0.0003370381,0.0006354155,0.001153369,0.0004009639,0.001136145,0.0007511192,0.001270176,0.0002456546],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003931189,"about_ca_system_score_gemma":0.0005439695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002813449,"about_ca_topic_score_gemma":0.003676956,"domain_scores_codex":[0.9990819,0.0002056415,0.00005472511,0.000224005,0.0003402876,0.00009354977],"domain_scores_gemma":[0.9987428,0.0005287592,0.0002073297,0.0001180856,0.0003586126,0.00004452389],"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":[0.001155879,0.0005569878,0.02018684,0.0001688591,0.0003942835,0.000310305,0.0001773531,0.3179533,0.04432315,0.003809697,0.002362081,0.6086013],"study_design_scores_gemma":[0.000003972393,0.00002718371,0.001863082,0.000002579463,0.00001283431,0.00004145159,0.000008406444,0.9951673,0.001926707,0.000812397,0.0001276697,0.000006463567],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07903954,0.000344095,0.9184746,0.00009422984,0.00005858457,0.00002793015,0.00008195174,0.001334867,0.0005443097],"genre_scores_gemma":[0.8580768,0.0001657767,0.1405506,0.00003776432,0.00004573044,0.00003887994,0.0002330662,0.00007987832,0.0007714368],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002813449,"threshold_uncertainty_score":0.005594194,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02076974901253803,"score_gpt":0.2429634756932868,"score_spread":0.2221937266807488,"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."}}