{"id":"W4401629876","doi":"10.1016/j.engappai.2024.109088","title":"Advancing unsupervised anomaly detection with normalizing flow and multi-scale ensemble learning","year":2024,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ballard Power Systems (Canada)","funders":"","keywords":"Computer science; Anomaly detection; Scale (ratio); Ensemble learning; Artificial intelligence; Machine learning; Unsupervised learning; Anomaly (physics); Pattern recognition (psychology)","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":[0.000190141,0.0001299484,0.0001182239,0.0002184554,0.0001656887,0.000131099,0.0002428047,0.0000537225,0.000003781332],"category_scores_gemma":[0.00001384324,0.0001305363,0.00003836477,0.0009147075,0.00004138202,0.0003218821,0.00007183234,0.0002021196,0.00001512486],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000349882,"about_ca_system_score_gemma":0.00002547708,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005631044,"about_ca_topic_score_gemma":0.00003272456,"domain_scores_codex":[0.9990541,0.00001059816,0.0002749857,0.0003588293,0.0001161426,0.0001853661],"domain_scores_gemma":[0.9994125,0.00009222198,0.00004676001,0.0002935905,0.00008488868,0.00007005176],"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":[0.000002821285,0.00003557889,0.0000401445,0.00008742348,0.00001396885,0.000001026359,0.0004681719,0.07914044,0.1909644,0.01754829,0.000001877995,0.7116959],"study_design_scores_gemma":[0.000007235168,0.00004755149,0.0000472711,0.00003700121,0.000006540088,0.00001582176,0.00007563512,0.7225782,0.2750874,0.00035345,0.001632325,0.0001115971],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01042365,0.0003344409,0.9880575,0.00007795597,0.00003660731,0.0002772879,0.000001559376,0.0007294964,0.00006149524],"genre_scores_gemma":[0.6373677,0.00004429972,0.3623294,0.000004168499,0.00002846959,0.0001897153,0.000001139177,0.00001258861,0.0000225309],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7115843,"threshold_uncertainty_score":0.5323117,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00976443678066586,"score_gpt":0.2403181524725964,"score_spread":0.2305537156919305,"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."}}