{"id":"W3034355320","doi":"10.1109/phm-besancon49106.2020.00046","title":"Deep Variational Autoencoder: An Efficient Tool for PHM Frameworks","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hydro-Québec","funders":"","keywords":"Autoencoder; Interpretability; Computer science; Visualization; Artificial intelligence; Dimensionality reduction; Classifier (UML); Machine learning; Prognostics; Data mining; Dimension (graph theory); Deep learning; Pattern recognition (psychology); Mathematics","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":[0.0002004903,0.0002114299,0.0002089132,0.00007989731,0.0002059376,0.000363931,0.001254338,0.0005245574,0.00007806423],"category_scores_gemma":[0.00003997297,0.0002071506,0.0001799889,0.0001991266,0.00002402912,0.00009431214,0.0008568185,0.0006484818,0.00003158434],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007656244,"about_ca_system_score_gemma":0.0001793615,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000200233,"about_ca_topic_score_gemma":0.000003192006,"domain_scores_codex":[0.9983196,0.0000309739,0.0003387918,0.0008485834,0.0002502449,0.0002117595],"domain_scores_gemma":[0.9984936,0.0001026875,0.000178489,0.0009109173,0.0001934549,0.0001208676],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002824792,0.0001070504,0.000003954434,0.00002323086,0.00001861734,4.571317e-7,0.0002114804,0.114191,0.00002416737,0.8650944,0.00141094,0.01891194],"study_design_scores_gemma":[0.00006339399,0.00005387325,0.0001871145,0.000008306059,0.000008806906,0.000002135504,0.000005380293,0.8535586,0.0001636261,0.1407163,0.005002881,0.0002295407],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00005002669,0.00001381234,0.9912376,0.00484257,0.0003281665,0.0009248975,0.00002313754,0.001346785,0.001233038],"genre_scores_gemma":[0.05850787,0.000005429872,0.9381665,0.001688048,0.0002847405,0.001083542,0.00007022652,0.00001685654,0.0001768],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7393677,"threshold_uncertainty_score":0.8447359,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02030444437109124,"score_gpt":0.2859199891385841,"score_spread":0.2656155447674928,"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."}}