{"id":"W3084389888","doi":"10.1109/icphm49022.2020.9187022","title":"Semi-Supervised Learning Approach for Optimizing Condition-based-Maintenance (CBM) Decisions","year":2020,"lang":"en","type":"article","venue":"","topic":"Reliability and Maintenance Optimization","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Reliability (semiconductor); Predictive maintenance; Prognostics; Condition monitoring; Preventive maintenance; Machine learning; Set (abstract data type); Fault (geology); Artificial intelligence; Big data; Condition-based maintenance; Fault detection and isolation; Reliability engineering; Data mining; 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":[0.000155647,0.0001697038,0.0002105505,0.00004503952,0.0001434971,0.0000602779,0.0001536433,0.00009710553,0.000124582],"category_scores_gemma":[0.0005493325,0.0001582558,0.0001203558,0.0002429566,0.00003663064,0.0001907198,0.00001910767,0.0001952316,0.0000243356],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005434268,"about_ca_system_score_gemma":0.00002691813,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002888342,"about_ca_topic_score_gemma":8.230883e-7,"domain_scores_codex":[0.9989899,0.00002008844,0.0002716338,0.000285419,0.0001253477,0.0003076407],"domain_scores_gemma":[0.9993193,0.000226559,0.00002893639,0.0001539499,0.0001272672,0.0001440396],"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":[0.00002006205,0.0000149049,0.00003702348,0.00007837387,0.0000137474,5.135025e-7,0.0001471703,0.9904593,0.001086866,0.0007588099,0.006293381,0.001089898],"study_design_scores_gemma":[0.0006913668,0.00006022492,0.00001306082,0.00003188958,0.00001468684,7.788137e-7,0.0003490654,0.9907568,0.001636764,0.00008760933,0.006145926,0.0002118054],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001644199,0.00005461869,0.984964,0.0005286057,0.0000855559,0.0004726723,0.00001550547,0.0006937126,0.01154119],"genre_scores_gemma":[0.6368095,0.00006063066,0.3618664,0.0006328378,0.00007925984,0.0001408746,0.0001958671,0.00004795429,0.0001666266],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6351653,"threshold_uncertainty_score":0.6453486,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02076261767345257,"score_gpt":0.2234355499428134,"score_spread":0.2026729322693608,"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."}}