{"id":"W2512344339","doi":"10.1007/s10489-016-0829-4","title":"Machine learning-based methods for TTF estimation with application to APU prognostics","year":2016,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Reliability and Maintenance Optimization","field":"Engineering","cited_by":33,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University; National Research Council Canada","funders":"","keywords":"Prognostics; Computer science; Cluster analysis; Machine learning; Support vector machine; Predictive maintenance; Artificial intelligence; Predictive modelling; Data mining; Component (thermodynamics); Predictive analytics; Reliability 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":[0.0002992286,0.0001371684,0.0001262744,0.00006176325,0.00005767823,0.00002099828,0.0001268526,0.00006394039,0.0000140354],"category_scores_gemma":[0.0001987189,0.00009638269,0.00002277135,0.0002282693,0.0000378167,0.00006134433,0.00001085321,0.00006672028,0.00005438688],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007540172,"about_ca_system_score_gemma":0.00001680279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003818739,"about_ca_topic_score_gemma":0.000004690173,"domain_scores_codex":[0.99927,0.00001324803,0.0002015289,0.0002316374,0.00008461075,0.0001990313],"domain_scores_gemma":[0.9992469,0.0003301175,0.00004158043,0.0002123757,0.0001030626,0.00006594117],"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":[0.00003639544,0.00001092148,0.00002046841,0.00003884764,0.000004828196,2.686712e-8,0.00004060069,0.5909479,0.004172305,0.005486514,0.00002294815,0.3992183],"study_design_scores_gemma":[0.00009840161,0.0001003548,0.00001882178,0.00003325576,0.00001268996,4.857764e-7,0.00001114001,0.8605434,0.1290051,0.002973174,0.007048143,0.0001550092],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001656097,0.00002186986,0.9974533,0.0002094176,0.00004687177,0.001144374,0.000005325024,0.0003250303,0.0006281807],"genre_scores_gemma":[0.4534836,0.00001951653,0.545622,0.00004836791,0.00001623996,0.0007262675,0.00002145804,0.00002582425,0.00003671085],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.453318,"threshold_uncertainty_score":0.3930372,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009661680582974275,"score_gpt":0.2736757204206994,"score_spread":0.2640140398377251,"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."}}