{"id":"W3027812880","doi":"10.1016/j.cie.2020.106536","title":"A relative entropy based feature selection framework for asset data in predictive maintenance","year":2020,"lang":"en","type":"article","venue":"Computers & Industrial Engineering","topic":"Machine Fault Diagnosis Techniques","field":"Engineering","cited_by":59,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Feature engineering; Kullback–Leibler divergence; Computer science; Data mining; Prognostics; Entropy (arrow of time); Feature selection; Data-driven; Feature (linguistics); Mutual information; Cluster analysis; Artificial intelligence","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000195927,0.0002852684,0.0003395785,0.0001507444,0.00002987071,0.00005854207,0.0005003415,0.0003706268,0.000007344675],"category_scores_gemma":[0.001266225,0.0003222011,0.00006477071,0.0005951572,0.00001261782,0.0003438154,0.0001062891,0.001088485,0.000002003275],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002369123,"about_ca_system_score_gemma":0.00004780087,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008092547,"about_ca_topic_score_gemma":0.000001956046,"domain_scores_codex":[0.9987335,0.00002813735,0.0002786696,0.0004230838,0.0001588219,0.0003777727],"domain_scores_gemma":[0.9988985,0.0005485556,0.00005101585,0.0003034095,0.00003573441,0.0001627718],"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":[0.00009791146,0.00002814812,0.001142968,0.0001045147,0.000103702,0.0000116838,0.0002014233,0.9517605,0.0008091899,0.001859286,0.04023035,0.003650367],"study_design_scores_gemma":[0.000985279,0.0001416854,0.0004146266,0.0003699604,0.00002280299,0.000001516418,0.000006560236,0.9790593,0.002021776,0.0001064424,0.01658004,0.0002900289],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003823786,0.00007237668,0.9919501,0.001110162,0.000700238,0.0008765263,0.0001985471,0.001248429,0.00001983948],"genre_scores_gemma":[0.7522085,0.00001327434,0.245606,0.0002483256,0.001343505,0.000186413,0.0002875662,0.0001042955,0.000002158084],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7483847,"threshold_uncertainty_score":0.999923,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03508270518889641,"score_gpt":0.272607500635747,"score_spread":0.2375247954468505,"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."}}