{"id":"W4396629560","doi":"10.1109/tai.2024.3396422","title":"Remaining Useful Life Prediction via Frequency Emphasizing Mix-Up and Masked Reconstruction","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Artificial Intelligence","topic":"Machine Fault Diagnosis Techniques","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Singapore Institute of Manufacturing Technology; National University of Singapore","keywords":"Leverage (statistics); Computer science; Bottleneck; Artificial intelligence; Machine learning; Autoencoder; Domain (mathematical analysis); Data mining; Deep learning; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002609628,0.000258423,0.0001981961,0.0004208644,0.0001945144,0.0001779088,0.0001147621,0.0001815211,0.0002076224],"category_scores_gemma":[0.0000234754,0.0002851672,0.00009780989,0.0004966771,0.00009884609,0.0004818318,0.000001349605,0.0005249321,0.0001088562],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001417666,"about_ca_system_score_gemma":0.00003006834,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007936214,"about_ca_topic_score_gemma":0.0001341248,"domain_scores_codex":[0.9985293,0.00004842446,0.0005288035,0.0004117982,0.0001979981,0.0002836612],"domain_scores_gemma":[0.9993479,0.0001905382,0.00002888961,0.0002429332,0.00004705249,0.0001426642],"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":[0.00002204184,0.00004938465,0.00004330373,0.0001708126,0.0001001044,0.00001453829,0.001174692,0.02432589,0.05885125,0.0008419394,0.0001390522,0.914267],"study_design_scores_gemma":[0.00002240027,0.0001139654,0.00004761724,0.0003815423,0.00006353208,0.00008729861,0.0002280589,0.5284526,0.4623123,0.007740889,0.0002342276,0.0003155321],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1129334,0.0003742581,0.8802425,0.0001164035,0.003310951,0.0002755037,0.00004039891,0.00224777,0.0004587879],"genre_scores_gemma":[0.9942264,0.0006867393,0.00466573,0.00003982679,0.0001620111,0.0001234811,0.000003531708,0.00006428365,0.00002799483],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9139515,"threshold_uncertainty_score":0.9999601,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03230652616771762,"score_gpt":0.2861934823015627,"score_spread":0.2538869561338451,"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."}}