{"id":"W4381681150","doi":"10.1016/j.ymssp.2023.110491","title":"Prior knowledge-embedded meta-transfer learning for few-shot fault diagnosis under variable operating conditions","year":2023,"lang":"en","type":"article","venue":"Mechanical Systems and Signal Processing","topic":"Machine Fault Diagnosis Techniques","field":"Engineering","cited_by":110,"is_retracted":false,"has_abstract":false,"ca_institutions":"National Research Council Canada; University of British Columbia","funders":"","keywords":"Meta learning (computer science); Computer science; Machine learning; Artificial intelligence; Fault (geology); Generalization; Feature (linguistics); Feature learning; Feature selection; Variable (mathematics); Task (project management); Metric (unit); Transfer of learning; Process (computing); 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000933008,0.0003331603,0.0006410143,0.0001557557,0.000590709,0.0004012142,0.0001649695,0.0002296162,0.0000953776],"category_scores_gemma":[0.0001159152,0.000286574,0.0001426821,0.0004851631,0.00002653214,0.0003037905,0.00005263789,0.0003618969,0.0000148288],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006294762,"about_ca_system_score_gemma":0.00004039881,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003692659,"about_ca_topic_score_gemma":0.00001097098,"domain_scores_codex":[0.9981723,0.0001125865,0.0005633584,0.0004282457,0.0002144595,0.0005090766],"domain_scores_gemma":[0.9988678,0.000647947,0.00004231545,0.0001270296,0.000149422,0.0001654618],"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":[0.00002701624,0.0003010341,0.0002756216,0.008676786,0.001879176,0.00002202446,0.001768985,0.5994449,0.3212328,0.03999857,0.00702803,0.01934508],"study_design_scores_gemma":[0.0004738568,0.0001190327,0.00002784556,0.0004957792,0.0004710034,0.00001273023,0.0003740793,0.9694489,0.02115942,0.001106426,0.005818028,0.0004928497],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1385383,0.005305487,0.8475543,0.0001607522,0.0003754422,0.002206224,0.00008916053,0.004162133,0.001608157],"genre_scores_gemma":[0.9947301,0.00008576004,0.001828714,0.00004229578,0.0002002312,0.00271814,0.00005849849,0.0001025027,0.0002337513],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8561918,"threshold_uncertainty_score":0.9999586,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04844841729963133,"score_gpt":0.3228498561878337,"score_spread":0.2744014388882023,"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."}}