{"id":"W4318480157","doi":"10.1063/9.0000451","title":"Classification and characterization of coexisting defects from magnetic flux leakage data using deep learning method","year":2023,"lang":"en","type":"article","venue":"AIP Advances","topic":"Non-Destructive Testing Techniques","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"","keywords":"Magnetic flux leakage; Deep learning; Convolutional neural network; Nondestructive testing; Ferromagnetism; Artificial intelligence; Materials science; Finite element method; Computer science; Characterization (materials science); Leakage (economics); Artificial neural network; Pipeline transport; Machine learning; Structural engineering; Engineering; Mechanical engineering; Magnet; Condensed matter physics; Physics; Nanotechnology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003749475,0.0008155874,0.0005090728,0.001578601,0.0001590085,0.0004389558,0.0007672471,0.0008077926,0.0006487618],"category_scores_gemma":[0.000994008,0.0002487008,0.0005095874,0.0004696276,0.0003064645,0.0006188829,0.0005045626,0.0004770747,0.0002190601],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004609285,"about_ca_system_score_gemma":0.0005267765,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004276797,"about_ca_topic_score_gemma":0.004427765,"domain_scores_codex":[0.9997997,0.00001740592,0.00001939646,0.00005307009,0.00006881837,0.00004169979],"domain_scores_gemma":[0.9995248,0.000112668,0.00008895163,0.00003890574,0.0002023189,0.00003225765],"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":[0.00060302,0.0004310714,0.03726061,0.0002936668,0.000102415,0.0008635376,0.0001796721,0.4827162,0.07544097,0.001290168,0.004215777,0.3966029],"study_design_scores_gemma":[0.00000666909,0.00004415785,0.00213033,0.000009289646,0.00001210907,0.00006139868,0.00002801808,0.9875844,0.00943938,0.0003596644,0.0003168016,0.000007791878],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5656646,0.0006869793,0.4285513,0.0002861751,0.00005729932,0.00009040449,0.0007496161,0.002073557,0.001839997],"genre_scores_gemma":[0.9558506,0.0002128078,0.0409542,0.00009971914,0.00001645731,0.00005729086,0.001168049,0.00003262567,0.001608278],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.004276797,"threshold_uncertainty_score":0.008503854,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05744575270271777,"score_gpt":0.3231673884693367,"score_spread":0.2657216357666189,"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."}}