{"id":"W3153503116","doi":"10.1016/j.ultras.2021.106436","title":"Towards using convolutional neural network to locate, identify and size defects in phased array ultrasonic testing","year":2021,"lang":"en","type":"article","venue":"Ultrasonics","topic":"Non-Destructive Testing Techniques","field":"Engineering","cited_by":65,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Phased array; Intersection (aeronautics); Convolutional neural network; Computer science; Ultrasonic sensor; Finite element method; Artificial neural network; Phased array ultrasonics; Data acquisition; Acoustics; Optics; Artificial intelligence; Materials science; Physics; Structural engineering; Engineering; Telecommunications","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003227843,0.0002806231,0.0003102681,0.00006271125,0.0001049686,0.0001052134,0.0001625219,0.000131774,0.00002146078],"category_scores_gemma":[0.00216985,0.0003424481,0.00004951335,0.0009985276,0.00006396484,0.0001869308,0.000030139,0.0004092271,0.000004615126],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003143138,"about_ca_system_score_gemma":0.000158066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006844422,"about_ca_topic_score_gemma":0.00009323031,"domain_scores_codex":[0.9983653,0.00007263067,0.0003452137,0.0003920788,0.0002152666,0.0006095149],"domain_scores_gemma":[0.9983797,0.001009349,0.0000504633,0.0002568146,0.0001466019,0.0001570733],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.000007992133,0.00002985905,0.09556516,0.0001040551,0.00002777336,0.00005279859,0.0001368362,0.02867132,0.8736355,0.0008882147,0.00009269422,0.0007877962],"study_design_scores_gemma":[0.002261737,0.0002351286,0.631639,0.001846126,0.0001537786,0.001790759,0.0002415021,0.03798017,0.2661023,0.05491002,0.0003388217,0.002500637],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9703826,0.0009347141,0.02583528,0.00002742142,0.0003213022,0.0002327748,0.00001471185,0.0006767857,0.001574408],"genre_scores_gemma":[0.6635619,0.00001372424,0.3361793,0.00007570303,0.00009898355,0.00001339067,0.000006114478,0.00004837516,0.000002455354],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6075332,"threshold_uncertainty_score":0.9999027,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03399877094350187,"score_gpt":0.2737627800476568,"score_spread":0.2397640091041549,"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."}}