{"id":"W3161912265","doi":"10.1007/s10845-021-01776-1","title":"Automated visual detection of geometrical defects in composite manufacturing processes using deep convolutional neural networks","year":2021,"lang":"en","type":"article","venue":"Journal of Intelligent Manufacturing","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":37,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"","keywords":"Convolutional neural network; Intersection (aeronautics); Artificial intelligence; Computer science; Deep learning; Process (computing); Composite number; Artificial neural network; Pattern recognition (psychology); Binary number; Benchmark (surveying); Algorithm; Mathematics; 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":[],"consensus_categories":[],"category_scores_codex":[0.0004094311,0.0002366718,0.0005196605,0.0008405301,0.00007684474,0.00007431566,0.0001213856,0.0002224197,0.00003114537],"category_scores_gemma":[0.0001293678,0.0002258095,0.0002046839,0.000553794,0.00002505732,0.0002698372,0.00004852694,0.0006186207,0.000002254778],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004065908,"about_ca_system_score_gemma":0.0000517397,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003398242,"about_ca_topic_score_gemma":0.00002815875,"domain_scores_codex":[0.9977773,0.0001080018,0.001166883,0.00017088,0.0004419805,0.0003349635],"domain_scores_gemma":[0.9988756,0.000253135,0.0004013501,0.0001055511,0.0002458855,0.0001184395],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00009431564,0.00004788102,0.0007358416,0.0002091327,0.0000859355,0.0001152317,0.0000754412,0.9578729,0.03221573,7.962204e-7,0.000003602019,0.008543161],"study_design_scores_gemma":[0.0003242078,0.0000680592,0.00411795,0.0002057107,0.0000275133,0.0004987217,0.00009931592,0.3783522,0.6161171,0.000009924045,0.00004531333,0.0001340288],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8911035,0.001213179,0.1060178,0.000002515767,0.001424314,0.0001140162,0.000001290828,0.00008902942,0.0000343818],"genre_scores_gemma":[0.9991654,0.00010182,0.0002817411,0.000007910871,0.0004007134,0.000001756103,0.00000242608,0.00003435131,0.000003841097],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5839013,"threshold_uncertainty_score":0.9208246,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02062040507223864,"score_gpt":0.2609941369438242,"score_spread":0.2403737318715855,"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."}}