{"id":"W2737457785","doi":"10.1016/j.chemolab.2017.07.008","title":"Multi-class classification for steel surface defects based on machine learning with quantile hyper-spheres","year":2017,"lang":"en","type":"article","venue":"Chemometrics and Intelligent Laboratory Systems","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":42,"is_retracted":false,"has_abstract":false,"ca_institutions":"Lakehead University","funders":"State Key Laboratory of Robotics and System","keywords":"Quantile; Classifier (UML); Artificial intelligence; Mathematics; Pattern recognition (psychology); Boundary (topology); Computer science; One-class classification; Machine learning; Statistics; Mathematical analysis","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":[0.003574131,0.0007126025,0.001690403,0.001947479,0.000520582,0.00133741,0.001809058,0.001179236,0.001158883],"category_scores_gemma":[0.007788753,0.0003784425,0.001303891,0.001518436,0.0009644268,0.001695369,0.001975709,0.00134043,0.0004357533],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001055017,"about_ca_system_score_gemma":0.0009521859,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004205372,"about_ca_topic_score_gemma":0.00242958,"domain_scores_codex":[0.9984466,0.0005060689,0.000110099,0.0003220831,0.0004521014,0.0001630263],"domain_scores_gemma":[0.9959818,0.001941392,0.0003628709,0.0004900991,0.001044965,0.0001788633],"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":[0.0005705382,0.000187352,0.007914082,0.0001713145,0.0001393201,0.0001054417,0.0002444973,0.50109,0.00974777,0.01760425,0.002940113,0.4592853],"study_design_scores_gemma":[0.000002880333,0.00001599318,0.0005813236,0.000002743939,0.000004003976,0.000008992732,0.000008721102,0.9962611,0.0007101324,0.002300319,0.00009939017,0.000004532619],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04638572,0.0002444026,0.9522673,0.0001361876,0.00001971166,0.00003217556,0.00005685477,0.0004837229,0.0003738597],"genre_scores_gemma":[0.8018741,0.0002036282,0.1962766,0.00007606564,0.00006271607,0.00008772594,0.0004469551,0.0001248151,0.0008474094],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004205372,"threshold_uncertainty_score":0.01890206,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05711096008556061,"score_gpt":0.2670004874774562,"score_spread":0.2098895273918956,"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."}}