{"id":"W2809944199","doi":"10.1007/s42243-018-0103-6","title":"Multi-class classification method for strip steel surface defects based on support vector machine with adjustable hyper-sphere","year":2018,"lang":"en","type":"article","venue":"Journal of Iron and Steel Research International","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Support vector machine; Pattern recognition (psychology); Binary classification; Mathematics; One-class classification; Surface (topology); Artificial intelligence; Feature vector; Classifier (UML); Structured support vector machine; Minification; Multiclass classification; Computer science; Algorithm; Mathematical optimization; Geometry","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":[0.0009703013,0.0008398852,0.001274598,0.001725159,0.0005553139,0.0008953772,0.001542051,0.001197123,0.001551569],"category_scores_gemma":[0.001408665,0.000357619,0.0009982459,0.001000175,0.0003628769,0.001211105,0.0009156098,0.0009715724,0.0006558113],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004210277,"about_ca_system_score_gemma":0.0009066469,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003447934,"about_ca_topic_score_gemma":0.002857194,"domain_scores_codex":[0.9989773,0.0001077896,0.00008095922,0.0002908491,0.0004260914,0.0001170344],"domain_scores_gemma":[0.9988638,0.0001994869,0.00007071469,0.00009214714,0.0007069474,0.00006693938],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004489704,0.0002112097,0.00322185,0.0001227469,0.00007959776,0.0001018502,0.0001161354,0.03554176,0.03240091,0.001669354,0.003749064,0.9223366],"study_design_scores_gemma":[0.00001761836,0.00007994771,0.002141024,0.000008174848,0.00002543954,0.0000750133,0.00003997368,0.9874232,0.00859248,0.000704585,0.0008727309,0.00001978235],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06235155,0.0004106997,0.9341841,0.0001341266,0.0001254966,0.00007866737,0.0000826008,0.001462432,0.00117023],"genre_scores_gemma":[0.6934716,0.0002962955,0.3014233,0.0001321923,0.000120875,0.0002019236,0.0005003557,0.0001231628,0.003730362],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003447934,"threshold_uncertainty_score":0.006855726,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09428210083464171,"score_gpt":0.3749240949677056,"score_spread":0.2806419941330639,"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."}}