{"id":"W4384560547","doi":"10.1007/s11668-023-01695-8","title":"An Autoencoder with Convolutional Neural Network for Surface Defect Detection on Cast Components","year":2023,"lang":"en","type":"article","venue":"Journal of Failure Analysis and Prevention","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University","funders":"","keywords":"Autoencoder; Artificial intelligence; Convolutional neural network; Pattern recognition (psychology); Computer science; Retraining; Cluster analysis; Identification (biology); Convolution (computer science); Artificial neural network; Automation; Machine learning; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000258505,0.0005605478,0.0005452977,0.0004674532,0.0001652114,0.0003253214,0.0007096359,0.0005367929,0.001147551],"category_scores_gemma":[0.000426617,0.0003251186,0.0004513395,0.0003420008,0.000169998,0.0004224535,0.000435284,0.0005742028,0.0003710823],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003558309,"about_ca_system_score_gemma":0.0006008464,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009172097,"about_ca_topic_score_gemma":0.01171189,"domain_scores_codex":[0.9998559,0.00001306726,0.000006477109,0.00003914789,0.0000598654,0.00002561021],"domain_scores_gemma":[0.9997918,0.00005492771,0.00001640041,0.00002633473,0.00009962918,0.0000108239],"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":[0.0002777223,0.0001732014,0.001938335,0.000121949,0.0001035064,0.0001453111,0.00004434512,0.286269,0.06507664,0.001416809,0.003408576,0.6410246],"study_design_scores_gemma":[0.000002149971,0.00002125398,0.0004930075,0.000002705121,0.00001060284,0.00001770973,0.000003014134,0.9948277,0.004248469,0.0001266267,0.0002435876,0.000003166573],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1253181,0.0006318897,0.8690794,0.0001448461,0.0001362269,0.0000523649,0.0001680747,0.002146526,0.002322584],"genre_scores_gemma":[0.7838917,0.0004014861,0.2077813,0.0001214625,0.00004490666,0.00004962274,0.0004342906,0.00009271217,0.007182508],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009172097,"threshold_uncertainty_score":0.01823741,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02163082648547668,"score_gpt":0.2596744921532966,"score_spread":0.23804366566782,"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."}}