{"id":"W3193440158","doi":"10.1007/978-3-030-75506-5_64","title":"Deep Learning-Based Automatic Detection of Defective Tablets in Pharmaceutical Manufacturing","year":2021,"lang":"en","type":"book-chapter","venue":"World Congress on Medical Physics and Biomedical Engineering, September 7 - 12, 2009, Munich, Germany","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":23,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"","keywords":"Artificial intelligence; Computer science; Support vector machine; Convolutional neural network; Hyperparameter; Transfer of learning; Deep learning; Machine learning; Pattern recognition (psychology); Set (abstract data type); AdaBoost","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":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0006182759,0.0007664346,0.001236044,0.000663783,0.00008411225,0.00006137529,0.0002774459,0.001006265,0.0008633157],"category_scores_gemma":[0.0001129479,0.0007431916,0.0003264344,0.0002760665,0.0002343215,0.00009493288,0.0001280245,0.002854031,0.00005198668],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002509719,"about_ca_system_score_gemma":0.00009262122,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002964903,"about_ca_topic_score_gemma":0.0001020558,"domain_scores_codex":[0.9961732,0.0000984727,0.001104333,0.0006229376,0.001370338,0.0006306883],"domain_scores_gemma":[0.9981169,0.0005276122,0.0002366443,0.0004226357,0.00008060786,0.0006156115],"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":[0.0003270765,0.0008936265,0.00005549535,0.0087423,0.002393661,0.002296163,0.0003308892,0.1594545,0.005753605,0.003523306,0.004758015,0.8114713],"study_design_scores_gemma":[0.002362326,0.0002265639,0.000100606,0.003735424,0.0001569984,0.00003834369,0.00001048926,0.6973915,0.007530523,0.00010587,0.2873664,0.0009750472],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2061051,0.04327009,0.1976546,0.0008481941,0.0670305,0.01363344,0.0008172812,0.01052248,0.4601184],"genre_scores_gemma":[0.9880572,0.0004020619,0.00006069089,0.0001154536,0.001056378,0.00007615405,0.000122529,0.0002464284,0.009863115],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8104963,"threshold_uncertainty_score":0.9995019,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0114056290499249,"score_gpt":0.2342520444241091,"score_spread":0.2228464153741842,"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."}}