{"id":"W4377042701","doi":"10.3390/s23104793","title":"Image Generation and Recognition for Railway Surface Defect Detection","year":2023,"lang":"en","type":"article","venue":"Sensors","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Transport Canada","keywords":"Obstacle; Artificial intelligence; Nondestructive testing; Artificial neural network; Segmentation; Computer science; Pattern recognition (psychology); Identification (biology); Track (disk drive); Pixel; Computer vision; Image segmentation; Sampling (signal processing); Filter (signal processing)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002544027,0.0004136734,0.0002974331,0.0007721309,0.0001257077,0.0003001604,0.0005485367,0.0004969235,0.002167433],"category_scores_gemma":[0.000485979,0.0001868973,0.0004665211,0.0004826077,0.0001967728,0.0003994198,0.0003058157,0.0003545746,0.001001502],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003755397,"about_ca_system_score_gemma":0.0003348859,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002499601,"about_ca_topic_score_gemma":0.002695148,"domain_scores_codex":[0.9998411,0.0000152959,0.000006278227,0.00004963109,0.00006631184,0.00002133524],"domain_scores_gemma":[0.9998451,0.00003011197,0.00002040973,0.00003142481,0.00006570338,0.000007245215],"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":[0.0002161778,0.000107633,0.002800064,0.0001755071,0.00003808607,0.0002241395,0.00006551508,0.06455591,0.173256,0.002572892,0.005660031,0.7503281],"study_design_scores_gemma":[0.00001301628,0.0001311891,0.006357953,0.00001658466,0.00002929865,0.0003315942,0.00003427545,0.8906814,0.09404658,0.001314756,0.007022929,0.00002038788],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0921568,0.0005600617,0.8963714,0.0002142443,0.0000974363,0.0001490398,0.0003511111,0.004779657,0.00532025],"genre_scores_gemma":[0.5495417,0.0005414257,0.4414891,0.0001557053,0.00004071744,0.0001072518,0.001241377,0.0002352882,0.00664746],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002499601,"threshold_uncertainty_score":0.007250786,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01622693294988104,"score_gpt":0.2228881358327438,"score_spread":0.2066612028828628,"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."}}