{"id":"W4399585680","doi":"10.1016/j.engstruct.2024.118343","title":"Pixel-level concrete bridge crack detection using Convolutional Neural Networks, gabor filters, and attention mechanisms","year":2024,"lang":"en","type":"article","venue":"Engineering Structures","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":49,"is_retracted":false,"has_abstract":false,"ca_institutions":"Royal Military College of Canada","funders":"","keywords":"Convolutional neural network; Bridge (graph theory); Computer science; Structural engineering; Gabor filter; Pixel; Artificial intelligence; Pattern recognition (psychology); Engineering; Feature extraction","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":[0.000299053,0.0005348659,0.0005103559,0.0007491466,0.0001915281,0.00060541,0.0007198934,0.0007202533,0.00149349],"category_scores_gemma":[0.0007302966,0.0002623554,0.0004970135,0.0005610024,0.0002346024,0.0008186704,0.0005864059,0.0005813165,0.0004603912],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005785073,"about_ca_system_score_gemma":0.0005559762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009039677,"about_ca_topic_score_gemma":0.01326318,"domain_scores_codex":[0.9998316,0.00001292281,0.000005782704,0.00005853953,0.00004220129,0.0000489159],"domain_scores_gemma":[0.9997552,0.00007646762,0.00003807274,0.00003391421,0.00007291423,0.00002342752],"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":[0.000677017,0.0003977625,0.008370698,0.000132396,0.0001711619,0.0001745338,0.00006788285,0.1381853,0.1256509,0.004761185,0.005044421,0.7163668],"study_design_scores_gemma":[0.000005477996,0.00003588984,0.003649348,0.000008332396,0.00002714422,0.00003312747,0.000008123052,0.9859093,0.008720076,0.00115528,0.0004413114,0.000006548454],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.327399,0.001244826,0.6629093,0.000438815,0.0001411739,0.00005279993,0.0004675079,0.002364457,0.004982043],"genre_scores_gemma":[0.9247796,0.0003655269,0.07040644,0.0001083291,0.00005440813,0.00002129142,0.0005243331,0.0000524699,0.00368764],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009039677,"threshold_uncertainty_score":0.01797408,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01004749709603155,"score_gpt":0.2103510988253206,"score_spread":0.200303601729289,"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."}}