{"id":"W4402602677","doi":"10.1007/978-3-031-61499-6_18","title":"Improving Crack Detection on Concrete Structures Using Real-World Data Augmentation for Deep Learning Convolutional Neural Networks","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in civil engineering","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Current Water Technologies (Canada); Government of New Brunswick; Transport Canada; University of New Brunswick","funders":"","keywords":"Convolutional neural network; Deep learning; Computer science; Artificial neural network; Artificial intelligence","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":[0.0004422564,0.001484304,0.000724427,0.0008933652,0.0002250062,0.0008120036,0.001316567,0.00119397,0.003035556],"category_scores_gemma":[0.001573223,0.0005483742,0.0007978179,0.000667995,0.0003698362,0.001266818,0.00100648,0.001362919,0.001854936],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005743951,"about_ca_system_score_gemma":0.0006481824,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007574925,"about_ca_topic_score_gemma":0.01611348,"domain_scores_codex":[0.9997181,0.00002933556,0.00001235676,0.00009863987,0.00009619521,0.00004532864],"domain_scores_gemma":[0.9992449,0.0002851841,0.00006515605,0.0001386576,0.0002341056,0.00003204511],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002858695,0.0002643671,0.003021165,0.0001871564,0.0001105682,0.0001128138,0.00005309601,0.3257034,0.05134887,0.001613975,0.009778772,0.6075199],"study_design_scores_gemma":[0.00000299077,0.00001568005,0.000374329,0.000005553622,0.000006998137,0.00001426025,0.000004718857,0.9940258,0.004732531,0.0004008415,0.0004128244,0.000003500302],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1363582,0.001213405,0.8479937,0.0004099733,0.0002530137,0.0000739437,0.000993101,0.008498427,0.00420628],"genre_scores_gemma":[0.6291411,0.000614071,0.3578061,0.0002139911,0.00009564059,0.00006775094,0.003705583,0.0004219253,0.007933853],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007574925,"threshold_uncertainty_score":0.01506168,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01695453290172404,"score_gpt":0.2459382554485849,"score_spread":0.2289837225468609,"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."}}