{"id":"W4313518939","doi":"10.3390/s23010504","title":"Improving Concrete Crack Segmentation Networks through CutMix Data Synthesis and Temporal Data Fusion","year":2023,"lang":"en","type":"article","venue":"Sensors","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Segmentation; Computer science; Artificial intelligence; Convolutional neural network; Artificial neural network; Pattern recognition (psychology); Transfer of learning; Pixel; Key (lock); Deep learning; Data mining; Computer vision","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":[0.0009664946,0.001433396,0.0007525051,0.001021051,0.0003616149,0.0006403932,0.0009460556,0.001049368,0.001139547],"category_scores_gemma":[0.002263862,0.0003704032,0.0008538923,0.0007210535,0.0004698752,0.001740684,0.001259488,0.001224495,0.0006551869],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007137759,"about_ca_system_score_gemma":0.0007738021,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006625183,"about_ca_topic_score_gemma":0.0090777,"domain_scores_codex":[0.999558,0.00005171277,0.00002399149,0.0001897139,0.0001182239,0.00005838582],"domain_scores_gemma":[0.9993356,0.0001963355,0.00006485062,0.0001215939,0.0002473478,0.00003430776],"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":[0.0005606677,0.0003986468,0.004379655,0.0001208142,0.0001532533,0.0001530071,0.0001491923,0.2977832,0.0705588,0.001651054,0.003741971,0.6203498],"study_design_scores_gemma":[0.000008418227,0.00006660626,0.0008148265,0.000004962497,0.00001804279,0.00002254857,0.00002706979,0.9828686,0.0147158,0.0008228247,0.0006208668,0.000009480703],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2357552,0.0008470414,0.753063,0.0003609493,0.0001578225,0.0001481481,0.0009262747,0.006107834,0.002633712],"genre_scores_gemma":[0.695125,0.0002293913,0.2966982,0.0002294922,0.00005499425,0.0001971889,0.004325833,0.0002024257,0.002937507],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006625183,"threshold_uncertainty_score":0.01317322,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03070952763763122,"score_gpt":0.2622207032400817,"score_spread":0.2315111756024505,"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."}}