{"id":"W3111553838","doi":"10.1155/2020/8515213","title":"Pavement Crack Detection and Segmentation Method Based on Improved Deep Learning Fusion Model","year":2020,"lang":"en","type":"article","venue":"Mathematical Problems in Engineering","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":74,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Fundamental Research Funds for the Central Universities; National Key Research and Development Program of China; University of Waterloo; National Natural Science Foundation of China","keywords":"Segmentation; Convolutional neural network; Computer science; Hyperparameter; Artificial intelligence; Artificial neural network; Pattern recognition (psychology); Identification (biology); Structural engineering; Engineering","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001932758,0.0001792911,0.0001811715,0.00008736655,0.00003386223,0.00003430706,0.00005276333,0.00007804381,0.000008756422],"category_scores_gemma":[0.0000782058,0.000172164,0.00002977904,0.0001349401,0.000005860392,0.00009457454,0.00002489603,0.0003383705,0.000003577456],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000960183,"about_ca_system_score_gemma":0.000002878918,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000110705,"about_ca_topic_score_gemma":8.00296e-7,"domain_scores_codex":[0.9991704,0.00001233981,0.0002628521,0.0001825226,0.0001303039,0.0002416454],"domain_scores_gemma":[0.9997357,0.00006982664,0.00002377098,0.00007741921,0.00001354396,0.00007975113],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003076649,0.000005495711,0.0000134979,0.0005654734,0.000004938192,9.720145e-7,0.0005786633,0.8118199,0.1787869,0.00008682834,6.563874e-7,0.008133627],"study_design_scores_gemma":[0.0003517904,0.0000614907,0.00002696909,0.0001495318,0.000008267402,0.000001277504,0.00006210514,0.9707983,0.02779404,0.0005566119,0.00001708003,0.0001725202],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02327206,0.00002667637,0.9758353,0.00003204668,0.00007335093,0.0002726859,4.626208e-7,0.0002765816,0.0002107974],"genre_scores_gemma":[0.909945,0.000008598859,0.08984556,0.00003506001,0.00005250004,0.00006563788,0.000001819777,0.00004249797,0.000003325888],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8866729,"threshold_uncertainty_score":0.7020642,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008954998106586608,"score_gpt":0.2168958193773785,"score_spread":0.2079408212707918,"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."}}