{"id":"W3021470593","doi":"10.1016/j.conbuildmat.2020.119397","title":"A cost effective solution for pavement crack inspection using cameras and deep neural networks","year":2020,"lang":"en","type":"article","venue":"Construction and Building Materials","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":242,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Discriminator; Computer science; Feature (linguistics); Convolutional neural network; Deconvolution; Artificial neural network; Artificial intelligence; Layer (electronics); Generator (circuit theory); Deep learning; Computer vision; Pattern recognition (psychology); Algorithm; Materials science","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":[0.0002301505,0.001179067,0.0007578293,0.0006288515,0.0003080387,0.000575937,0.001347614,0.00137931,0.005749257],"category_scores_gemma":[0.0008236357,0.0005051377,0.0006929368,0.0006574419,0.0002509067,0.001446525,0.001052133,0.001209994,0.001388433],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006538788,"about_ca_system_score_gemma":0.001081853,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008139632,"about_ca_topic_score_gemma":0.01539727,"domain_scores_codex":[0.9996626,0.00003335029,0.00001247048,0.00009190405,0.0001388286,0.00006081182],"domain_scores_gemma":[0.9997315,0.00005507599,0.00002475939,0.00004798191,0.0001232803,0.0000174846],"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":[0.0002790125,0.0002135493,0.001011202,0.0001738077,0.0001246133,0.0001651914,0.00003248797,0.124634,0.03384255,0.004068727,0.01379775,0.8216571],"study_design_scores_gemma":[0.00001426746,0.00005915227,0.000589318,0.00001185669,0.00003076604,0.00007626644,0.00001912319,0.9873633,0.00667434,0.002818173,0.002332971,0.00001043238],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02019086,0.0007533598,0.9717775,0.0004060875,0.0001705743,0.00007345657,0.0003262325,0.002428463,0.003873454],"genre_scores_gemma":[0.4021035,0.0006685245,0.5819079,0.0003983323,0.0001407154,0.0001569001,0.0009586973,0.0001721244,0.01349321],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008139632,"threshold_uncertainty_score":0.01923317,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01605780200932707,"score_gpt":0.2422186045702031,"score_spread":0.226160802560876,"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."}}