{"id":"W2885948806","doi":"10.3390/met8080612","title":"Pattern Deep Region Learning for Crack Detection in Thermography Diagnosis System","year":2018,"lang":"en","type":"article","venue":"Metals","topic":"Thermography and Photoacoustic Techniques","field":"Engineering","cited_by":42,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"Engineering and Physical Sciences Research Council; National Natural Science Foundation of China","keywords":"Thermography; Deep learning; Artificial intelligence; Artificial neural network; Computer science; Pattern recognition (psychology); Eddy-current testing; Convolution (computer science); Convolutional neural network; Range (aeronautics); Machine learning; Engineering; Eddy current; Infrared; Aerospace engineering","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":[0.000318876,0.0003377474,0.0003956073,0.0002548173,0.000175568,0.0002981253,0.0007879914,0.0006224325,0.001757893],"category_scores_gemma":[0.0006512897,0.0002220733,0.0002847071,0.000229603,0.0002009639,0.000691495,0.0004871905,0.0005743584,0.0004203908],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003611751,"about_ca_system_score_gemma":0.0004792374,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001730257,"about_ca_topic_score_gemma":0.002722583,"domain_scores_codex":[0.9998405,0.0000226859,0.000009681634,0.00005452969,0.00004544765,0.00002717014],"domain_scores_gemma":[0.9997997,0.00005120189,0.00002619559,0.00002685064,0.00008160725,0.00001449246],"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":[0.0005000667,0.0002413839,0.002768837,0.0001157443,0.0000656012,0.0001777327,0.00008435162,0.1782306,0.1327415,0.003894743,0.003287101,0.6778924],"study_design_scores_gemma":[0.000005684406,0.00005088033,0.0003730194,0.000002767707,0.000008283748,0.00003649838,0.000004162721,0.9849696,0.01356641,0.0006062411,0.0003719796,0.00000449752],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06112222,0.0003390002,0.9357933,0.0001705843,0.00003687511,0.00004138408,0.00008538176,0.001177447,0.00123381],"genre_scores_gemma":[0.7974246,0.0002051049,0.197697,0.0001468502,0.00002793212,0.00006871908,0.0001682535,0.00004775737,0.004213721],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001757893,"threshold_uncertainty_score":0.005880713,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01191375600335949,"score_gpt":0.2165921694979258,"score_spread":0.2046784134945664,"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."}}