{"id":"W4390909145","doi":"10.1080/10589759.2024.2304719","title":"A novel approach for one-step defect detection and depth estimation using sequenced thermal signal encoding","year":2024,"lang":"en","type":"article","venue":"Nondestructive Testing And Evaluation","topic":"Thermography and Photoacoustic Techniques","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"National Natural Science Foundation of China","keywords":"Robustness (evolution); Encoding (memory); Computer science; Convolutional neural network; Artificial neural network; Artificial intelligence; Pattern recognition (psychology); SIGNAL (programming language); Thermography; Convolution (computer science); Recurrent neural network; Feedforward neural network; Thermal infrared; Algorithm; Infrared","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":[0.0003107977,0.0006669572,0.0003528642,0.0007303617,0.00011563,0.0004041388,0.0008764221,0.0005622743,0.0009601219],"category_scores_gemma":[0.0008512159,0.000289907,0.0003211453,0.0003955638,0.0002888707,0.001031942,0.0006144371,0.000532635,0.0003267643],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003864112,"about_ca_system_score_gemma":0.0005600477,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001175397,"about_ca_topic_score_gemma":0.003018528,"domain_scores_codex":[0.999752,0.00002268662,0.00001220585,0.00005928397,0.0001334762,0.00002038821],"domain_scores_gemma":[0.9996064,0.00008825255,0.00006809965,0.00006679242,0.0001490099,0.00002154181],"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":[0.0002347107,0.000139728,0.003043949,0.0002417997,0.00006610881,0.0001533122,0.00009435575,0.03716223,0.4357942,0.002397047,0.0008740422,0.5197985],"study_design_scores_gemma":[0.00001228515,0.0001951758,0.002271432,0.00001963025,0.00004488543,0.0006512552,0.00002960183,0.7836951,0.2096644,0.001040887,0.002340008,0.00003525625],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03722652,0.0002649065,0.9603415,0.00007362378,0.00004511343,0.00004643889,0.00009101959,0.000811542,0.001099346],"genre_scores_gemma":[0.439218,0.0003127625,0.5571542,0.00008905709,0.0000312429,0.00005986684,0.0001965826,0.00006305561,0.002875193],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001175397,"threshold_uncertainty_score":0.003211915,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08671326124073031,"score_gpt":0.3033066952654741,"score_spread":0.2165934340247438,"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."}}