{"id":"W4412430672","doi":"10.1016/j.ndteint.2025.103481","title":"U-NET autoencoder for amplitude recovery on binarized Full Matrix Captures","year":2025,"lang":"en","type":"article","venue":"NDT & E International","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Society of Nephrology; École de Technologie Supérieure","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Autoencoder; Net (polyhedron); Matrix (chemical analysis); Amplitude; Computer science; Artificial intelligence; Pattern recognition (psychology); Mathematics; Materials science; Artificial neural network; Physics; Composite material; Geometry; Optics","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":[0.0009398234,0.0008833862,0.0006233402,0.0004377089,0.000228452,0.0004800242,0.0007838914,0.0009403555,0.001629357],"category_scores_gemma":[0.001882609,0.0003835336,0.0005743719,0.000323402,0.0004247352,0.0006734494,0.0007374433,0.001168196,0.0005498703],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005433523,"about_ca_system_score_gemma":0.0007617624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008330766,"about_ca_topic_score_gemma":0.006762938,"domain_scores_codex":[0.9997662,0.00005065186,0.00001617585,0.0000688414,0.000058033,0.00004009781],"domain_scores_gemma":[0.999437,0.0002924642,0.0000405081,0.00004045649,0.0001702312,0.00001925545],"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":[0.0002512024,0.0001144971,0.000966001,0.0001156812,0.00007953298,0.0001252411,0.0001062575,0.6541607,0.01591937,0.00347279,0.002071009,0.3226178],"study_design_scores_gemma":[0.00000198364,0.00002007192,0.0001035492,0.000004582359,0.000003808311,0.000007608495,0.000004363545,0.9979977,0.001389921,0.0002876293,0.0001759154,0.000002916933],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04268198,0.0005911717,0.9535298,0.0001553081,0.00007852398,0.00007380507,0.0000916816,0.00113331,0.001664306],"genre_scores_gemma":[0.6740776,0.0005663878,0.3158995,0.0003200656,0.00006725768,0.0002694451,0.0007296489,0.0001347222,0.007935419],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008330766,"threshold_uncertainty_score":0.01656455,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01915156693666172,"score_gpt":0.3387696673826244,"score_spread":0.3196181004459627,"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."}}