{"id":"W4399469643","doi":"10.1016/j.engappai.2024.108685","title":"A denoising autoencoder based on U-Net and bidirectional long short-term memory for multi-level random telegraph signal analysis","year":2024,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Industry Canada; Ontario Ministry of Research, Innovation and Science; Government of Canada","keywords":"Noise reduction; Computer science; Noise (video); White noise; Autoencoder; Additive white Gaussian noise; SIGNAL (programming language); Encoder; Term (time); Algorithm; Speech recognition; Artificial intelligence; Pattern recognition (psychology); Telecommunications; Deep learning","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":[0.0008819288,0.000872087,0.000824358,0.0004066686,0.0002569866,0.0005774243,0.000984975,0.001020402,0.0009490498],"category_scores_gemma":[0.001547621,0.0004256155,0.0007725584,0.0003612601,0.000518427,0.0007732563,0.0007712204,0.001540813,0.0005193571],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005490251,"about_ca_system_score_gemma":0.0007950804,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006563515,"about_ca_topic_score_gemma":0.007805191,"domain_scores_codex":[0.9997156,0.00005203329,0.00002024937,0.00008889024,0.00007886309,0.00004423912],"domain_scores_gemma":[0.9995902,0.0001609181,0.00004759856,0.00003256429,0.0001458207,0.00002292861],"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":[0.0001579259,0.0001024992,0.001520604,0.0001236112,0.0001224799,0.0001349407,0.0001001721,0.7748264,0.01852027,0.005949304,0.002110926,0.1963308],"study_design_scores_gemma":[0.000001748622,0.00001487628,0.00008733539,0.000004720937,0.000006678943,0.00000932508,0.000003061105,0.9974711,0.001650537,0.0005297431,0.0002163935,0.000004386922],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0182327,0.0004973441,0.9794034,0.0001400954,0.00005598926,0.00002483495,0.00006541708,0.0006388326,0.0009414173],"genre_scores_gemma":[0.6405467,0.000815734,0.3482352,0.0004969017,0.00009624183,0.0002139868,0.000744505,0.0001979872,0.008652795],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006563515,"threshold_uncertainty_score":0.01305062,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05688728540563749,"score_gpt":0.3270787243486134,"score_spread":0.2701914389429759,"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."}}