{"id":"W4307171308","doi":"10.3390/su142113788","title":"Hyperparameter Sensitivity Analysis of Deep Learning-Based Pipe Burst Detection Model for Multiregional Water Supply Networks","year":2022,"lang":"en","type":"article","venue":"Sustainability","topic":"Water Systems and Optimization","field":"Engineering","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Ministry of Environment - Saskatchewan","keywords":"Hyperparameter; Sensitivity (control systems); Hyperparameter optimization; Computer science; Artificial neural network; Artificial intelligence; Deep learning; Data set; Machine learning; Set (abstract data type); Activation function; Rectifier (neural networks); Function (biology); Pattern recognition (psychology); Data mining; Recurrent neural network; Engineering; Support vector machine","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006994798,0.0001347029,0.0002839068,0.0002055678,0.0001972308,0.00001738949,0.00005870315,0.00006746605,0.00002027389],"category_scores_gemma":[0.00006742255,0.0001239468,0.0002381221,0.0003488433,0.00003723535,0.0000812406,0.00003974892,0.0001683823,1.500389e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006022869,"about_ca_system_score_gemma":0.00002309425,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001870175,"about_ca_topic_score_gemma":0.0004422046,"domain_scores_codex":[0.9988731,0.0001643318,0.0002735167,0.0002439741,0.0001606055,0.0002845286],"domain_scores_gemma":[0.9992338,0.0001048953,0.00004308991,0.000232721,0.0003423273,0.00004321314],"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":[0.00008650115,0.00004568881,0.007038264,0.000115615,0.0001355898,0.000001246582,0.0005029472,0.9908843,0.0001218649,0.000006986735,0.00001191272,0.001049056],"study_design_scores_gemma":[0.0002863407,0.000056234,0.003811173,9.461575e-7,0.0002010077,7.253947e-7,0.0001926659,0.9939952,0.001027,0.00008151736,0.0001998799,0.0001472899],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3824851,0.00001243949,0.616984,0.00004260103,0.00007281197,0.0003040111,0.00001520763,0.00007978909,0.000004058306],"genre_scores_gemma":[0.9988552,3.752797e-7,0.0005755867,0.00001240095,0.00002526335,0.0002013134,0.0002064846,0.00002383267,0.00009952586],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6164085,"threshold_uncertainty_score":0.5054404,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00589998513152155,"score_gpt":0.2000076239397083,"score_spread":0.1941076388081867,"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."}}