{"id":"W4247115639","doi":"10.1051/matecconf/201714902025","title":"Neural networks and principle component analysis approaches to predict pile capacity in sand","year":2018,"lang":"en","type":"article","venue":"MATEC Web of Conferences","topic":"Geotechnical Engineering and Soil Mechanics","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Artificial neural network; Pile; Perceptron; Bearing capacity; Regularization (linguistics); Computer science; Test data; Generalization; Component (thermodynamics); Displacement (psychology); Artificial intelligence; Structural engineering; Engineering; Algorithm; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001674194,0.0001118558,0.0002670856,0.0001623224,0.00001878945,0.00002362307,0.0001222086,0.00007778116,0.00002250572],"category_scores_gemma":[0.00001530539,0.0001013996,0.00003200494,0.0003428736,0.00004943553,0.00003270322,0.00004424945,0.0001123015,0.000001252146],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001066391,"about_ca_system_score_gemma":0.00001149374,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001014422,"about_ca_topic_score_gemma":0.0002006978,"domain_scores_codex":[0.9993576,0.00001529407,0.0002076049,0.0001365496,0.0001010725,0.0001819164],"domain_scores_gemma":[0.9997079,0.00002949289,0.00002008751,0.000147571,0.00001920907,0.00007567908],"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":[0.00001121856,0.00001957782,0.009199911,0.00007370127,0.0001010416,9.962745e-7,0.0001394886,0.984066,0.0004318921,0.003407661,0.00001562192,0.002532889],"study_design_scores_gemma":[0.000101833,0.0000646663,0.03687718,0.0000189269,0.00003189829,7.120242e-7,0.00002450007,0.9613336,0.001061179,0.0001013318,0.0002787689,0.0001053764],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9775347,0.00006962441,0.02072815,0.00002696472,0.00009434747,0.00009547204,0.00000805172,0.0001227784,0.001319906],"genre_scores_gemma":[0.9995304,0.00001757802,0.0003876057,0.000005204895,0.00002829447,0.00001334855,0.000004054401,0.000007404752,0.000006089817],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02767727,"threshold_uncertainty_score":0.4134957,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05854784612663082,"score_gpt":0.2083609563624351,"score_spread":0.1498131102358043,"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."}}