{"id":"W3114177701","doi":"10.3390/app11010013","title":"Developing Machine Learning-Based Models for Railway Inspection","year":2020,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Railway Engineering and Dynamics","field":"Engineering","cited_by":64,"is_retracted":false,"has_abstract":true,"ca_institutions":"Defence Research and Development Canada; National Research Council Canada","funders":"Transport Canada","keywords":"Convolutional neural network; Computer science; Software deployment; Deep learning; Artificial intelligence; Preprocessor; Feature engineering; Machine learning; Reliability engineering; Engineering","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001388422,0.0001071004,0.0001060906,0.00005651416,0.000177083,0.00005164267,0.0001506192,0.00003983441,0.000002933531],"category_scores_gemma":[0.00001922506,0.0001024618,0.00002893427,0.0003501733,0.00004665043,0.00008285621,0.00001079674,0.0001016548,0.00001011368],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003307421,"about_ca_system_score_gemma":0.0000300997,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002564293,"about_ca_topic_score_gemma":0.000004217093,"domain_scores_codex":[0.9993696,0.000002928226,0.0001171721,0.0001805765,0.0001260768,0.000203626],"domain_scores_gemma":[0.9998099,0.00005362799,0.0000159308,0.00004796263,0.00001303942,0.00005950831],"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":[0.000003078069,0.000001473727,0.00002072123,0.0000352504,0.000003716693,1.372959e-7,0.0001415814,0.982141,0.001669295,0.01484486,0.00007128475,0.001067581],"study_design_scores_gemma":[0.0001681191,0.00003110354,0.00001696249,0.000005258084,0.000003213246,3.204835e-7,0.00004909296,0.992894,0.003228925,0.0009733539,0.002479429,0.0001502245],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01509148,0.00009128214,0.9793743,0.0003050595,0.0001357654,0.0001384209,0.000004988852,0.001058257,0.003800419],"genre_scores_gemma":[0.9666983,0.000009387563,0.03300649,0.0001429261,0.00006782929,0.00003844831,0.000009959757,0.00001810137,0.000008524789],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9516069,"threshold_uncertainty_score":0.4178272,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02879842776610042,"score_gpt":0.2220033309385834,"score_spread":0.193204903172483,"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."}}