{"id":"W3145694833","doi":"10.1016/j.eswa.2021.114996","title":"Modeling train timetables as images: A cost-sensitive deep learning framework for delay propagation pattern recognition","year":2021,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Railway Engineering and Dynamics","field":"Engineering","cited_by":51,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Computer science; Deep learning; Component (thermodynamics); Convolutional neural network; Artificial intelligence; Backpropagation; Data modeling; Artificial neural network; Machine learning; Pattern recognition (psychology); Database","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003410428,0.0007534088,0.0006633312,0.0005119484,0.0001743512,0.0007416172,0.001694845,0.001024866,0.002268896],"category_scores_gemma":[0.001101918,0.0004911499,0.0005055867,0.0007660004,0.0003044568,0.0009069282,0.0006655371,0.001585911,0.0007053541],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008577711,"about_ca_system_score_gemma":0.0009742419,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01681138,"about_ca_topic_score_gemma":0.01744141,"domain_scores_codex":[0.9998636,0.00001606783,0.000005981733,0.00005236799,0.00003077534,0.00003121077],"domain_scores_gemma":[0.99975,0.00008825007,0.00003626535,0.00003437164,0.00006808533,0.000023169],"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":[0.0001537919,0.0001066069,0.0009576232,0.00005811905,0.00004990566,0.00006054299,0.00002803354,0.7804666,0.006827901,0.00666491,0.003966824,0.2006593],"study_design_scores_gemma":[0.00000150126,0.000006067395,0.00006314236,0.000001890913,0.000003149732,0.000004428772,0.000001455239,0.9978533,0.0006661197,0.001223612,0.0001733304,0.000001916242],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03340118,0.0004865683,0.9629164,0.0002887142,0.00009888261,0.00002759448,0.0004998555,0.00113365,0.001147149],"genre_scores_gemma":[0.8163521,0.0006582015,0.1723586,0.0002674031,0.0001189341,0.00009037863,0.001421636,0.0001937646,0.00853894],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01681138,"threshold_uncertainty_score":0.03342706,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01272543052202176,"score_gpt":0.234794696189414,"score_spread":0.2220692656673922,"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."}}