{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001220078,0.0001907552,0.0002101124,0.00007372504,0.0001748284,0.0001075765,0.00006484206,0.0001261913,0.000005348174],"category_scores_gemma":[0.00005070053,0.0001918916,0.00005222398,0.0002469324,0.00001373549,0.0001318747,0.000008169125,0.0002029242,0.00004254812],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001022701,"about_ca_system_score_gemma":0.00003085401,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000405694,"about_ca_topic_score_gemma":0.00001347567,"domain_scores_codex":[0.9990328,0.00003082308,0.0002634054,0.000282131,0.0001389148,0.0002519405],"domain_scores_gemma":[0.9992541,0.0001336811,0.00004152145,0.0002279141,0.0002564281,0.00008632013],"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":[0.00000525733,0.00001925419,0.000004858188,0.0001211544,0.00006652002,0.000003063627,0.0008750259,0.9640376,0.003001147,0.0004947642,0.00002142128,0.03134992],"study_design_scores_gemma":[0.0002142447,0.00002317019,0.000004100671,0.0002073405,0.00002612081,0.0000698186,0.001754726,0.9939719,0.001588049,0.0002022759,0.001670612,0.000267588],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003676528,0.001126201,0.9927939,0.00004578028,0.0001093019,0.001149453,0.00005492414,0.0005758042,0.0004681471],"genre_scores_gemma":[0.9263615,0.000133826,0.06641363,0.00003073876,0.0003176301,0.005833839,0.000690731,0.0001049619,0.0001131447],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9263802,"threshold_uncertainty_score":0.7825114,"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."}}