{"id":"W2997073788","doi":"10.1016/j.ins.2019.12.053","title":"A deep learning approach for multi-attribute data: A study of train delay prediction in railway systems","year":2019,"lang":"en","type":"article","venue":"Information Sciences","topic":"Traffic Prediction and Management Techniques","field":"Engineering","cited_by":126,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"China Scholarship Council; Southwest Jiaotong University","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Mean squared error; Deep learning; Artificial neural network; Trajectory; Time series; Series (stratigraphy); State (computer science); Machine learning; Recurrent neural network; Pattern recognition (psychology); Data mining; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002894145,0.0005075016,0.0007523549,0.0006599347,0.0004149202,0.0009127181,0.001284359,0.001040174,0.0009576086],"category_scores_gemma":[0.009123275,0.0004240551,0.0005416813,0.001416396,0.000658437,0.002074936,0.0006726803,0.001973308,0.00007918092],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001385634,"about_ca_system_score_gemma":0.001172003,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02814593,"about_ca_topic_score_gemma":0.015728,"domain_scores_codex":[0.9994857,0.0002245889,0.00002461916,0.000105082,0.00008170316,0.00007822952],"domain_scores_gemma":[0.9905771,0.008184978,0.0003627179,0.0002364398,0.0004670734,0.0001717119],"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":[0.0001442087,0.0001876291,0.01309098,0.00006996361,0.00008855698,0.00009086713,0.0001299864,0.9420993,0.0004744879,0.009247007,0.0008364668,0.03354054],"study_design_scores_gemma":[0.00000207861,0.00001043458,0.0007023741,0.000002542811,0.000003994775,0.000003653882,0.00001332137,0.9973997,0.00006872156,0.001742678,0.00004874687,0.000001875058],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7964038,0.001471509,0.1977889,0.001955862,0.00006787237,0.00003184972,0.0002930167,0.0001275823,0.001859649],"genre_scores_gemma":[0.9868606,0.0002748451,0.0113851,0.0000484717,0.00003256816,0.00001016566,0.0001441338,0.00001390722,0.001230232],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02814593,"threshold_uncertainty_score":0.05596423,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05523602894779469,"score_gpt":0.2810159262967556,"score_spread":0.2257798973489609,"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."}}