{"id":"W2981207057","doi":"10.1016/j.ssci.2019.104510","title":"A hybrid model to improve the train running time prediction ability during high-speed railway disruptions","year":2019,"lang":"en","type":"article","venue":"Safety Science","topic":"Railway Systems and Energy Efficiency","field":"Engineering","cited_by":56,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"China Scholarship Council; National Natural Science Foundation of China","keywords":"Support vector machine; Benchmark (surveying); Train; Machine learning; Computer science; Predictive modelling; Kalman filter; Artificial intelligence; Data mining; Simulation","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":[0.001000208,0.0001573482,0.0001585528,0.0001088745,0.0004462707,0.00008404265,0.0004992262,0.00003397311,0.00005115731],"category_scores_gemma":[0.00005601296,0.0001179496,0.00006146393,0.0005971737,0.0001492235,0.0004542628,0.00008944525,0.0001581576,0.0002481585],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002481153,"about_ca_system_score_gemma":0.00007147159,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006279873,"about_ca_topic_score_gemma":0.000004855679,"domain_scores_codex":[0.9983401,0.0000151829,0.0003030338,0.0004195251,0.0004320672,0.0004901303],"domain_scores_gemma":[0.9991311,0.0000331257,0.00003325356,0.0005905686,0.00006157358,0.0001503803],"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":[0.000004702373,0.000006636017,0.0001036628,0.00001137596,0.000002403385,2.66977e-7,0.0005194674,0.6629726,0.3353674,0.0004641227,0.00001421107,0.0005331416],"study_design_scores_gemma":[0.0001883836,0.00002930446,0.03256925,0.00002853646,0.000004044035,0.000007009508,0.0000798064,0.9608803,0.005700046,0.0001404453,0.0002136294,0.0001592138],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9810277,0.00001903422,0.01133983,0.0002071156,0.0008099728,0.0004005283,0.00005117826,0.0003025986,0.005842018],"genre_scores_gemma":[0.9985112,0.000002927347,0.0003926464,0.00002379767,0.00009317176,0.00001894075,0.00000288393,0.00001807713,0.0009363808],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3296674,"threshold_uncertainty_score":0.4809846,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005028233187755179,"score_gpt":0.1967299021950694,"score_spread":0.1917016690073143,"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."}}