{"id":"W2914182690","doi":"10.1155/2019/8392592","title":"ST-LSTM: A Deep Learning Approach Combined Spatio-Temporal Features for Short-Term Forecast in Rail Transit","year":2019,"lang":"en","type":"article","venue":"Journal of Advanced Transportation","topic":"Traffic Prediction and Management Techniques","field":"Engineering","cited_by":75,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Chongqing Science and Technology Commission","keywords":"Computer science; Long short term memory; Term (time); Urban rail transit; Deep learning; Process (computing); Artificial intelligence; Rail transit; Machine learning; Data mining; Recurrent neural network; Artificial neural network; Transport engineering; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001694844,0.0001333137,0.0002433565,0.0002362205,0.00002350787,0.00001593651,0.00009302897,0.00007319502,0.00001022684],"category_scores_gemma":[0.000003989164,0.0001331316,0.0001191318,0.0001460335,0.000009729933,0.0004464664,7.429278e-7,0.0002577954,3.634962e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005326942,"about_ca_system_score_gemma":0.000008946578,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000125652,"about_ca_topic_score_gemma":0.00008803172,"domain_scores_codex":[0.9991109,0.000009926584,0.0004418395,0.0001081892,0.0001744344,0.0001547527],"domain_scores_gemma":[0.9997019,0.00002179373,0.00009880314,0.00006530583,0.00006573378,0.00004650846],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.0004178311,0.00007793618,0.004822151,0.0002837931,0.00006265677,0.00001017879,0.001851556,0.9562211,0.001983801,0.0006177901,0.000225303,0.03342592],"study_design_scores_gemma":[0.01616659,0.002552327,0.7274782,0.0007306759,0.0003200436,0.00004368726,0.003502249,0.2299018,0.005290146,0.001500043,0.0113186,0.001195641],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5673041,0.000182744,0.4311993,0.00002555584,0.0002795592,0.0004811081,0.000009262686,0.000294735,0.0002235861],"genre_scores_gemma":[0.9817232,0.0001203034,0.01779965,0.00001403647,0.00004191432,0.00002463988,0.0002181529,0.00003026339,0.00002779471],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7263193,"threshold_uncertainty_score":0.5428948,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007277318026712274,"score_gpt":0.2200938958730618,"score_spread":0.2128165778463496,"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."}}