{"id":"W3181709473","doi":"10.1155/2021/9928073","title":"Short-Term Traffic Flow Prediction: A Method of Combined Deep Learnings","year":2021,"lang":"en","type":"article","venue":"Journal of Advanced Transportation","topic":"Traffic Prediction and Management Techniques","field":"Engineering","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"China Postdoctoral Science Foundation; Shandong University of Science and Technology; Shandong University","keywords":"Deep learning; Traffic flow (computer networking); Computer science; Convolutional neural network; Artificial intelligence; Term (time); Set (abstract data type); Margin (machine learning); Artificial neural network; Field (mathematics); Flow (mathematics); Machine learning; Function (biology); Data mining; Mathematics","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":[0.0001531251,0.0001017263,0.0002280587,0.000139123,0.00002578658,0.000008695786,0.00007192607,0.00005860703,0.00002420302],"category_scores_gemma":[0.000009614819,0.0001068454,0.0001348059,0.0002031303,0.00001423449,0.0003354376,0.000001202945,0.0001965531,4.395339e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003289837,"about_ca_system_score_gemma":0.00001605934,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":1.338412e-7,"about_ca_topic_score_gemma":0.000009624911,"domain_scores_codex":[0.9990121,0.00002269145,0.0005519356,0.00008468747,0.0002296076,0.00009898888],"domain_scores_gemma":[0.9995334,0.00002747372,0.0001192571,0.00008777151,0.0001758802,0.0000562378],"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":[0.00004504037,0.00005294786,0.0002471282,0.0001113057,0.00009500456,0.00003692991,0.0008624298,0.8034004,0.01413739,0.0001057679,0.0002459049,0.1806598],"study_design_scores_gemma":[0.006953588,0.001436835,0.5580024,0.0009982627,0.001058742,0.000242286,0.003708492,0.2954977,0.1100007,0.0004270007,0.0208903,0.0007837997],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2641202,0.000276107,0.7343833,0.000047125,0.0005196708,0.00008341966,0.00001023172,0.0004124687,0.0001474687],"genre_scores_gemma":[0.907778,0.0006044789,0.09147712,0.00001036903,0.0000509877,0.000004458884,0.00004092269,0.00001845183,0.00001518356],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6436578,"threshold_uncertainty_score":0.4357029,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006976266495966334,"score_gpt":0.2395332986481051,"score_spread":0.2325570321521388,"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."}}