{"id":"W2937665960","doi":"10.1109/vtcfall.2018.8690756","title":"Non-Stationary Traffic Flow Prediction Using Deep Learning","year":2018,"lang":"en","type":"article","venue":"","topic":"Traffic Prediction and Management Techniques","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Traffic flow (computer networking); Stochastic gradient descent; Similarity (geometry); Gradient descent; Time domain; Flow (mathematics); Scheme (mathematics); Artificial neural network; Intelligent transportation system; Deep learning; Time series; Artificial intelligence; Series (stratigraphy); Function (biology); Domain (mathematical analysis); Algorithm; Real-time computing; Data mining; Machine learning; Mathematics; Computer vision; Engineering; Image (mathematics); Computer network","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":[0.00007796931,0.0000883313,0.00006342311,0.0001245011,0.0001127092,0.00002489214,0.0000579007,0.00005238174,0.0001436025],"category_scores_gemma":[0.000004071504,0.00009319719,0.00002769869,0.0001475598,0.00002776748,0.0001990992,0.0000146312,0.00009730566,0.00006345394],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005024231,"about_ca_system_score_gemma":0.000003842141,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000276851,"about_ca_topic_score_gemma":0.000009416862,"domain_scores_codex":[0.999501,0.000007436522,0.0001331495,0.0001123062,0.000104526,0.0001415091],"domain_scores_gemma":[0.9998253,0.000006797485,0.00001213378,0.00008542388,0.00003016906,0.00004016755],"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":[0.000006221225,0.00002115985,0.0002078587,0.00003503205,0.00004796724,0.000002545719,0.0005417288,0.7549249,0.002398571,0.0001890281,0.02845429,0.2131707],"study_design_scores_gemma":[0.0001268158,0.00004579443,0.001375878,0.0000116892,0.00001155611,0.000004063032,0.0001229778,0.9808508,0.0006170062,0.000008051693,0.01673835,0.000087004],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1077727,0.00002333345,0.8539049,0.00001246129,0.0005076313,0.0001283251,0.000001571385,0.009880925,0.02776816],"genre_scores_gemma":[0.9791206,0.00004067292,0.0203054,0.00003738348,0.0002312565,0.00001059935,0.00001873413,0.00002330223,0.0002120596],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8713479,"threshold_uncertainty_score":0.3800471,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008645650063349244,"score_gpt":0.2136732147380278,"score_spread":0.2050275646746786,"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."}}