{"id":"W4380029284","doi":"10.1177/03611981231172958","title":"Real-Time Intersection Turning Movement Flow Forecasting Using a Parallel Bidirectional Long Short-Term Memory Neural Network Model","year":2023,"lang":"en","type":"article","venue":"Transportation Research Record Journal of the Transportation Research Board","topic":"Traffic Prediction and Management Techniques","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Robustness (evolution); Artificial neural network; Intersection (aeronautics); Perceptron; Traffic flow (computer networking); Long short term memory; Term (time); Artificial intelligence; Recurrent neural network; Machine learning; Simulation; Engineering; Transport engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003655396,0.0002828478,0.0003791105,0.001318796,0.000673042,0.0001543718,0.0006076759,0.0001756762,0.00008398151],"category_scores_gemma":[0.00004511594,0.000250415,0.0003727638,0.002359565,0.0002110003,0.0007727414,0.00001457434,0.001700718,0.00001205145],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004810741,"about_ca_system_score_gemma":0.0001720238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000771106,"about_ca_topic_score_gemma":0.004803793,"domain_scores_codex":[0.9945855,0.000435685,0.001213108,0.0003546476,0.002424536,0.0009865598],"domain_scores_gemma":[0.9978698,0.0003390342,0.000180324,0.0003113579,0.001014771,0.0002846452],"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":[0.0003112022,0.0000460094,0.01564817,0.0001870166,0.0001781938,0.00009397798,0.001051334,0.9493064,0.009325184,0.00009888881,0.01388501,0.009868606],"study_design_scores_gemma":[0.0005169255,0.0001519401,0.1636073,0.0003762259,0.00005036901,0.000001265274,0.0004582186,0.8335246,0.0004739664,0.0005070824,0.0001373055,0.000194844],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9400023,0.00005143152,0.05676967,0.0002354926,0.0008772353,0.0008564127,0.00003088752,0.0008584581,0.0003180622],"genre_scores_gemma":[0.9904451,0.0009386897,0.007522298,0.00001695191,0.0004068125,0.0001000311,0.00005447853,0.0001001195,0.0004154829],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1479591,"threshold_uncertainty_score":0.9999948,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09728586684468411,"score_gpt":0.3413848727993938,"score_spread":0.2440990059547097,"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."}}