{"id":"W4224991288","doi":"10.3390/s22093348","title":"Applying Hybrid Lstm-Gru Model Based on Heterogeneous Data Sources for Traffic Speed Prediction in Urban Areas","year":2022,"lang":"en","type":"article","venue":"Sensors","topic":"Traffic Prediction and Management Techniques","field":"Engineering","cited_by":83,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Higher Education Commision, Pakistan","keywords":"Computer science; Convolutional neural network; Mean squared error; Geospatial analysis; Pipeline (software); Feature (linguistics); Data mining; Mean absolute percentage error; Data pre-processing; Deep learning; Variety (cybernetics); Feature engineering; Artificial intelligence; Preprocessor; Intelligent transportation system; Machine learning; Artificial neural network; Engineering; Geography; Cartography","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":[0.0002265781,0.0001548332,0.0001425677,0.0002757587,0.0001143444,0.00002689934,0.0002828429,0.00003077873,0.00001762312],"category_scores_gemma":[0.00001309263,0.0001833782,0.00005174251,0.0001360283,0.00001408915,0.00006777596,0.00006938702,0.0001777208,0.000003336077],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001275074,"about_ca_system_score_gemma":0.00001054096,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004235637,"about_ca_topic_score_gemma":0.000009071135,"domain_scores_codex":[0.9989693,0.00002956552,0.0002194684,0.0003176172,0.0002223031,0.0002417867],"domain_scores_gemma":[0.9994234,0.00003560699,0.00002998741,0.000453909,0.000007972866,0.00004915694],"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":[0.00004223913,0.00005321991,0.00004229683,0.00003699549,0.00001660218,0.000008332831,0.00008152314,0.9731573,0.0001441465,0.00002032761,0.01974212,0.006654863],"study_design_scores_gemma":[0.0005073044,0.00006915814,0.00003504574,0.00001401615,0.00001895091,0.000004782696,0.000090154,0.9792468,0.0005354239,0.00001191395,0.01931393,0.000152524],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.921788,0.00007273193,0.06659465,0.00009217231,0.0004805068,0.001827677,0.001005115,0.006731205,0.001407996],"genre_scores_gemma":[0.9980285,0.000009399062,0.0008009738,0.0001334972,0.00006377791,0.0002901357,0.0005083993,0.00005222189,0.0001131256],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07624052,"threshold_uncertainty_score":0.7477946,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02380245126092681,"score_gpt":0.2260359144035185,"score_spread":0.2022334631425917,"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."}}