{"id":"W3083552202","doi":"10.1007/s12652-020-02507-9","title":"Predicting irregularities in arrival times for transit buses with recurrent neural networks using GPS coordinates and weather data","year":2020,"lang":"en","type":"article","venue":"Journal of Ambient Intelligence and Humanized Computing","topic":"Traffic Prediction and Management Techniques","field":"Engineering","cited_by":39,"is_retracted":false,"has_abstract":false,"ca_institutions":"Fleming College; McGill University; Trent University","funders":"","keywords":"Computer science; Autoregressive integrated moving average; Public transport; Global Positioning System; Artificial neural network; Metropolitan area; Real-time computing; Support vector machine; Recurrent neural network; Automatic vehicle location; Artificial intelligence; Operations research; Transport engineering; Time series; Machine learning; Telecommunications; Geography","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":[0.0002614992,0.0001327117,0.0002401864,0.000101863,0.00008886812,0.0001100884,0.0001798052,0.00003484066,0.000002449641],"category_scores_gemma":[0.00002110698,0.0001153135,0.00002726757,0.00009546406,0.00004990278,0.0002780491,0.00007100387,0.0002111373,3.391104e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000172636,"about_ca_system_score_gemma":0.000007910907,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006348291,"about_ca_topic_score_gemma":0.0000135502,"domain_scores_codex":[0.9991665,0.00001974012,0.0003836535,0.0001505385,0.0001090321,0.0001705746],"domain_scores_gemma":[0.9996148,0.00008718904,0.0001083626,0.00007489052,0.00004950084,0.00006519706],"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":[0.0003691562,0.00008392587,0.008187695,0.0007283901,0.0003102836,0.00005969651,0.007831438,0.7928535,0.000589941,0.001338768,0.00102834,0.1866188],"study_design_scores_gemma":[0.0003119249,0.0002438004,0.0003078152,0.0003864914,0.00005543591,0.00004797973,0.00131099,0.9967467,0.0002061564,0.00004906525,0.0002145923,0.0001191098],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3667431,0.001234121,0.6314774,0.00009652282,0.000125546,0.000153382,0.000003056011,0.0001500253,0.00001682598],"genre_scores_gemma":[0.9922277,0.0003339312,0.00716587,0.0000718821,0.0001776113,8.0326e-7,0.000003117941,0.00001813107,9.971462e-7],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6254845,"threshold_uncertainty_score":0.4702348,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05399517428102669,"score_gpt":0.263679105524231,"score_spread":0.2096839312432043,"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."}}