{"id":"W4226524907","doi":"10.1109/tits.2022.3157056","title":"FedSTN: Graph Representation Driven Federated Learning for Edge Computing Enabled Urban Traffic Flow Prediction","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Intelligent Transportation Systems","topic":"Traffic Prediction and Management Techniques","field":"Engineering","cited_by":166,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"State Key Laboratory of Industrial Control Technology; Natural Science Foundation of Hebei Province; National Natural Science Foundation of China","keywords":"Computer science; Intelligent transportation system; Graph; Enhanced Data Rates for GSM Evolution; Data mining; Deep learning; Traffic flow (computer networking); Edge computing; Smart city; Traffic congestion; Distributed computing; Artificial intelligence; Computer network; Theoretical computer science; Computer security; Engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003410559,0.0003065784,0.0003159044,0.0005947085,0.001049559,0.0001224184,0.0001641194,0.0001135137,0.00006525614],"category_scores_gemma":[0.00000246923,0.0003759525,0.0002576527,0.0007020966,0.00002813869,0.0002516443,5.636398e-7,0.0004964083,0.00001100576],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002892368,"about_ca_system_score_gemma":0.0000241904,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003448494,"about_ca_topic_score_gemma":0.00005765307,"domain_scores_codex":[0.9977403,0.0001417614,0.0008462978,0.0004566551,0.0004674978,0.000347486],"domain_scores_gemma":[0.9993253,0.0001136953,0.0001335468,0.0001947288,0.000123032,0.0001097412],"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":[0.0001025756,0.00013072,0.00004618807,0.0001644866,0.0002041018,0.000003628682,0.002198539,0.9758527,0.0008529028,0.00006620869,0.004959081,0.01541882],"study_design_scores_gemma":[0.0007543709,0.0003032474,0.0001338066,0.00006528793,0.0001268798,0.000006652216,0.003350694,0.9792391,0.004089382,0.000002823695,0.01161706,0.0003107069],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04705172,0.00008264847,0.9406934,0.00002550961,0.003283522,0.001785632,0.0002522614,0.006625807,0.0001994921],"genre_scores_gemma":[0.996793,0.0001192697,0.000517278,0.00002540309,0.0001136892,0.001355743,0.0006481889,0.00009439588,0.0003329989],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9497413,"threshold_uncertainty_score":0.9998692,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01878456535698501,"score_gpt":0.2345109424485296,"score_spread":0.2157263770915446,"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."}}