{"id":"W4391097131","doi":"10.1109/jiot.2024.3356554","title":"Sparse Mobile Crowdsensing for Cost-Effective Traffic State Estimation With Spatio–Temporal Transformer Graph Neural Network","year":2024,"lang":"en","type":"article","venue":"IEEE Internet of Things Journal","topic":"Traffic Prediction and Management Techniques","field":"Engineering","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Science Foundation of Jiangsu Province for Distinguished Young Scholars; National Natural Science Foundation of China","keywords":"Computer science; Data mining; Artificial neural network; Graph; Transformer; Real-time computing; Artificial intelligence; Machine learning","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004687998,0.0007523549,0.0006463311,0.0005338411,0.0002843956,0.0005267632,0.001175774,0.0006244093,0.0008501784],"category_scores_gemma":[0.00206565,0.0003090084,0.0004140847,0.0007523889,0.0004553689,0.001178975,0.0009855297,0.0008704699,0.0001701869],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008277044,"about_ca_system_score_gemma":0.0007078109,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01461197,"about_ca_topic_score_gemma":0.01408843,"domain_scores_codex":[0.9997484,0.00005531928,0.0000126419,0.00007495035,0.00006723703,0.00004141626],"domain_scores_gemma":[0.999553,0.0002190845,0.00004962313,0.00003838266,0.0001161979,0.00002370354],"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":[0.000139647,0.00006698024,0.002313928,0.00007212129,0.00004614161,0.00009482914,0.00006613931,0.8839539,0.003305288,0.00636766,0.001792419,0.101781],"study_design_scores_gemma":[0.000001634145,0.00000500073,0.0000811504,0.000001290167,0.000002354277,0.000005133458,0.000003949721,0.9981177,0.0002621424,0.001409307,0.0001086126,0.000001680243],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0474415,0.0003663694,0.9486104,0.0004089288,0.00008355854,0.00004405578,0.0002430727,0.0006681277,0.002133929],"genre_scores_gemma":[0.940051,0.0002585235,0.05715934,0.0001657194,0.0000545657,0.00006371752,0.0003642387,0.00003478254,0.001848126],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01461197,"threshold_uncertainty_score":0.02905381,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009397141766397334,"score_gpt":0.2413627548481554,"score_spread":0.231965613081758,"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."}}