{"id":"W4379745810","doi":"10.1109/lnet.2023.3283936","title":"Heterogeneous GNN-RL-Based Task Offloading for UAV-Aided Smart Agriculture","year":2023,"lang":"en","type":"article","venue":"IEEE Networking Letters","topic":"UAV Applications and Optimization","field":"Engineering","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Nokia","keywords":"Computer science; Reinforcement learning; Robustness (evolution); Internet of Things; Task (project management); Edge computing; Distributed computing; Network topology; Enhanced Data Rates for GSM Evolution; Embedded system; Real-time computing; Computer network; Artificial intelligence; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001042711,0.0001755017,0.0001497228,0.00009445652,0.0001588438,0.0000741815,0.0001435107,0.00009149981,0.000005534931],"category_scores_gemma":[0.000003795944,0.000173713,0.0001003646,0.0005022535,0.00001666632,0.0000536719,0.000008947656,0.0001082639,0.00004338978],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007561811,"about_ca_system_score_gemma":0.000005425796,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005839594,"about_ca_topic_score_gemma":0.00001314983,"domain_scores_codex":[0.9990635,0.00001276655,0.0002027999,0.0002238623,0.0001116921,0.0003853771],"domain_scores_gemma":[0.9995704,0.00009930159,0.00004059857,0.0002057756,0.00002460562,0.0000593721],"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":[0.000003544439,0.000003371231,0.0001636883,0.00002956299,0.00002781821,0.000003151625,0.00004408921,0.8791232,0.03451408,0.000006054885,0.08355249,0.002529002],"study_design_scores_gemma":[0.0003641276,0.00001275733,0.0002057555,0.00006010657,0.00003518705,0.000003571029,0.000005707789,0.8956158,0.007798998,0.00002350562,0.0955658,0.0003086967],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2913207,0.0002125029,0.6998119,0.001455005,0.003310779,0.0009603701,0.00003213709,0.002559223,0.0003374339],"genre_scores_gemma":[0.993209,0.00003412937,0.003618452,0.00124936,0.00127263,0.0002943772,0.0001899695,0.0000755166,0.00005654228],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7018883,"threshold_uncertainty_score":0.7083809,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01245797320812924,"score_gpt":0.2031550092623449,"score_spread":0.1906970360542156,"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."}}