{"id":"W4389934412","doi":"10.1109/jiot.2023.3344457","title":"Delay and Energy-Efficient Asynchronous Federated Learning for Intrusion Detection in Heterogeneous Industrial Internet of Things","year":2023,"lang":"en","type":"article","venue":"IEEE Internet of Things Journal","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"Queen's University; National Natural Science Foundation of China; Queen's University Belfast","keywords":"Computer science; Intrusion detection system; Energy consumption; Asynchronous communication; Efficient energy use; Artificial intelligence; Machine learning; Deep learning; Industrial Internet; Distributed computing; Computer network; Internet of Things; Computer security","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011557,0.0005522139,0.0007058642,0.0003708979,0.0004859758,0.0007823756,0.001302005,0.0006534066,0.0006589426],"category_scores_gemma":[0.002507737,0.0002300768,0.0004128813,0.0004395749,0.0005527681,0.001718069,0.001114853,0.0008282496,0.0001268817],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008049361,"about_ca_system_score_gemma":0.0008804662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001756522,"about_ca_topic_score_gemma":0.00242105,"domain_scores_codex":[0.9994099,0.0001296011,0.00004132288,0.0001820492,0.0001303441,0.0001068119],"domain_scores_gemma":[0.9991297,0.0004173741,0.0001219253,0.0001360747,0.0001475656,0.00004727392],"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":[0.0003454178,0.0002771463,0.00485453,0.0001147553,0.00006547603,0.0001716847,0.0001092431,0.739862,0.009271692,0.01155743,0.002163734,0.2312069],"study_design_scores_gemma":[0.000006718124,0.00003457817,0.0001876803,0.00000276429,0.000007271135,0.00002507584,0.00001059928,0.9947687,0.001660087,0.003053262,0.0002397974,0.000003545324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05116409,0.0002532085,0.94635,0.000252807,0.00005482634,0.00004683109,0.00004680158,0.0006604044,0.001171079],"genre_scores_gemma":[0.9490195,0.00009428497,0.04967418,0.0001531161,0.00002209377,0.00005075822,0.00007157974,0.00001814908,0.0008963943],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001756522,"threshold_uncertainty_score":0.006112039,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02928309967422148,"score_gpt":0.2609291907023623,"score_spread":0.2316460910281408,"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."}}