{"id":"W3154459044","doi":"10.1109/jiot.2021.3074382","title":"Toward Accurate Anomaly Detection in Industrial Internet of Things Using Hierarchical Federated Learning","year":2021,"lang":"en","type":"article","venue":"IEEE Internet of Things Journal","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":245,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"King Saud University","keywords":"Anomaly detection; Computer science; Federated learning; Reinforcement learning; Industrial Internet; The Internet; Artificial intelligence; Internet of Things; Computer security; Machine learning; Data mining; World Wide Web","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":["metaresearch","metaepi_narrow","open_science","research_integrity"],"consensus_categories":["open_science"],"category_scores_codex":[0.001606592,0.0002523615,0.0005216626,0.0005698629,0.00007257792,0.0005488765,0.008572178,0.0003697967,0.00004163788],"category_scores_gemma":[0.01474125,0.000249006,0.0001708223,0.0008080833,0.0001583398,0.003202392,0.0130076,0.002997068,0.000003879312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002916885,"about_ca_system_score_gemma":0.0003083638,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007456717,"about_ca_topic_score_gemma":0.00001833963,"domain_scores_codex":[0.9968405,0.0004547573,0.001144895,0.0004963827,0.0006093192,0.0004541957],"domain_scores_gemma":[0.9971675,0.0002817741,0.00102086,0.001066943,0.0003594793,0.000103423],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008648523,0.000682745,0.0153401,0.000237548,0.0007204515,0.002474464,0.01425217,0.001727729,0.6795694,0.0007775787,0.009129728,0.2742232],"study_design_scores_gemma":[0.0008299638,0.0002350599,0.000159635,0.0006751785,0.00001326931,0.00116033,0.0001419355,0.5397502,0.4462102,0.01046376,0.0001532463,0.0002071648],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5735969,0.00007423988,0.4236362,0.001273398,0.00113908,0.00005598358,6.956421e-7,0.000092317,0.0001312425],"genre_scores_gemma":[0.9267496,0.00003102237,0.07293966,0.0001043231,0.00009000805,0.000001458975,0.000001730045,0.00001971629,0.00006249051],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5380225,"threshold_uncertainty_score":0.9999962,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07706288089800138,"score_gpt":0.2980538154561173,"score_spread":0.2209909345581159,"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."}}