{"id":"W4388919384","doi":"10.1109/tgcn.2023.3335342","title":"Deep Learning-Driven Anomaly Detection for Green IoT Edge Networks","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Green Communications and Networking","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"Mitacs","keywords":"Anomaly detection; Computer science; Troubleshooting; Energy consumption; Deep learning; Efficient energy use; Wireless sensor network; Real-time computing; Reliability (semiconductor); Enhanced Data Rates for GSM Evolution; Transmission (telecommunications); Data transmission; Artificial intelligence; Data mining; Distributed computing; Computer network; Telecommunications; 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":["sts"],"consensus_categories":[],"category_scores_codex":[0.0003560819,0.0002125069,0.0002053103,0.0003118336,0.002084825,0.000143113,0.0009560985,0.0001684077,0.000004359471],"category_scores_gemma":[8.254516e-7,0.0002324703,0.0001580569,0.001398311,0.0001213591,0.000202025,0.00004018254,0.0004889892,0.00002020763],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006141506,"about_ca_system_score_gemma":0.00001945993,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002828405,"about_ca_topic_score_gemma":0.0008544928,"domain_scores_codex":[0.9985569,0.0001314822,0.0003540939,0.0004454031,0.0001350002,0.000377138],"domain_scores_gemma":[0.9979171,0.0004614841,0.0001579317,0.001224172,0.0001175997,0.0001217361],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009949457,0.00005026914,0.00004899665,0.000008485745,0.00003704508,3.94581e-7,0.0001594836,0.006909085,0.0002552346,0.0004221089,0.00004125724,0.9920577],"study_design_scores_gemma":[0.0002336909,0.0002132868,0.0001731936,0.00002889055,0.00003124517,0.00001304247,0.00003501743,0.9528981,0.0003496809,0.0008519382,0.0449293,0.000242603],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0009650315,0.0003039086,0.9951534,0.001340826,0.000232792,0.000554834,0.000004261067,0.001167701,0.0002772394],"genre_scores_gemma":[0.9816918,0.002024119,0.01421418,0.000173455,0.0001604972,0.0008418701,0.00001028416,0.00003633219,0.0008474047],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9918151,"threshold_uncertainty_score":0.9992144,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03193565485445973,"score_gpt":0.2688131730888251,"score_spread":0.2368775182343654,"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."}}