{"id":"W3212439832","doi":"10.1016/j.iot.2021.100470","title":"Federated learning with hyperparameter-based clustering for electrical load forecasting","year":2021,"lang":"en","type":"preprint","venue":"Internet of Things","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Electric System Operator","keywords":"Computer science; Hyperparameter; Cluster analysis; Aggregate (composite); Machine learning; Enhanced Data Rates for GSM Evolution; Convergence (economics); Artificial intelligence; Mean squared error; Electricity; Electrical load; Popularity; Data mining; Power (physics); 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":["metaresearch","metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0007879192,0.0004314494,0.0006892532,0.0002530645,0.00009289222,0.0008831943,0.01640972,0.0004619171,0.00000731334],"category_scores_gemma":[0.02226756,0.0004064948,0.0002064149,0.0003532156,0.0001060868,0.0005050947,0.07440978,0.001570435,0.000001761804],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003647427,"about_ca_system_score_gemma":0.0004838847,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004729877,"about_ca_topic_score_gemma":0.00003086302,"domain_scores_codex":[0.9969128,0.0001100712,0.0006180867,0.00120681,0.0005817407,0.0005704584],"domain_scores_gemma":[0.9947847,0.0007430049,0.0007244532,0.003135632,0.0005401744,0.00007199539],"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":[0.001663552,0.001259455,0.005927733,0.007711793,0.00272201,0.001126535,0.005427871,0.04650319,0.01772578,0.0006338375,0.04740118,0.8618971],"study_design_scores_gemma":[0.000460309,0.0004102227,0.00001340035,0.001479394,0.00002951844,0.00004912482,0.00002442082,0.9591101,0.03494117,0.002781837,0.0002824483,0.0004180376],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1039539,0.0002000527,0.892037,0.001876076,0.0003932844,0.0004150033,0.000004168802,0.0008403132,0.0002801772],"genre_scores_gemma":[0.4982441,0.000003625135,0.5014329,0.0001230231,0.00001912892,0.00006223263,0.00003200402,0.00003138718,0.00005156497],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.912607,"threshold_uncertainty_score":0.9998387,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04856344549688869,"score_gpt":0.2729989233823644,"score_spread":0.2244354778854757,"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."}}