{"id":"W3112092637","doi":"10.1109/smc42975.2020.9283064","title":"Unsupervised Stacked Autoencoders for Anomaly Detection on Smart Cyber-physical Grids","year":2020,"lang":"en","type":"article","venue":"","topic":"Smart Grid Security and Resilience","field":"Engineering","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Autoencoder; Computer science; Anomaly detection; Cyber-physical system; Deep learning; Vulnerability (computing); Artificial intelligence; Data mining; Smart grid; Ensemble learning; Representation (politics); Machine learning; Electric power system; Construct (python library); Big data; Random forest; Artificial neural network; Feature learning; Power (physics); Engineering; Computer security; Computer network","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007405247,0.0007042519,0.0006850261,0.0005709004,0.0002571508,0.0004221538,0.0005589866,0.0004756421,0.0006321233],"category_scores_gemma":[0.002111889,0.0003736748,0.0004838537,0.0004983585,0.0003419573,0.0008811649,0.0004312657,0.001046939,0.0001718595],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004598875,"about_ca_system_score_gemma":0.0005420431,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006337444,"about_ca_topic_score_gemma":0.006462776,"domain_scores_codex":[0.9996794,0.00007991128,0.00002357377,0.00007348375,0.00009454128,0.00004909033],"domain_scores_gemma":[0.9992179,0.0003996287,0.00008956383,0.00008085231,0.000189402,0.00002261662],"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":[0.00008982136,0.00006576129,0.00166354,0.00002745978,0.00006798746,0.00007977017,0.00004867517,0.8533039,0.004062496,0.001971889,0.0008145947,0.137804],"study_design_scores_gemma":[5.85499e-7,0.000005145171,0.0001727339,0.000001125692,0.000001875241,0.000004221845,0.000002144661,0.9989555,0.0004271191,0.0003847656,0.00004354193,0.000001178898],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1209309,0.0003350844,0.876053,0.0001794473,0.00005743081,0.00002277253,0.00009603389,0.001172286,0.001153004],"genre_scores_gemma":[0.9106374,0.0001923944,0.08740325,0.00007039699,0.00003440682,0.00002903098,0.0002599955,0.00004380784,0.001329233],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006337444,"threshold_uncertainty_score":0.01260108,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01581713835787829,"score_gpt":0.2116338345144194,"score_spread":0.1958166961565411,"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."}}