{"id":"W4309007402","doi":"10.3390/su142215001","title":"Detecting Nontechnical Losses in Smart Meters Using a MLP-GRU Deep Model and Augmenting Data via Theft Attacks","year":2022,"lang":"en","type":"article","venue":"Sustainability","topic":"Electricity Theft Detection Techniques","field":"Engineering","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"Thompson Rivers University","funders":"King Saud University","keywords":"Smart meter; Hyperparameter; Computer science; Perceptron; Receiver operating characteristic; Deep learning; Electricity meter; Artificial intelligence; Multilayer perceptron; Artificial neural network; Electricity; Machine learning; Engineering; Power (physics)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001990287,0.000229709,0.0002992646,0.0003125221,0.0003336681,0.00005502245,0.0004893467,0.00009365318,0.00001588027],"category_scores_gemma":[0.0007610414,0.0002741002,0.00005346776,0.0006990037,0.00009026156,0.000383426,0.00101469,0.0008091229,1.979095e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002046131,"about_ca_system_score_gemma":0.0001047962,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005372953,"about_ca_topic_score_gemma":0.0003624421,"domain_scores_codex":[0.9979708,0.0002006474,0.0004510646,0.0005525622,0.0002656658,0.0005592569],"domain_scores_gemma":[0.9986978,0.0002045731,0.0000711168,0.0008582553,0.00009589038,0.000072395],"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":[0.0001569075,0.0002529261,0.042595,0.001106877,0.0001113638,0.00008708049,0.002074825,0.8034531,0.02898934,0.0002422254,0.00004119635,0.1208892],"study_design_scores_gemma":[0.0002070243,0.00005763245,0.000679908,0.000008858704,0.0000239402,0.00004568919,0.0006928398,0.9840093,0.004623883,0.009263217,0.00009651328,0.0002912148],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7415816,0.0002187842,0.2568711,0.00005100681,0.0000467331,0.0005040275,0.000008508403,0.000654121,0.00006415569],"genre_scores_gemma":[0.9920698,0.000008402283,0.007720601,0.00002840903,0.00001732078,0.00008870706,0.000005991047,0.0000518559,0.000008912186],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2504882,"threshold_uncertainty_score":0.9999711,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0240244546194913,"score_gpt":0.283027735656265,"score_spread":0.2590032810367737,"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."}}