{"id":"W3127967937","doi":"10.48550/arxiv.2102.06039","title":"An Ensemble Deep Convolutional Neural Network Model for Electricity Theft Detection in Smart Grids","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Electricity Theft Detection Techniques","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Smart grid; Convolutional neural network; Artificial intelligence; Electricity; Ensemble forecasting; Data mining; Deep learning; Ensemble learning; Random forest; Precision and recall; Machine learning; Engineering","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":[0.000323686,0.0003928743,0.0004256622,0.0004197588,0.0001564647,0.00006838152,0.0004460806,0.0005977709,0.00001222381],"category_scores_gemma":[0.00003370428,0.0005466866,0.0002467328,0.0008522784,0.00004490324,0.0003067886,0.000135239,0.001063994,0.000002734981],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008948586,"about_ca_system_score_gemma":0.0001051141,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001714745,"about_ca_topic_score_gemma":0.002214346,"domain_scores_codex":[0.998135,0.0001346228,0.0002924073,0.0007495979,0.00009013918,0.0005982256],"domain_scores_gemma":[0.998917,0.0001117164,0.000109237,0.000549385,0.0001857253,0.0001269697],"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":[0.00008220435,0.00005269203,0.0007244492,0.00007910521,0.00005989719,0.00001984323,0.00006327025,0.9932824,0.00328944,0.0009646968,0.0000361722,0.001345823],"study_design_scores_gemma":[0.0003570681,0.00009030716,0.0005585337,0.00003243783,0.00006595113,0.000008218992,0.00002144953,0.9683244,0.01151964,0.01849904,0.00001780679,0.0005051537],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4532411,0.00009315219,0.5452899,0.000003158167,0.000239714,0.00035561,0.000008114986,0.0006270246,0.0001421866],"genre_scores_gemma":[0.9977219,0.000223114,0.001570276,0.00003783001,0.0001702672,0.00001921973,0.00006676133,0.00007542793,0.0001151725],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5444808,"threshold_uncertainty_score":0.9996985,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03460945671725664,"score_gpt":0.1801583213228186,"score_spread":0.145548864605562,"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."}}