{"id":"W3008498556","doi":"10.1109/icmla.2019.00232","title":"Design of a Cost-Effective Deep Convolutional Neural Network–Based Scheme for Diagnosing Faults in Smart Grids","year":2019,"lang":"en","type":"article","venue":"","topic":"Electricity Theft Detection Techniques","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Smart grid; Convolutional neural network; Cluster analysis; Real-time computing; Fault (geology); Electric power system; Artificial neural network; Energy consumption; Matching (statistics); Artificial intelligence; Data mining; Power (physics); 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":[],"consensus_categories":[],"category_scores_codex":[0.0003062769,0.0001382637,0.0002197632,0.0001610129,0.00002321064,0.000007825952,0.000094339,0.0001060947,0.00003773265],"category_scores_gemma":[0.00006949318,0.0001460175,0.0000621164,0.0003370241,0.00002055755,0.0001127101,0.00001169341,0.0001594391,0.0000062352],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001827861,"about_ca_system_score_gemma":0.00001817167,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002821614,"about_ca_topic_score_gemma":0.00003030801,"domain_scores_codex":[0.9991571,0.00005532866,0.0002293351,0.0001572495,0.0001076515,0.000293387],"domain_scores_gemma":[0.9988492,0.0008778117,0.00003827292,0.0001278128,0.00007360815,0.0000332828],"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":[0.000151109,0.00004837795,0.01427931,0.0001111887,0.00003452245,0.00000102111,0.00003356388,0.9369563,0.03956715,0.0003570085,0.0005331602,0.007927286],"study_design_scores_gemma":[0.0007050475,0.000213452,0.003039867,0.00003806016,0.000005255009,0.000001703941,0.00000361012,0.8325776,0.1628323,0.0003016876,0.0001412245,0.0001401063],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1673705,0.0001168244,0.8287305,0.00001718757,0.0001680016,0.002931198,0.000003553729,0.0004124564,0.0002497978],"genre_scores_gemma":[0.9706613,0.000005204284,0.02825074,0.00006676483,0.00003969009,0.0009174725,0.000007222106,0.00003086112,0.00002073417],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8032908,"threshold_uncertainty_score":0.5954422,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01224012608473819,"score_gpt":0.2351048902849226,"score_spread":0.2228647642001844,"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."}}