{"id":"W3176542144","doi":"10.18280/jesa.540312","title":"Detection of Non-Technical Losses in Electric Distribution Network by Applying Machine Learning and Feature Engineering","year":2021,"lang":"en","type":"article","venue":"Journal Européen des Systèmes Automatisés","topic":"Electricity Theft Detection Techniques","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Feature engineering; Depreciation (economics); Feature (linguistics); Computer science; Electric power; Reliability engineering; Power (physics); Artificial intelligence; Machine learning; Industrial engineering; Engineering; Deep learning","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004594979,0.0002218892,0.0003697739,0.0002089899,0.0001383163,0.0001036014,0.0001018491,0.000178019,0.000007395889],"category_scores_gemma":[0.0002816702,0.0002366035,0.00007883479,0.001268247,0.0000217577,0.0002228899,0.00004166637,0.001072489,0.000001409122],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003619112,"about_ca_system_score_gemma":0.00002391748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001297696,"about_ca_topic_score_gemma":0.0000211537,"domain_scores_codex":[0.9986085,0.000122664,0.0004787961,0.0001747143,0.0002332851,0.0003820088],"domain_scores_gemma":[0.9994146,0.0001396515,0.0001517309,0.0001046966,0.00009940215,0.00008997571],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001057783,0.00002181814,0.002166548,0.0002818185,0.00004695613,0.00005982804,0.00003350641,0.02050973,0.8130041,0.00001873449,0.0002328888,0.1636135],"study_design_scores_gemma":[0.0004268839,0.0002147787,0.06995711,0.0005868455,0.00004669982,0.003115154,0.00001259759,0.5652932,0.3576414,0.000293373,0.002026476,0.0003855092],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.599371,0.01382861,0.3855331,0.00001767535,0.0001599685,0.0002140651,0.000007362042,0.0007513225,0.0001169523],"genre_scores_gemma":[0.9938302,0.0025829,0.003354102,0.000004293859,0.0000987602,0.00001984317,0.00001022969,0.00005750918,0.00004217719],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5447835,"threshold_uncertainty_score":0.964841,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00409004643414001,"score_gpt":0.2070198263363009,"score_spread":0.2029297799021609,"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."}}