{"id":"W4200621921","doi":"10.1109/iccais52680.2021.9624524","title":"Non-Intrusive Load Monitoring based Demand Prediction for Smart Meter Attack Detection","year":2021,"lang":"en","type":"article","venue":"2021 International Conference on Control, Automation and Information Sciences (ICCAIS)","topic":"Electricity Theft Detection Techniques","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Smart meter; Smart grid; Support vector machine; Computer science; Electricity; Real-time computing; Energy consumption; Energy (signal processing); Load profile; Electricity meter; Data mining; Engineering; Artificial intelligence","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":[0.0006407647,0.0001905802,0.0001881559,0.0004175046,0.0002847612,0.0005723067,0.0001767504,0.0001290428,0.0001963088],"category_scores_gemma":[0.0002982721,0.0001934461,0.00008135497,0.0003775925,0.00006788484,0.002845576,0.00001865504,0.0001629098,0.00004632542],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002807772,"about_ca_system_score_gemma":0.0001500324,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001020164,"about_ca_topic_score_gemma":0.00001758903,"domain_scores_codex":[0.9984025,0.0000405797,0.0005206848,0.0002235453,0.0005971009,0.0002155842],"domain_scores_gemma":[0.9984487,0.0001458909,0.000176441,0.0001349722,0.001017755,0.00007629869],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000546723,0.0001813781,0.00415679,0.00044107,0.0005341251,0.000004836966,0.002418326,0.1357868,0.2580126,0.02346057,0.003678516,0.5707783],"study_design_scores_gemma":[0.000940296,0.0001494453,0.002655491,0.00006732708,0.00001570999,0.000008322874,0.0001328454,0.856476,0.1350446,0.0003633885,0.003978685,0.0001678935],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08047739,0.00003301804,0.8967046,0.001029233,0.001897903,0.0006035002,0.0001086808,0.0005139326,0.01863175],"genre_scores_gemma":[0.9972934,0.0001207281,0.001776866,0.0003139541,0.0001440752,0.0002045335,0.00004529776,0.000009482468,0.00009167284],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.916816,"threshold_uncertainty_score":0.7888501,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02150698109144061,"score_gpt":0.271736193876035,"score_spread":0.2502292127845944,"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."}}