{"id":"W2990083057","doi":"10.1109/tii.2019.2955470","title":"Semisupervised Multilabel Deep Learning Based Nonintrusive Load Monitoring in Smart Grids","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Industrial Informatics","topic":"Smart Grid Energy Management","field":"Engineering","cited_by":132,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"China Scholarship Council; National Natural Science Foundation of China","keywords":"Computer science; Smart grid; Artificial intelligence; Machine learning; Convolutional neural network; Deep learning; Feature (linguistics); Energy consumption; Feature extraction; Representation (politics); Energy (signal processing); Feature learning; Load management; Data mining; Pattern recognition (psychology); 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":[0.000290698,0.0002965719,0.0003010944,0.0003870741,0.00009322298,0.00008528175,0.0002232193,0.0002930069,0.0002183215],"category_scores_gemma":[0.0000153492,0.0003312502,0.00010204,0.0005621117,0.00002285931,0.0004663157,0.000002967262,0.001070361,0.0003746182],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006525775,"about_ca_system_score_gemma":0.00006385808,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007404629,"about_ca_topic_score_gemma":0.00002571563,"domain_scores_codex":[0.9982929,0.00003690434,0.0006704063,0.000131383,0.0004240159,0.0004444181],"domain_scores_gemma":[0.9992689,0.0001660963,0.00006665885,0.0003260222,0.00005951662,0.0001127709],"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":[0.00004202687,0.00004065266,0.0007503844,0.00007462563,0.00005459066,0.000002657721,0.0008160397,0.9867206,0.0002235871,0.00000280733,0.00006435156,0.01120769],"study_design_scores_gemma":[0.003389428,0.0001090211,0.0001612129,0.0002166151,0.00003288491,0.000001536402,0.001157006,0.9584923,0.03238199,0.000001332083,0.003667376,0.0003893409],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7883148,0.00001578961,0.196427,0.00003119847,0.006909671,0.0006997971,0.00001119949,0.0006354714,0.006955175],"genre_scores_gemma":[0.9981982,0.00003449423,0.001166151,0.000039188,0.0001676739,0.00008172174,0.000006670874,0.00005171992,0.000254171],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2098835,"threshold_uncertainty_score":0.9999139,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0194499486938346,"score_gpt":0.2146579060105038,"score_spread":0.1952079573166692,"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."}}