{"id":"W4392255272","doi":"10.1145/3638209.3638211","title":"Assessing the Effectiveness of Supervised and Semi-supervised NILM Approaches in an Industrial Context","year":2023,"lang":"en","type":"article","venue":"","topic":"Smart Grid Energy Management","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence; Context (archaeology); Supervised learning; Artificial neural network; Energy consumption; Data mining; Regression analysis; 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":[0.001104111,0.0001347612,0.0002087657,0.000147621,0.00003436964,0.00007269423,0.0001550666,0.00008314137,0.00001614013],"category_scores_gemma":[0.00004578696,0.0001021462,0.00002763162,0.0004911106,0.00004707421,0.0002903414,0.00008310263,0.0001381772,0.000003864689],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003722547,"about_ca_system_score_gemma":0.00001113145,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001182434,"about_ca_topic_score_gemma":0.00008867632,"domain_scores_codex":[0.9990551,0.0002378107,0.0001928853,0.0001734564,0.0001357054,0.0002050564],"domain_scores_gemma":[0.9992765,0.0004210245,0.00001216546,0.0002391213,0.00001225844,0.00003895216],"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":[0.00008587194,0.0000952714,0.2131745,0.0005946343,0.000193426,0.00001962832,0.001491294,0.7023135,0.01867928,0.004647182,0.0004810387,0.05822435],"study_design_scores_gemma":[0.001827637,0.00004000666,0.2942266,0.0001000737,0.00002021871,9.534161e-7,0.003931009,0.6871899,0.01213792,0.0001248633,0.0001822184,0.0002185639],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9946305,0.00005519915,0.0008682572,0.00003687798,0.0002566545,0.0002931065,0.000001363034,0.0002217658,0.003636307],"genre_scores_gemma":[0.9997218,0.00001116814,0.00005875132,0.00001171423,0.00007021432,0.00006215059,0.00001564746,0.00002838368,0.00002013531],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08105211,"threshold_uncertainty_score":0.4165402,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09404407097871972,"score_gpt":0.2641884330251689,"score_spread":0.1701443620464491,"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."}}