{"id":"W4288562897","doi":"10.48550/arxiv.1902.08736","title":"Wavenilm: A causal neural network for power disaggregation from the\\n complex power signal","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Smart Grid Energy Management","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Power (physics); Convolutional neural network; Artificial neural network; Convergence (economics); Aggregate (composite); AC power; SIGNAL (programming language); Artificial intelligence; Machine learning","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":[0.000144022,0.0004153074,0.0003601607,0.0000750437,0.0001290978,0.00008828451,0.0007371279,0.0002470877,0.0003471698],"category_scores_gemma":[0.00001094523,0.0004226591,0.0002822206,0.0002193811,0.00007033807,0.0001402571,0.0005922286,0.0004407253,0.00009273056],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000276182,"about_ca_system_score_gemma":0.00003058023,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001892372,"about_ca_topic_score_gemma":0.0001539444,"domain_scores_codex":[0.9984745,0.0000713717,0.0002281939,0.0006447724,0.0001056932,0.0004754407],"domain_scores_gemma":[0.9985676,0.00027071,0.000124054,0.0008714978,0.00006940119,0.00009668418],"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":[0.00005887825,0.00001773944,0.002747818,0.00003084456,0.0003276843,0.0000244987,0.0001116659,0.9667102,0.00002105482,0.00700692,0.02288552,0.00005717322],"study_design_scores_gemma":[0.0006448957,0.00004262511,0.01617303,0.00007816345,0.0001971896,6.324302e-7,0.0001011231,0.9616364,0.00001475157,0.004983173,0.01559027,0.0005377628],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6611744,0.0001757074,0.3266568,0.0001591453,0.004683391,0.001132714,0.0002620765,0.0005695582,0.005186216],"genre_scores_gemma":[0.9976543,0.00003619441,0.0003278093,0.0001539823,0.0004947315,0.000006015414,0.0004655698,0.00008406939,0.0007773818],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3364799,"threshold_uncertainty_score":0.9998225,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04965668999390301,"score_gpt":0.1706192327784281,"score_spread":0.1209625427845251,"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."}}