{"id":"W2917956205","doi":"10.1109/icassp.2019.8682543","title":"Wavenilm: A Causal Neural Network for Power Disaggregation from the Complex Power Signal","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Smart Grid Energy Management","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Power (physics); Convergence (economics); Convolutional neural network; Aggregate (composite); Artificial neural network; SIGNAL (programming language); AC power; Artificial intelligence; Machine learning; Data mining","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001897672,0.0004236618,0.0003694106,0.00003792195,0.0000804732,0.0001690074,0.0005479919,0.0002221668,0.001303202],"category_scores_gemma":[0.00001275581,0.0003237692,0.0002397695,0.0000825971,0.00003444203,0.00007082878,0.0005370877,0.0004093178,0.00009983869],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001432311,"about_ca_system_score_gemma":0.00001980985,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002229928,"about_ca_topic_score_gemma":0.0001904056,"domain_scores_codex":[0.9983729,0.00004712884,0.0003817395,0.0004451025,0.0002882561,0.0004648603],"domain_scores_gemma":[0.9986565,0.0003115728,0.0000867971,0.0008296981,0.00005036431,0.00006507241],"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":[0.00001678648,0.000008733473,0.0004670682,0.00002390954,0.0002384692,0.000001421082,0.000113014,0.7944368,0.00003012626,0.001250227,0.2031269,0.0002865949],"study_design_scores_gemma":[0.0004105875,0.00003504525,0.02173932,0.0000722333,0.00009778043,7.264356e-7,0.00006166464,0.8808471,0.00003798552,0.001879404,0.09430037,0.0005178133],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1748866,0.001040544,0.7451105,0.002686785,0.02535618,0.004157121,0.0005917002,0.001974287,0.04419629],"genre_scores_gemma":[0.9918484,0.00001557633,0.003873666,0.0005773623,0.001394161,0.0002127292,0.001069752,0.000124825,0.0008835263],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8169618,"threshold_uncertainty_score":0.9999214,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02190079717596109,"score_gpt":0.2249626903000825,"score_spread":0.2030618931241214,"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."}}