{"id":"W2975975302","doi":"10.1109/access.2019.2943752","title":"Similarity-Based Chained Transfer Learning for Energy Forecasting With Big Data","year":2019,"lang":"en","type":"article","venue":"IEEE Access","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":63,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Transfer of learning; Initialization; Artificial intelligence; Machine learning; Artificial neural network; Similarity (geometry); Big data; Energy consumption; Smart meter; Deep learning; Data modeling; Energy (signal processing); Recurrent neural network; Data mining; Smart grid; Database; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001950729,0.0002284841,0.0002439912,0.0001133908,0.0001089011,0.0001364476,0.0006459874,0.00009802664,0.00002843007],"category_scores_gemma":[0.00002118929,0.0002041522,0.0000481404,0.0002522288,0.00001909209,0.0004152855,0.00003723089,0.000194702,0.000002926304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002408577,"about_ca_system_score_gemma":0.00003857012,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006616767,"about_ca_topic_score_gemma":0.0002734316,"domain_scores_codex":[0.9988324,0.00001928157,0.0002143638,0.0003441589,0.0001637354,0.0004260343],"domain_scores_gemma":[0.9991659,0.0002278811,0.00002706727,0.0004483659,0.00005089231,0.00007987746],"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":[0.00006629027,0.00001481238,0.003210986,0.0002647593,0.00006572856,0.000007370556,0.00007449715,0.9609675,0.002312209,0.0001205131,0.0002459974,0.03264929],"study_design_scores_gemma":[0.001120105,0.00009634728,0.00006286605,0.0001729627,0.00003292915,0.000005272195,0.000015328,0.9400091,0.02145112,0.00003371757,0.03663164,0.0003686588],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3818827,0.0001094768,0.6117041,0.00004433342,0.001238631,0.0001949172,0.00004591581,0.0004705887,0.004309337],"genre_scores_gemma":[0.9978213,0.000007426724,0.0009692165,0.0001382148,0.0004781997,0.0000357012,0.0002408211,0.00009952996,0.0002095554],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6159386,"threshold_uncertainty_score":0.8325085,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07430641055625936,"score_gpt":0.2520843559768287,"score_spread":0.1777779454205693,"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."}}