{"id":"W4392628723","doi":"10.26868/25222708.2023.1400","title":"Ensemble transfer learning strategy in forecasting power consumption for residential buildings","year":2023,"lang":"en","type":"article","venue":"Building Simulation Conference proceedings","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Ensemble forecasting; Transfer of learning; Ensemble learning; Artificial intelligence; Machine learning; Power consumption; Predictive power; Deep learning; Energy consumption; Long short term memory; Data modeling; Predictive modelling; Power (physics); Transfer (computing); Recurrent neural network; Artificial neural network; Engineering; Database","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007401779,0.0005884442,0.0006422942,0.0004875222,0.0002532329,0.0003988078,0.0006771965,0.0005252165,0.001028489],"category_scores_gemma":[0.001666625,0.000208644,0.0004304615,0.0006499527,0.000215709,0.001408144,0.0005097919,0.0007446021,0.0002282336],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004120849,"about_ca_system_score_gemma":0.0004451057,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006690436,"about_ca_topic_score_gemma":0.005278824,"domain_scores_codex":[0.9998234,0.00004989854,0.000009407812,0.00003987816,0.00004934995,0.00002811669],"domain_scores_gemma":[0.9997067,0.0001413595,0.00002368527,0.0000318358,0.00008432595,0.00001194772],"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":[0.00005764238,0.00005784156,0.001392604,0.00001742788,0.00004621454,0.00005270754,0.00003800084,0.8994547,0.001456198,0.00106322,0.0006058879,0.09575751],"study_design_scores_gemma":[7.266166e-7,0.000007587328,0.0001307929,7.920523e-7,0.000002199986,0.000002809325,0.000003089038,0.9991478,0.0002638861,0.0003805943,0.00005842679,0.000001242385],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2832559,0.0008638051,0.7101139,0.0003095952,0.0000963036,0.00004698842,0.0001342883,0.00105524,0.004123993],"genre_scores_gemma":[0.9737902,0.0002008563,0.02416468,0.00004493902,0.00003378075,0.00003686321,0.000146855,0.00002710303,0.001554708],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006690436,"threshold_uncertainty_score":0.01330298,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05504695749078569,"score_gpt":0.2839213225859204,"score_spread":0.2288743650951347,"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."}}