{"id":"W4401689408","doi":"10.1016/j.jobe.2024.110492","title":"Automated model order reduction for building thermal load prediction using smart thermostats data","year":2024,"lang":"en","type":"article","venue":"Journal of Building Engineering","topic":"Building Energy and Comfort Optimization","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hydro-Québec; Concordia University","funders":"","keywords":"Thermostat; Reduction (mathematics); Retrofitting; Computer science; Flexibility (engineering); Mean squared error; Model predictive control; Cascade; System identification; Temperature control; Building model; Data mining; Engineering; Simulation; Control engineering; Control (management); Mathematics; Statistics; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006747892,0.0002167968,0.0002310725,0.0003232745,0.0000757905,0.0001364728,0.000273469,0.0001390583,0.000003345742],"category_scores_gemma":[0.00007977105,0.0002128843,0.00008958147,0.0004133508,0.00001036933,0.001299883,0.0000495436,0.0003087364,1.726613e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003556594,"about_ca_system_score_gemma":0.0001049171,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000333127,"about_ca_topic_score_gemma":1.543077e-7,"domain_scores_codex":[0.9987209,0.00001009544,0.0004934001,0.0001780898,0.000275434,0.0003220373],"domain_scores_gemma":[0.9993886,0.00005805246,0.00008003018,0.0002449855,0.0001404279,0.00008794339],"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":[0.00001103624,0.000008778971,0.000006673496,0.0001492435,0.0001488373,0.000003043271,0.0001008275,0.8035225,0.1936111,0.0002418442,0.0007951987,0.00140099],"study_design_scores_gemma":[0.0002142171,0.00002499544,0.00001013454,0.0005140241,0.0001138647,0.0002061093,0.00001314478,0.9878958,0.009701848,0.0000531284,0.001054259,0.0001984427],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2941645,0.001508256,0.70106,0.00001995241,0.002326343,0.00008426306,0.00002106992,0.000799293,0.00001629237],"genre_scores_gemma":[0.7580163,0.00009559141,0.2410661,0.000004393902,0.0006819241,0.00000480535,0.00001363563,0.0001036727,0.00001349077],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4638518,"threshold_uncertainty_score":0.8681169,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02839160414909483,"score_gpt":0.2657935187859032,"score_spread":0.2374019146368083,"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."}}