{"id":"W4384937002","doi":"10.1016/j.enbuild.2023.113377","title":"Efficacy of temporal and spatial abstraction for training accurate machine learning models: A case study in smart thermostats","year":2023,"lang":"en","type":"article","venue":"Energy and Buildings","topic":"Building Energy and Comfort Optimization","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Thermostat; Computer science; Thermal comfort; Energy consumption; Abstraction; Real-time computing; Overhead (engineering); Efficient energy use; Energy (signal processing); Occupancy; Simulation; Machine learning; Artificial intelligence; Engineering; Architectural engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.0002058838,0.0001077602,0.0001483666,0.0001469705,0.00008353882,0.00002087695,0.00003026487,0.00006112538,0.000002100307],"category_scores_gemma":[0.00001558629,0.0001074021,0.00001990964,0.0001767974,0.00001576521,0.0001537725,0.00001993561,0.00008594044,2.756702e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001014633,"about_ca_system_score_gemma":0.00000685728,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002003479,"about_ca_topic_score_gemma":0.001284077,"domain_scores_codex":[0.9994486,0.00001786922,0.0001860334,0.000148546,0.00005600883,0.0001429235],"domain_scores_gemma":[0.9997623,0.00009994215,0.00004210258,0.00005107486,0.00001328484,0.000031298],"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":[0.00006605222,0.00002339162,0.00125328,0.00002245794,0.00002614642,0.00004418405,0.001817286,0.9465103,0.0004604201,0.0003151943,0.000005703187,0.04945557],"study_design_scores_gemma":[0.001039237,0.0001190699,0.0007888719,0.0000284465,0.00001433616,0.00005247645,0.0009163157,0.9960395,0.0003740544,0.0002862146,0.0002165545,0.0001248965],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.972213,0.000111666,0.02730877,0.00001143785,0.00007491911,0.00008858632,0.000002708743,0.0001332922,0.00005561756],"genre_scores_gemma":[0.9992306,0.0001122095,0.0005109691,0.000005080718,0.00002769537,0.00002946464,0.00002146658,0.00002391291,0.00003860396],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04952921,"threshold_uncertainty_score":0.4379731,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0417075302314922,"score_gpt":0.2558300615135889,"score_spread":0.2141225312820967,"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."}}