{"id":"W4400567455","doi":"10.1049/smc2.12088","title":"A hybrid attention‐based long short‐term memory fast model for thermal regulation of smart residential buildings","year":2024,"lang":"en","type":"article","venue":"IET Smart Cities","topic":"Building Energy and Comfort Optimization","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"HVAC; Thermal comfort; Model predictive control; Adaptability; Building automation; Computer science; Term (time); Efficient energy use; Control engineering; Occupancy; Control (management); Control system; Automotive engineering; Simulation; Engineering; Air conditioning; Architectural engineering; Artificial intelligence; Mechanical 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":[0.000140155,0.0001493326,0.0001557138,0.0001787894,0.00007838115,0.00007659933,0.0001052569,0.00007312196,0.00004340368],"category_scores_gemma":[0.00000613651,0.0001599394,0.0001400546,0.0000967861,0.00004833066,0.000300452,0.00001980381,0.00008319357,0.000001155185],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004725951,"about_ca_system_score_gemma":0.00003300387,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001226809,"about_ca_topic_score_gemma":0.00002661484,"domain_scores_codex":[0.9991905,0.00001135865,0.0002655054,0.0001744928,0.00017122,0.0001868974],"domain_scores_gemma":[0.999676,0.00003993118,0.0000241101,0.0001718698,0.00005600959,0.00003205922],"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":[0.00003531426,0.000008895492,0.0003170905,0.0003283914,0.00005982437,0.000001591924,0.0001595008,0.983042,0.01095412,0.001165672,0.002008884,0.001918692],"study_design_scores_gemma":[0.0001661007,0.00002391853,0.001133327,0.0001537275,0.00005562167,0.000003257009,0.00001688529,0.9662982,0.03138022,0.0005252082,0.00007726916,0.0001662408],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5344149,0.000172142,0.4641799,0.00003449246,0.0004390284,0.0001149437,0.00003181849,0.0002883993,0.0003244081],"genre_scores_gemma":[0.9946585,0.00001210009,0.003619731,0.00001679928,0.0001604128,0.00007152268,0.0001550481,0.00005521727,0.001250621],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4605601,"threshold_uncertainty_score":0.652214,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01286764540617587,"score_gpt":0.2177689193706308,"score_spread":0.2049012739644549,"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."}}