{"id":"W4289366677","doi":"10.48550/arxiv.1810.10619","title":"Using Personal Environmental Comfort Systems to Mitigate the Impact of\\n Occupancy Prediction Errors on HVAC Performance","year":2018,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Building Energy and Comfort Optimization","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Cisco Systems Canada; University of Waterloo; Cisco Systems","keywords":"HVAC; Occupancy; Model predictive control; Thermal comfort; Air conditioning; Energy consumption; Controller (irrigation); Building energy simulation; Ventilation (architecture); Automotive engineering; Simulation; Computer science; Engineering; Reliability engineering; Control (management); Architectural engineering; Energy performance; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003137433,0.0005785035,0.0002739086,0.0001739348,0.0002115783,0.0004453867,0.0006675788,0.0003181773,0.001244462],"category_scores_gemma":[0.00107768,0.0001904802,0.0002415124,0.0001655396,0.0002404252,0.0005035542,0.000576922,0.0004394314,0.0001506237],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003261452,"about_ca_system_score_gemma":0.0004818159,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006447409,"about_ca_topic_score_gemma":0.006694903,"domain_scores_codex":[0.999756,0.0000470718,0.00001090024,0.00003926692,0.00009871514,0.00004813933],"domain_scores_gemma":[0.9995895,0.0001463602,0.00008039313,0.00008013578,0.00007596675,0.0000275222],"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":[0.0001964933,0.0002059364,0.01142684,0.0001274351,0.00007074231,0.00007841408,0.00008900746,0.9150531,0.03136389,0.000712558,0.0004160369,0.04025958],"study_design_scores_gemma":[0.00001904951,0.0004176432,0.006404037,0.00001048832,0.00004876415,0.00005127853,0.00004566883,0.9509711,0.04026969,0.0002822964,0.001460732,0.000019221],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8990517,0.000332155,0.09496937,0.00009462915,0.00004308245,0.00006297261,0.000174516,0.001336522,0.003935079],"genre_scores_gemma":[0.9932016,0.00006560611,0.006228581,0.00001259647,0.000003280183,0.00001224297,0.00006961983,0.00002093622,0.0003855275],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006447409,"threshold_uncertainty_score":0.01281977,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05951077895885894,"score_gpt":0.1887555842286179,"score_spread":0.1292448052697589,"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."}}