{"id":"W6968720188","doi":"10.5281/zenodo.5517557","title":"A Comprehensive Comparative Analysis of Machine Learning Models for Predicting Heating and Cooling Loads","year":2021,"lang":"en","type":"book-chapter","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Scientific and Engineering Research Topics","field":"Dentistry","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Artificial neural network; Support vector machine; Mean squared error; Approximation error; Radial basis function; Mean absolute percentage error; Energy consumption; Kernel (algebra)","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005703981,0.0002211663,0.000546118,0.0005760121,0.001246218,0.0005021379,0.0004343811,0.0001377096,0.002571914],"category_scores_gemma":[0.0003961742,0.000248154,0.0001714193,0.0003672968,0.0001872765,0.0001404939,0.0009180741,0.0005677038,0.00008527024],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001053619,"about_ca_system_score_gemma":0.000007174552,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002881575,"about_ca_topic_score_gemma":0.000002034113,"domain_scores_codex":[0.9980662,0.0001156337,0.0004325515,0.0005560983,0.0005088107,0.0003207089],"domain_scores_gemma":[0.9977466,0.0001905445,0.0002382346,0.0003441067,0.001325348,0.0001551128],"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":[0.0009196532,0.0003091863,0.0001016314,0.005159547,0.01543741,0.0002383681,0.01838628,0.6096152,0.0106102,0.1980982,0.03742183,0.1037026],"study_design_scores_gemma":[0.0004717121,0.0001371033,0.00009736192,0.0002257603,0.0004023183,0.00004412226,0.0005829415,0.5747917,0.0001249336,0.0002540092,0.4225993,0.0002687617],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.04392669,0.006232932,0.2013736,0.0001251296,0.0005922816,0.002458576,0.006383073,0.001588374,0.7373193],"genre_scores_gemma":[0.7659613,0.0006729937,0.003286078,0.00004196899,0.0003849556,3.439137e-7,0.02250193,0.002395982,0.2047545],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.7220346,"threshold_uncertainty_score":0.9999971,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09183560593990077,"score_gpt":0.2843493602870238,"score_spread":0.1925137543471231,"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."}}