{"id":"W4402989891","doi":"10.1016/j.apenergy.2024.124584","title":"K-PCD: A new clustering algorithm for building energy consumption time series analysis and predicting model accuracy improvement","year":2024,"lang":"en","type":"article","venue":"Applied Energy","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Victoria; University of British Columbia","funders":"National Natural Science Foundation of China","keywords":"Cluster analysis; Time series; Series (stratigraphy); Energy consumption; Algorithm; Computer science; Data mining; Consumption (sociology); Engineering; Artificial intelligence; Machine learning","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":[0.0002130639,0.0002326187,0.0003251886,0.0003191939,0.000246944,0.0006327495,0.0003014904,0.00007954836,0.00001968229],"category_scores_gemma":[0.000009113414,0.0002219716,0.0001661565,0.0006744187,0.00003137161,0.0005650889,0.0004117724,0.0000665839,0.000001601201],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006050875,"about_ca_system_score_gemma":0.00005756285,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000353701,"about_ca_topic_score_gemma":0.000098639,"domain_scores_codex":[0.9983348,0.000009904171,0.0003797898,0.0006918075,0.0002051596,0.0003785648],"domain_scores_gemma":[0.9992448,0.0001296918,0.0001202944,0.0003270876,0.00004006119,0.0001380341],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005548103,0.000009691146,0.000003275515,0.00002412823,0.0005044635,0.000002120078,0.0003127655,0.06087795,0.008296194,0.06908113,0.0001162271,0.8607665],"study_design_scores_gemma":[0.0001579794,0.00004178547,0.000004291734,0.00002174991,0.0002816784,0.000005297885,0.00003759345,0.9880099,0.004584849,0.003333276,0.00327974,0.0002418679],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001484746,0.0005980513,0.9970677,0.0001265581,0.00007032359,0.00006279341,0.00001035826,0.0002882566,0.0002912529],"genre_scores_gemma":[0.4214694,0.000270837,0.5758556,0.0001473111,0.0002959275,0.0001083189,0.00004704341,0.00003673834,0.001768914],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.927132,"threshold_uncertainty_score":0.9051738,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01165233932418576,"score_gpt":0.2293212431663147,"score_spread":0.217668903842129,"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."}}