{"id":"W2258817502","doi":"10.1016/j.knosys.2016.01.048","title":"Fuzzy C-Means clustering of incomplete data based on probabilistic information granules of missing values","year":2016,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Rough Sets and Fuzzy Logic","field":"Computer Science","cited_by":110,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Cluster analysis; Fuzzy clustering; Probabilistic logic; Data mining; Missing data; Computer science; CURE data clustering algorithm; Determining the number of clusters in a data set; Constrained clustering; Canopy clustering algorithm; Correlation clustering; Data stream clustering; Mathematics; 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":[0.001198653,0.0002157486,0.0004366002,0.000306432,0.0001083287,0.0001064526,0.001537983,0.00008686139,0.000003178829],"category_scores_gemma":[0.0003181911,0.0001419118,0.00008190847,0.0003922606,0.0001270295,0.0007328824,0.0002520601,0.00007048159,0.00004045218],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008643077,"about_ca_system_score_gemma":0.0002529256,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007474434,"about_ca_topic_score_gemma":0.0000232882,"domain_scores_codex":[0.9978101,0.0002966546,0.0008371841,0.0003599587,0.0004162312,0.0002798655],"domain_scores_gemma":[0.9967076,0.0006726258,0.0004890786,0.001736405,0.0002984442,0.00009589209],"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":[0.0005834556,0.002162742,0.005792515,0.01962145,0.0002196354,0.00002719169,0.004965234,0.1486059,0.01135644,0.09093697,0.007220405,0.7085081],"study_design_scores_gemma":[0.001048732,0.000259199,0.0007448485,0.001762204,0.00001508513,0.000003020432,0.00003120882,0.9926625,0.0005433291,0.001077179,0.001629113,0.000223566],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001898325,0.0001729512,0.9870976,0.0002981849,0.0008540432,0.0005309412,0.0001482968,0.0001325883,0.008867129],"genre_scores_gemma":[0.9816223,0.000001549507,0.01818866,0.00003353056,0.00007798363,0.00001828108,0.00003501772,0.00001135677,0.00001127064],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.979724,"threshold_uncertainty_score":0.5786994,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0507020901633157,"score_gpt":0.2688525495052719,"score_spread":0.2181504593419562,"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."}}