{"id":"W2965409371","doi":"10.1109/isie.2019.8781307","title":"Model-Based Hierarchical Clustering for Categorical Data","year":2019,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Cluster analysis; Bhattacharyya distance; Categorical variable; Computer science; Hierarchical clustering; Brown clustering; Artificial intelligence; Multinomial distribution; Binary data; Data mining; Pattern recognition (psychology); Fuzzy clustering; Consensus clustering; Mixture model; CURE data clustering algorithm; Machine learning; Binary number; Mathematics; Statistics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004193047,0.0007872015,0.001410731,0.00379991,0.001201223,0.00156746,0.002382873,0.001109077,0.001699243],"category_scores_gemma":[0.01271391,0.0005692814,0.001983045,0.004136723,0.0009544684,0.002147019,0.001960751,0.0015513,0.001275982],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002084686,"about_ca_system_score_gemma":0.002448563,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01365052,"about_ca_topic_score_gemma":0.01907051,"domain_scores_codex":[0.995005,0.002160516,0.0002985098,0.0007808284,0.001535575,0.0002196368],"domain_scores_gemma":[0.9959156,0.001562009,0.0004254508,0.0009138079,0.001061698,0.0001213254],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001582861,0.0001405545,0.004001213,0.0003926607,0.0004216292,0.0001223178,0.000787374,0.5088549,0.005853876,0.1204532,0.00886824,0.3499457],"study_design_scores_gemma":[0.00001257487,0.00003004279,0.0008291096,0.00002448133,0.00002547159,0.00006481197,0.00007449355,0.930818,0.001230857,0.06411872,0.002734789,0.00003664598],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00242156,0.0001798552,0.9964645,0.00007077873,0.00001234262,0.00004426083,0.0001308082,0.0003694882,0.0003064655],"genre_scores_gemma":[0.1301637,0.0003545822,0.8665397,0.0001014686,0.0000367595,0.0002797565,0.001353415,0.0001590509,0.00101144],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01365052,"threshold_uncertainty_score":0.02714211,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07657443905414395,"score_gpt":0.3270737095638069,"score_spread":0.250499270509663,"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."}}