{"id":"W2005934890","doi":"10.1007/s10618-013-0336-8","title":"Clustering categorical data in projected spaces","year":2013,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Cluster analysis; Categorical variable; Computer science; Data mining; Outlier; CURE data clustering algorithm; Curse of dimensionality; Clustering high-dimensional data; Correlation clustering; Canopy clustering algorithm; Data stream clustering; Anomaly detection; Probabilistic logic; Set (abstract data type); Artificial intelligence; Pattern recognition (psychology); 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003565447,0.0006601155,0.00144292,0.003296275,0.0009856101,0.004170629,0.001682823,0.0008642421,0.00182067],"category_scores_gemma":[0.01966585,0.0004967592,0.001414593,0.005951377,0.001869137,0.003861298,0.00321019,0.002012498,0.0006795465],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001066883,"about_ca_system_score_gemma":0.00124046,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002782043,"about_ca_topic_score_gemma":0.002104797,"domain_scores_codex":[0.9939646,0.002668276,0.000378107,0.0008925467,0.001863327,0.0002331087],"domain_scores_gemma":[0.9905229,0.00468479,0.00065285,0.001505294,0.00226564,0.0003685236],"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":[0.0006760267,0.0003444984,0.01595098,0.0007624481,0.0004116018,0.000255947,0.001876909,0.2193246,0.006321073,0.2825914,0.005340605,0.4661439],"study_design_scores_gemma":[0.00002360792,0.0001145821,0.002372232,0.00006407911,0.00003795208,0.0001662636,0.0005937868,0.7229326,0.001872669,0.268724,0.003053106,0.00004528843],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02668364,0.0002873314,0.9716309,0.0002125753,0.00003736151,0.00005623259,0.0002977176,0.0002017069,0.0005925907],"genre_scores_gemma":[0.4011313,0.0008362117,0.5930611,0.0001097908,0.0001611146,0.0003080411,0.002352373,0.0001089263,0.001931086],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004170629,"threshold_uncertainty_score":0.01885611,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09257415986957443,"score_gpt":0.3536923389834265,"score_spread":0.261118179113852,"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."}}