{"id":"W2772904413","doi":"10.1109/tnnls.2017.2770167","title":"An Algorithm for Clustering Categorical Data With Set-Valued Features","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Science Foundation of Shanxi Province; Simon Fraser University; Kungliga Tekniska Högskolan; Shanxi Scholarship Council of China; National Natural Science Foundation of China","keywords":"Cluster analysis; Computer science; Categorical variable; Data mining; Initialization; Algorithm; Set (abstract data type); CURE data clustering algorithm; Canopy clustering algorithm; Data set; Determining the number of clusters in a data set; Data stream clustering; Heuristic; Correlation clustering; Pattern recognition (psychology); Artificial intelligence; Machine learning","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000533518,0.0002457973,0.0002923835,0.00008850164,0.00223993,0.001477884,0.001557202,0.0001183521,9.214853e-7],"category_scores_gemma":[0.00001191942,0.0001979391,0.00003891634,0.0001132177,0.0001083815,0.001244385,0.00003209135,0.0008343197,0.000001170805],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004161553,"about_ca_system_score_gemma":0.00002891895,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003251664,"about_ca_topic_score_gemma":0.00007320979,"domain_scores_codex":[0.9979032,0.0002147188,0.0002148231,0.0008254224,0.0003212537,0.0005206399],"domain_scores_gemma":[0.9977418,0.0002333363,0.0001573778,0.001540948,0.000096933,0.0002295948],"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":[0.00002727409,0.0000214964,0.00001096477,0.00002174372,0.00002585278,0.00002168979,0.0001102391,0.7203243,0.00001618476,0.00001745608,0.00001917048,0.2793836],"study_design_scores_gemma":[0.0006577358,0.0006091114,0.0002181303,0.00005316704,0.00001487239,0.0002353054,0.000106194,0.997411,0.00001384191,0.000003786263,0.0004193842,0.0002575275],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001395964,0.0001451729,0.9966058,0.0001631484,0.000975984,0.0004526063,0.00001241792,0.0002321738,0.0000167997],"genre_scores_gemma":[0.9650434,0.00003292629,0.03366124,0.00002702639,0.0003520124,0.00008735264,0.00001058355,0.00004176789,0.0007436929],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9636474,"threshold_uncertainty_score":0.9995587,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04585140131797229,"score_gpt":0.3288737313040195,"score_spread":0.2830223299860473,"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."}}