{"id":"W2971394479","doi":"10.1109/codit.2019.8820298","title":"An Improved K-medoids Algorithm Based on Binary Sequences Similarity Measures","year":2019,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Agence Nationale de la Recherche","keywords":"Cluster analysis; Computer science; Medoid; Similarity (geometry); Binary number; Euclidean distance; Data mining; k-medoids; Binary data; Algorithm; Fuzzy clustering; CURE data clustering algorithm; Artificial intelligence; Mathematics","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":[0.001754493,0.001165114,0.002280981,0.002429611,0.001023961,0.001650605,0.002517302,0.001857062,0.00245804],"category_scores_gemma":[0.005130092,0.0006530779,0.001881391,0.002949277,0.0008611021,0.002345693,0.001622064,0.00163891,0.001903719],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009576739,"about_ca_system_score_gemma":0.001615643,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007868059,"about_ca_topic_score_gemma":0.004443815,"domain_scores_codex":[0.9976692,0.0006361877,0.0002147088,0.000591421,0.0007696602,0.000118992],"domain_scores_gemma":[0.9984653,0.0005301878,0.0001471392,0.0001497101,0.0006379,0.00006990568],"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":[0.0005304398,0.000128517,0.001795615,0.0004774379,0.0002410042,0.0001389958,0.0005316601,0.4215258,0.01330077,0.0229889,0.006871986,0.5314688],"study_design_scores_gemma":[0.00004175253,0.000103564,0.0004180965,0.00003650131,0.00003559501,0.0001527607,0.00008980893,0.9801881,0.003661776,0.009295193,0.005918838,0.00005808114],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004282881,0.0004125761,0.9938084,0.0001108743,0.00008534918,0.00005694294,0.00006682589,0.000275286,0.000900758],"genre_scores_gemma":[0.124882,0.0006499526,0.8701501,0.0001664161,0.0001182159,0.0002410226,0.0004962447,0.000146352,0.003149697],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007868059,"threshold_uncertainty_score":0.01564449,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01801952349129417,"score_gpt":0.2617936893726659,"score_spread":0.2437741658813718,"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."}}