{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002982213,0.0001399543,0.0001284561,0.0001590348,0.0000924471,0.0002263316,0.001289257,0.0001063784,0.00006427953],"category_scores_gemma":[0.00002708956,0.0001064586,0.00004902712,0.0003437804,0.00006544265,0.0007117941,0.00009044887,0.000142733,0.0001821515],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004206471,"about_ca_system_score_gemma":0.00008722297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004395471,"about_ca_topic_score_gemma":0.000004253704,"domain_scores_codex":[0.9987597,0.00005545859,0.0001610599,0.0004763247,0.000318206,0.0002291942],"domain_scores_gemma":[0.998611,0.00006903789,0.00006536342,0.001116133,0.00007194938,0.00006653186],"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":[0.00001679898,0.0004997175,0.003662451,0.00001659734,0.0000163364,0.000008519503,0.0001339546,0.0004638582,0.04390447,0.1179217,0.003794518,0.8295611],"study_design_scores_gemma":[0.0003273242,0.0006921973,0.003701776,0.000005918032,0.000002067873,8.852537e-7,0.0000889684,0.946268,0.03492269,0.006587207,0.007151601,0.0002514177],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01446781,0.00003325118,0.9610367,0.009730952,0.000508813,0.0004131264,0.000004926337,0.002653284,0.01115107],"genre_scores_gemma":[0.8599024,0.000005153259,0.1380173,0.001261394,0.00001667275,0.00002272109,0.000003976234,0.000005770428,0.0007646526],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9458041,"threshold_uncertainty_score":0.4341256,"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."}}