{"id":"W2583764785","doi":"10.1109/icmla.2016.0089","title":"A Parallel K-Medoids Algorithm for Clustering based on MapReduce","year":2016,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Cluster analysis; Computer science; CURE data clustering algorithm; Data stream clustering; Medoid; Canopy clustering algorithm; Correlation clustering; Data mining; Big data; Algorithm; Scale (ratio); Parallel computing; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003297415,0.0001876538,0.0001711715,0.0001655075,0.0001380648,0.0001123265,0.001125645,0.00006658307,0.0000215814],"category_scores_gemma":[0.0001012829,0.0001236891,0.00009375042,0.0002333151,0.00005608672,0.0004003472,0.0003445099,0.00008596178,0.0001341434],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001412237,"about_ca_system_score_gemma":0.0000888929,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009755586,"about_ca_topic_score_gemma":0.000005315903,"domain_scores_codex":[0.9980581,0.00004573647,0.000210511,0.0006281206,0.0004293761,0.0006282004],"domain_scores_gemma":[0.9982262,0.0005363592,0.0000459158,0.0008782225,0.0001210983,0.0001922444],"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":[0.00001818966,0.00005121674,0.000003212749,0.00001100087,0.000006906688,0.000009510878,0.0000260811,0.002695139,0.001045338,0.001665627,0.0005522458,0.9939156],"study_design_scores_gemma":[0.001455031,0.0003293002,0.00006506882,0.00005208545,0.000001112964,0.000007162185,0.000004707786,0.985575,0.003443393,0.001521822,0.007319031,0.0002263347],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00003345722,0.000009164808,0.9924958,0.004192159,0.0003029233,0.0004282567,0.000008936816,0.0003858941,0.002143368],"genre_scores_gemma":[0.009481573,0.000004627058,0.9821759,0.0005453145,0.0001384887,0.0002594947,9.343212e-7,0.00002696713,0.007366657],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9936892,"threshold_uncertainty_score":0.5043893,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02886828927353668,"score_gpt":0.3075938819899316,"score_spread":0.2787255927163949,"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."}}