{"id":"W4291653299","doi":"10.1109/access.2022.3198992","title":"A Distance Metric for Uneven Clusters of Unsupervised K-Means Clustering Algorithm","year":2022,"lang":"en","type":"article","venue":"IEEE Access","topic":"Internet Traffic Analysis and Secure E-voting","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; University of Calgary","keywords":"Metric (unit); Cluster analysis; Centroid; Euclidean distance; Silhouette; Mathematics; Algorithm; k-medians clustering; Computer science; Cluster (spacecraft); Distance measures; Pattern recognition (psychology); Artificial intelligence; Data mining; Fuzzy clustering; Canopy clustering algorithm","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0005060907,0.0001423706,0.0002889557,0.0002711534,0.0002256438,0.0001530556,0.002177717,0.00002836898,0.00002850495],"category_scores_gemma":[0.00002425661,0.0001407651,0.0002051105,0.001202457,0.00002596661,0.0004468423,0.0005252084,0.0001413663,0.000001539968],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009297935,"about_ca_system_score_gemma":0.00004884429,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006531233,"about_ca_topic_score_gemma":0.00006789506,"domain_scores_codex":[0.998385,0.00008258913,0.0004004909,0.0004139745,0.0004088338,0.0003091824],"domain_scores_gemma":[0.9991539,0.0001727646,0.0002072247,0.0002996197,0.0001086692,0.00005788315],"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":[0.00005225954,0.0002871261,0.0002351236,0.0001697977,0.0002889335,0.00003092458,0.004589861,0.7916382,0.0001398281,0.01886871,0.003142212,0.180557],"study_design_scores_gemma":[0.0004282052,0.00008039725,0.00005350866,0.00001308149,0.00002266896,0.000005289995,0.0001434656,0.9960398,0.0002783729,0.00004972154,0.00271701,0.0001684719],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01010621,0.0001268523,0.9882697,0.0001873978,0.0008195372,0.0002299786,0.00002145486,0.00006970141,0.0001690965],"genre_scores_gemma":[0.9752269,0.000003917952,0.02411431,0.0002606692,0.00008055811,0.00007669573,0.000007308645,0.00001493061,0.0002146984],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9651207,"threshold_uncertainty_score":0.5740235,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02490290743496951,"score_gpt":0.2805617299968341,"score_spread":0.2556588225618646,"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."}}