{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003585944,0.001213573,0.001516828,0.003889689,0.001742591,0.002487354,0.002465426,0.001770905,0.001462389],"category_scores_gemma":[0.01765797,0.0004680956,0.001110964,0.004068968,0.001373794,0.003510094,0.002861171,0.002005791,0.0009827591],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001980508,"about_ca_system_score_gemma":0.002287806,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004722003,"about_ca_topic_score_gemma":0.004722691,"domain_scores_codex":[0.9928894,0.001888898,0.0008373753,0.00123841,0.002852121,0.0002936684],"domain_scores_gemma":[0.9930267,0.00201201,0.0006936447,0.0009324996,0.003103094,0.0002320686],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005141362,0.0001752152,0.007548971,0.0006565343,0.0003559207,0.0002495712,0.0007296875,0.3804534,0.01448184,0.07684538,0.01438868,0.5036007],"study_design_scores_gemma":[0.00003761105,0.0002130131,0.002305294,0.0000585299,0.00004100028,0.0003801267,0.0002196602,0.9413528,0.01028708,0.02927731,0.01569697,0.000130509],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007637312,0.0004007314,0.9896415,0.0001461863,0.00009238417,0.000130247,0.0001501614,0.0005670745,0.00123441],"genre_scores_gemma":[0.1350899,0.0003192856,0.861517,0.0001144089,0.00008044729,0.0004734313,0.0007877413,0.0002772071,0.001340552],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004722003,"threshold_uncertainty_score":0.01896453,"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."}}