{"id":"W2613364025","doi":"10.1109/icit.2017.7915506","title":"Proportional data clustering using K-means algorithm: A comparison of different distances","year":2017,"lang":"en","type":"article","venue":"","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Mitacs; Concordia University","keywords":"Cluster analysis; Silhouette; Initialization; Computer science; CURE data clustering algorithm; Divergence (linguistics); Correlation clustering; Metric (unit); Single-linkage clustering; k-medians clustering; Pattern recognition (psychology); Artificial intelligence; Confusion matrix; Canopy clustering algorithm; Fuzzy clustering; Data stream clustering; Data mining; 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":[0.0001470093,0.00007559859,0.0001476463,0.00002931358,0.0002444499,0.0002112613,0.001868712,0.00002528312,0.00001407094],"category_scores_gemma":[0.00002402342,0.00005554481,0.00002584144,0.00004065223,0.0001021725,0.0007492911,0.0008932058,0.00005549112,0.000001655172],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001932325,"about_ca_system_score_gemma":0.00003464888,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005652252,"about_ca_topic_score_gemma":0.00001748936,"domain_scores_codex":[0.999104,0.00001602838,0.0002463323,0.0002574188,0.000265476,0.000110713],"domain_scores_gemma":[0.9982591,0.00001589331,0.0002879535,0.001324755,0.00007694845,0.00003532852],"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":[0.00001017202,0.0004958711,0.02259214,0.00009985694,0.0000433476,0.000004231199,0.000329003,0.000008511324,0.01754609,0.03631765,0.0005781094,0.921975],"study_design_scores_gemma":[0.00007094678,0.00002177404,0.007403553,0.0000272589,0.000004117581,0.000002295792,0.00002460327,0.9542691,0.03661558,0.0009225139,0.0005536053,0.00008468256],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001422135,0.00004178753,0.9968671,0.0003405827,0.0001155058,0.00009347443,0.00001114791,0.00008469055,0.001023571],"genre_scores_gemma":[0.6786681,0.00001078357,0.3211026,0.000009114628,0.00002850464,0.000002085589,0.000008131632,0.000002802998,0.0001677864],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9542606,"threshold_uncertainty_score":0.3472564,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.160489720397552,"score_gpt":0.3944594605026029,"score_spread":0.2339697401050509,"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."}}