{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005709552,0.001476792,0.00180244,0.005582096,0.002063121,0.003114832,0.002806257,0.002009686,0.001715985],"category_scores_gemma":[0.02356978,0.0005311645,0.001287977,0.006579903,0.001252126,0.005586194,0.002757781,0.001285078,0.001032074],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001826119,"about_ca_system_score_gemma":0.001996878,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006132097,"about_ca_topic_score_gemma":0.003912074,"domain_scores_codex":[0.9911451,0.00260692,0.0008082706,0.001729484,0.003419792,0.0002903462],"domain_scores_gemma":[0.9922675,0.003229743,0.0005107743,0.001238442,0.002549573,0.0002039798],"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":[0.001202415,0.000360467,0.005900586,0.0009441643,0.0005504324,0.0001004957,0.0007315518,0.1400451,0.006363738,0.02449955,0.005296065,0.8140053],"study_design_scores_gemma":[0.00008161829,0.0004262617,0.003466394,0.0001156,0.0001270701,0.0004783395,0.0006840875,0.9409319,0.01388172,0.02913573,0.0105034,0.0001679591],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03197892,0.002819682,0.9604173,0.0002697049,0.0002021028,0.0002237724,0.0001709264,0.001333246,0.002584358],"genre_scores_gemma":[0.2000858,0.001336815,0.7954677,0.0001070263,0.00008244855,0.0003157271,0.0006651647,0.0004021202,0.001537197],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006132097,"threshold_uncertainty_score":0.03019542,"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."}}