{"id":"W2270192120","doi":"10.1371/journal.pone.0144059","title":"A Comparison Study on Similarity and Dissimilarity Measures in Clustering Continuous Data","year":2015,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":408,"is_retracted":false,"has_abstract":true,"ca_institutions":"IBM (Canada)","funders":"Universiti Malaya","keywords":"Similarity (geometry); Cluster analysis; Computer science; Data mining; Benchmark (surveying); Distance measures; Similarity measure; Measure (data warehouse); Cluster (spacecraft); Pattern recognition (psychology); Artificial intelligence; Geography","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01797167,0.0008908915,0.001196288,0.008430123,0.001010342,0.00304046,0.001397586,0.001454617,0.00111979],"category_scores_gemma":[0.09682115,0.0003037016,0.001241274,0.01063203,0.00148808,0.005809433,0.001706723,0.001202843,0.0003054438],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001719355,"about_ca_system_score_gemma":0.001092045,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001772873,"about_ca_topic_score_gemma":0.001528104,"domain_scores_codex":[0.9803352,0.008104173,0.002093108,0.002380759,0.006695054,0.0003917561],"domain_scores_gemma":[0.9195517,0.05883326,0.003292621,0.00502971,0.01228326,0.001009439],"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":[0.002176227,0.0005716927,0.08183413,0.004355904,0.002192463,0.0004226052,0.002494975,0.0566669,0.01142934,0.06501206,0.005745935,0.7670978],"study_design_scores_gemma":[0.0003522889,0.006583017,0.1498175,0.001585221,0.00168044,0.003230102,0.006019058,0.6854444,0.03097709,0.0716337,0.04213445,0.0005427367],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4486104,0.04321476,0.4883186,0.001639057,0.0009752794,0.0005503662,0.0009025484,0.0005570646,0.01523191],"genre_scores_gemma":[0.7592854,0.005580308,0.2324036,0.0001403576,0.0002876577,0.0002409717,0.001088006,0.0001050228,0.0008685301],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01797167,"threshold_uncertainty_score":0.09504437,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4315200459840546,"score_gpt":0.4023074041110184,"score_spread":0.02921264187303624,"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."}}