{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001359528,0.0001717244,0.0004234931,0.0001451788,0.00008667685,0.000228345,0.001563195,0.00005693714,0.000001098661],"category_scores_gemma":[0.0007806861,0.0001682708,0.00001037008,0.0003336209,0.00005996576,0.0006011096,0.002909433,0.0004810266,0.00000939965],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000107117,"about_ca_system_score_gemma":0.00006203075,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001897275,"about_ca_topic_score_gemma":0.0005908677,"domain_scores_codex":[0.9972825,0.0002679074,0.0003030888,0.0007500186,0.001001245,0.0003952508],"domain_scores_gemma":[0.9978405,0.0001788096,0.00006778325,0.0015519,0.0001215215,0.0002395502],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004827943,0.03187959,0.8636237,0.0002435435,0.0003874583,0.0005972164,0.01910749,0.00197927,0.001824261,0.0002853788,0.0003865876,0.07920274],"study_design_scores_gemma":[0.002137215,0.0009779115,0.08587564,0.0001654021,0.00001857557,0.000004503942,0.0008618334,0.9081994,0.0007884608,0.0005243316,0.00009685096,0.0003499153],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8611459,0.0002131435,0.1353776,0.001318403,0.00008157251,0.001013372,0.00002034751,0.0002453682,0.0005843471],"genre_scores_gemma":[0.9568639,0.000007065973,0.04293545,0.0000598997,0.00004276871,0.00002637491,0.000004790929,0.00001388652,0.00004584976],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9062201,"threshold_uncertainty_score":0.6861886,"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."}}