{"id":"W1991530504","doi":"10.1016/j.eswa.2014.12.002","title":"Nearest neighbor classification of categorical data by attributes weighting","year":2014,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Rough Sets and Fuzzy Logic","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Sherbrooke","funders":"National Natural Science Foundation of China","keywords":"Categorical variable; Weighting; k-nearest neighbors algorithm; Computer science; Artificial intelligence; Data mining; Pattern recognition (psychology); Subspace topology; Feature (linguistics); Feature selection; Decision tree; Machine learning","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":[0.002258196,0.0003087081,0.001180953,0.003083588,0.0006063614,0.001354108,0.001019024,0.0007562811,0.001201713],"category_scores_gemma":[0.009723048,0.0002102957,0.0009369535,0.002962844,0.0004984537,0.001889461,0.0008548691,0.0007169078,0.0005117143],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005689581,"about_ca_system_score_gemma":0.0006741314,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003124375,"about_ca_topic_score_gemma":0.00299409,"domain_scores_codex":[0.9967704,0.000940216,0.0002943629,0.0004370386,0.001416449,0.000141604],"domain_scores_gemma":[0.9973559,0.001091547,0.0001687787,0.0004485091,0.0008598244,0.00007534297],"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":[0.0006068594,0.0003778173,0.009280239,0.0002736858,0.0002078331,0.0001334678,0.0003651866,0.04969173,0.009242394,0.01804452,0.00412365,0.9076527],"study_design_scores_gemma":[0.00003837176,0.0002169137,0.005328931,0.00005753723,0.0001243587,0.0002321717,0.0003188776,0.9281812,0.006305557,0.05558041,0.003549849,0.00006586096],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1115159,0.0008571491,0.8840722,0.0001545027,0.0001719954,0.0001047301,0.0002829292,0.0003146263,0.002525903],"genre_scores_gemma":[0.6406489,0.0004808352,0.3549272,0.00005824374,0.0001006079,0.0001413989,0.0009646345,0.00005880157,0.002619383],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003124375,"threshold_uncertainty_score":0.01194263,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04317540440687309,"score_gpt":0.270307934158104,"score_spread":0.2271325297512309,"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."}}