{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003095641,0.0001333569,0.0002134144,0.00004803124,0.0002034928,0.0001379226,0.00161359,0.00006810025,0.000002616362],"category_scores_gemma":[0.00002628319,0.0000967561,0.00002004817,0.000471606,0.00006481479,0.0003375251,0.0002080671,0.00008417908,0.00004634341],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003110104,"about_ca_system_score_gemma":0.00004974733,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003096307,"about_ca_topic_score_gemma":0.00000750666,"domain_scores_codex":[0.9985256,0.00007791466,0.0003567319,0.0005400884,0.0002848242,0.0002148467],"domain_scores_gemma":[0.9973468,0.0001818727,0.0002486774,0.001988784,0.0001279847,0.0001058755],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000007129649,0.0003557185,0.002879714,0.00007382638,0.00004695137,7.51732e-7,0.0005567673,0.0001170609,0.00764994,0.8755006,0.07801963,0.03479194],"study_design_scores_gemma":[0.000308456,0.00009027098,0.002013646,0.00002523521,0.000008398025,0.00002198918,0.0001460363,0.4159706,0.0002950288,0.000474536,0.5803651,0.0002807831],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000209379,0.0008130723,0.9933747,0.001429064,0.00008219061,0.0004796705,0.00003342593,0.0001423239,0.003436165],"genre_scores_gemma":[0.97273,0.00002549038,0.02614133,0.0000784137,0.0002152701,0.0004733547,0.0002480702,0.0000130884,0.00007502088],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9725206,"threshold_uncertainty_score":0.3945599,"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."}}