{"id":"W2017733151","doi":"10.1109/iccit.2007.148","title":"Investigating the Performance of Naive- Bayes Classifiers and K- Nearest Neighbor Classifiers","year":2007,"lang":"en","type":"article","venue":"2007 International Conference on Convergence Information Technology (ICCIT 2007)","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":151,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Naive Bayes classifier; Artificial intelligence; k-nearest neighbors algorithm; Computer science; Machine learning; Bayes error rate; Classifier (UML); Bayes classifier; Random subspace method; Pattern recognition (psychology); Bayesian probability; Bayes' theorem; Data mining; Support vector machine","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":[0.0008000145,0.0002155596,0.0001780277,0.0006637947,0.0002310276,0.0002067805,0.001698264,0.0001760831,0.000231968],"category_scores_gemma":[0.0002303654,0.0001761392,0.00004273883,0.0006547805,0.0005508193,0.002674911,0.0004361249,0.0003947424,0.0001762815],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007018246,"about_ca_system_score_gemma":0.0001079189,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002652344,"about_ca_topic_score_gemma":0.000007847227,"domain_scores_codex":[0.9981056,0.00002151417,0.0006687075,0.0002748464,0.0005676798,0.0003616686],"domain_scores_gemma":[0.9984016,0.0001032873,0.0005095959,0.0004442615,0.0004537514,0.0000874744],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002218383,0.00003279325,0.03007096,0.0000339751,0.00006304773,0.000003141577,0.0003942575,0.0000544426,0.0003340449,0.7916552,0.003320423,0.1740155],"study_design_scores_gemma":[0.001071234,0.0004974811,0.05739089,0.0002540375,0.00002033225,0.00003877027,0.003352001,0.8694682,0.01101956,0.008314503,0.04786939,0.000703607],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3773804,0.00008348643,0.5219361,0.0138929,0.004943113,0.0008704689,0.00005337735,0.0006370599,0.08020312],"genre_scores_gemma":[0.988596,0.0002730399,0.009461794,0.001168319,0.00006174424,0.00002063884,0.00003425639,0.000006366062,0.0003778098],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8694137,"threshold_uncertainty_score":0.7182748,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02490013171729916,"score_gpt":0.2604650408833423,"score_spread":0.2355649091660431,"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."}}