A comparative study on the effect of feature selection on classification accuracy

• DOI: 10.1016/j.protcy.2012.02.068
• Publication Date: 2012-05-23T15:08:32Z
• Authors: Esra Mahsereci Ka...; Selma Ayşe Özel; Turgay İbrikçi
• Keywords: C4.5 algorithm; Multilayer perceptron; Feature (linguistics); Perceptron

Feature selection has become interest to many research areas which deal with machine learning and data mining, because it provides the classifiers be fast, cost-effective, more accurate. In this paper effect of feature on accuracy NaïveBayes, Artificial Neural Network as Multilayer Perceptron, J48 decision tree is presented. These are compared fifteen real datasets pre-processed methods. Up 15.55% improvement in classification observed, Perceptron appears most sensitive classifier selection.