An Analytical Comparison on Filter Feature Extraction Method in Data Mining using J48 Classifier

Abstract

The feature selection approach provides improved prediction and minimizes the computation time. Due to the higher numbers of features the understanding of the data in pattern recognition becomes difficult sometimes. That's why researchers have used different feature selection techniques with the single classifiers in their intrusion detection system to build up a model which gives a better accuracy and prediction performance. In this paper, we provide a comparative analysis with the feature selection approach in WEKA machine learning tool using the J48 classifier. The research work show the comparison of the performance of single J48 classifier with filter methods. The prediction performance may differ marginally in some cases but with the removal of irrelevant features time complexity can be easily ignored and a better prediction rate is guaranteed.

Machine Learning Techniques for Diabetes Prediction: A Comparative Analysis

“…Feature selection, as a component of dimensional reduction, aims to eliminate redundant features and identify an optimal subset from the dataset to build highly accurate models [23]. In this research, two methods were employed: CfsSubsetEval and WrapperSubsetEval.…”

“…The CfsSubsetEval, also known as Correlation-based feature selection (CFS), selects features highly correlated with the class but uncorrelated with each other [24]. In the CFS method, Genetic Search is one of the search techniques utilized, implementing a search based on genetic algorithms [23]. WrapperSubsetEval, on the other hand, employs an induction algorithm as an evaluation function for identifying a good feature subset, with accuracy estimation techniques measuring the accuracy of induced classifiers [25], [26].…”