RELIEF: Feature Selection Approach

Abstract

Feature subset selection is a technique for reducing the attribute space of a feature set. In other words, it is identifying a subset of features by removing irrelevant or redundant features. A good feature set contains a highly relevant feature which helps to improve the efficiency of the classification algorithms and to classify accurately. Relief is a feature selection algorithm for random selection of instances for feature weight calculation. The Relief algorithm adopts the random selection of instances for weight estimation. It uses the Monte Carlo Approaches for randomization selection of instances in the Relief. The efficiency and effectiveness of proposed algorithm is evaluated with Cotton Disease  data sets  provided by cotton research  station  and WEKA tool. Naí¯ve Bayes and J48 are used as the classifiers. The classification results, in terms of classification accuracy and size of  feature  subspace to show the performance of the Relief algorithm.