2-Dimensional Homogeneous Distributed Ensemble Feature Selection

Abstract

Big data can be seen from the number of its samples and features. The selection of the most representative feature is an important task in Uig data analysis to reduce the dimension. The feature selection method is used to handle this problem. In this research, a homogeneous distributed ensemble feature selection method with 2-dimensional partition is used as new approach of feature selection. The results showed that the proposed method can improve the accuracy from the other feature selection method with an increase of 2% for several datasets. In addition, it also speeds up the computation to almost two times faster.