Filter-Based Feature selection for microarray data using Improved Binary Gravitational Search Algorithm

Today, high-dimensional data have become one of the most important challenges in machine learning. Among thousands of features which exist in such data, some are redundant or unrelated and selecting a few of them improves classifier performance. Micro-array data which are one of the most important high-dimensional data in medicine have a large number of features and a few number of samples. Thus, old simple methods can be used to select features of such data effectively. Among several methods which have been proposed for selecting features of high-dimensional data, Swarm intelligence-based methods have attracted attentions more than ever. These methods are suitable to solve time-consuming and complex problems such that they search near-optimal solution with desirable computational cost. In this paper, a filter based Swarm intelligence-based search method based on Improved Binary Gravitational Search Algorithm (IBSGA) is proposed to integrate filter approaches with Swarm intelligence-based methods to improve feature selection process in micro-array data. The proposed method is applied to 5 high-dimensional micro-array databases and the obtained results are compared with one of the up-to-date methods used for feature selection in micro-array data. Experimental results verify efficiency of the proposed algorithm.