Feature Selection techniques are generally employed to remove the inessential attributes before machine learning technique could be applied. It thus plays an extremely important role by eliminating the unnecessary features that do not contribute and sometimes degrade the performance and prediction accuracy of the machine learning technique. With the growth of dimensionality of data, Feature Selection becomes even more important because it helps to reduce the dimensions of data and hence decreases the requisite memory and computational complexity of the machine learning techniques. Support vector machine-recursive feature elimination (SVM-RFE) has proven to be an efficient wrapper feature selection technique which continues to be widely utilized in many applications, especially in classification of gene expression data. From the perspective of this data, not only the precision in classification but also the stability of Feature Selection method plays an important role. Nonetheless, the topic of stability is ignored in study of feature selection algorithms. To improve the stability of RFE method, a fusion of Information Gain and RFE (IG-RFE-SVM) method is proposed in this paper. Experimental studies show that IG-RFE-SVM outperforms SVM-RFE method in terms of stability
A Novel Feature Selection Method for Gene Expression Data Based on Samples Localization
