BIOCOMP Study of Classification Accuracy of Microarray Data for Cancer Classification using Hybrid, Wrapper and Filter Feature Selection Method

Microarray analysis are becoming a powerful tool for clinical diagnosis, as they have the potential to discover gene expression patterns that are characteristic for a particular disease. This problem has received increased attention in the context of cancer research, especially in tumor classification. Various feature selection methods and classifier design strategies also have been used and compared. Feature selection is an important preprocessing method for any classification process. Selecting a useful gene subset as a classifier not only decreases the computational time and cost, but also increases classification accuracy. In this study, we applied the correlation-based feature selection method (CFS), which evaluates a subset of features by considering the individual predictive ability of each feature along with the degree of redundancy between them as a filter approach, and three wrappers (J48, Random Forest and Random Trees) to implement feature selection; selected gene subsets were used to evaluate the performance of classification. Experimental results show that by employing the proposed method fewer gene subsets are need to be selected to achieve better classification accuracy.