Two-Stage Gene Selection in Microarray Dataset Using Fuzzy Mutual Information and Binary Particle Swarm Optimization

Abstract

Many data in the classification problem contain a number of additional and irrelevant attributes (genes) that affect the accuracy of the classification. Many evolutionary algorithms are used to determine the feature and reduce dimensional patterns such as particle swarm optimization (PSO), after converting it from continuous space to a discrete space. In this research, a method of gene selection was proposed through two consecutive stages: in the first stage, the fuzzy mutual information (FMI) method is used to determine the most important genes selected through a fuzzy model that was built based on the data size. In the second stage, the BPSO algorithm is used to reduce and determine a specific number of genes affecting the process of classification, which came from the first stage. The proposed algorithm, FMI_BPSO, describes efficiency and effectiveness by obtaining a higher classification accuracy and a small number of selected genes compared to other competitor algorithms.