Renyi's entropy as an index of diversity in simple-stage cluster sampling
Information Sciences: an International Journal
Feature Subset Selection Using a Genetic Algorithm
IEEE Intelligent Systems
Hi-index | 0.00 |
It is an important subject to extract feature genes from microarray expression profiles in the study of computational biology. Based on an improved genetic algorithm (IGA), a feature selection method is proposed in this paper to find a feature gene subset so that the genes related to diseases could be kept and the redundant genes could be eliminated more effectively. In the proposed method, the information entropy is used as a separate criterion, and the crossover and mutation operators in the genetic algorithm are improved to control the number of the feature genes in the subset. After analyzing the microarray expression data, the artificial neural network (ANN) is used to evaluate the feature gene subsets obtained in different parameter conditions. Simulation results show that the proposed method can be used to find the optimal or quasi-optimal feature gene subset with more useful and less redundant information.