Cancer diagnosis is one of the emerging applications in microarray gene expression data. Feature selection plays a crucial role because of the huge dimensionality and less training and testing samples. Finding a small subset of significant genes from a large set of gene expression data is a challenging task. This paper presents the usage of genetic algorithm as a tool to determine the informative gene subset and uses Extreme Learning Machines classifier to determine the classifier accuracy. Experiments are carried out on two microarray datasets and the results reveal that the proposed approach produces better classification rate compared to Support Vector Machines and nearest neighbor classifier. © 2017 IEEE.
cited By 0; Conference of 4th International Conference on Advanced Computing and Communication Systems, ICACCS 2017 ; Conference Date: 6 January 2017 Through 7 January 2017; Conference Code:130103
C. Arunkumar, Sooraj, M. P., and Ramakrishnan, S. M. P., “Finding expressed genes using genetic algorithm and extreme learning machines”, in 2017 4th International Conference on Advanced Computing and Communication Systems, ICACCS 2017, 2017.