Microarray Cancer Gene Feature Selection Using Spider Monkey Optimization Algorithm and Cancer Classification using SVM

The microarray cancer gene expression data is used for classifying the cancer disease. This work focuses on two objectives, first is the cancer gene feature selection by employing a new swarm intelligence technique, namely Spider Monkey Optimization algorithm in order to minimize the number of features in cancer data. The second objective is to classify cancer data by employing the subset of gene features obtained by the first objective. The proposed method has experimented with various benchmark cancer datasets and it reveals that the proposed method outperforms all other existing techniques in terms of the minimum number of features and maximum classification accuracy. (C) 2018 The Authors. Published by Elsevier B.V.