Improved Multiobjective Binary Biogeography Based Optimization using CVM for Feature Selection Using Gene Expression Data

Gene expression data play an important role in the development of efficient cancer diagnoses and classification. The genes identified are subsequently used to classify independent test set samples. The different feature selection methods are investigated and most frequent features are selected among all methods. This paper provides gene selection strategies for multiclass classification that can be used to reach high prediction accuracies with a tiny low number of selected genes. In this paper, a multi-objective biogeography based optimization method is proposed to select the small subset of informative gene relevant to the classification. In the proposed algorithm, firstly, the KNN (K’s Nearest Neighbour) algorithm is used to choose the 60 top gene expression data. Secondly, to make biogeography based optimization suitable for the discrete problem, binary biogeography based optimization, as called BBBO, is proposed based on a binary migration model and a binary mutation model. Then Core Vector Machine (CVM), is proposed by integrating the nondominated sorting method and the crowding distance method into the BBBO framework. In order to show the effective and efficiency of the algorithm, the proposed algorithm is tested on ten gene expression dataset benchmarks. Experimental results demonstrate that the proposed method is better or at least comparable with previous particle swarm optimization (PSO) algorithm and support vector machine (SVM) from literature when considering the quality of the solutions obtained.