Hybrid feature selection method using gene expression data

Gene expression profiles, which represent the state of a cell at a molecular level, have great potential as a medical diagnosis tool. Compared to the number of genes involved available training data sets generally have a fairly small sample size in cancer type classification. These training data limitations constitute a challenge to certain classification methodologies. The gene (feature) selection can extract genes which influence classification accuracy effectively, to eliminate the useless genes, and to improve the calculate performance and the classification accuracy. This paper presents hybrid feature selection method - Taguchi-Genetic algorithm to find optimal feature subset, to appraise feature set using K-nearest neighbor with leave-one-out cross-validation based on Euclidean distance calculation. Experimental results show that our method simplifies features effectively and obtains a higher classification accuracy compared to other classification methods from the literature.