International Journal of Engineering and Technology

Microarray data studies produce large number of data and in order to analyze such large micro array data lies on Data mining or Statistical Analysis. Our objective is to classify the micro array gene expression data. Usually before going for the classification the dimensionality reduction will be performed on the micro array gene expression dataset. A statistical approach for the extraction of the gene has been proposed. The drawback in the statistical analysis is that, it doesn’t identify the important genes. Here for the classification process we use k-nearest neighbor and SVM and Naïve Bayesian classifiers. From the experimental result our proposed classifiers show increase in the efficiency and accuracy.