            Vaishali P Khobragade 1 , Dr.A.Vinayababu 2 1 Jyothishmathi Institute of Technology & Science, CSE Department, JNTU Hyderabad Karimnagar, AndhraPradesh 505001, India 2 Principal JNTUH College of Engineering, JNT University Hyderabad, AndhraPradesh 500085, India Abstract In this paper, an efficient technique is proposed for the precise classification of microarray genes from the microarray gene expression dataset. The proposed classification technique performs the classification process with the aid of three phases namely, dimensionality reduction, feature selection and gene classification. Initially, the proposed technique reduces the dimensionality by utilizing Genetic Algorithm (GA). The main objective of dimensionality reduction is to select the optimal number of genes from the microarray gene expression dataset. Next, in the feature selection process the features are extracted from the column gene values. Here, probability of GA-indexed gene and new statistical features are selected for each column gene values and these selected features are given to the Feed Forward Back propagation Neural Network (FFBNN). The FFBNN network is trained using the selected features and then this well trained FFBNN network performance is tested with the column gene values. The FFBNN network classifies the microarray gene values into their corresponding cancer class types. The performance of the classification technique is evaluated by the performance measures such as accuracy, specificity and sensitivity. Keywords: Micro array gene expression data, Classification, Feed Forward Back Propagation Neural Network (FFBNN), Statistical measures. 1. Introduction Deoxyribonucleic acid (DNA) microarray technology provides tools for monitoring the expression levels of huge number of different genes simultaneously [9]. It is possible for the biologists to concurrently evaluate the expressions of thousands of genes in a single experiment by the aid of microarray technologies [5] [15] [19]. This technology provides a unique tool, which has been currently used for medical diagnosis and gene analysis, especially to inspect how a cell’s gene expression pattern changes in different conditions. A microarray method also plays an important role in personalized medicine because it can be used to identify the individual’s unique genetic vulnerability to treat the diseases [1]. High-throughput microarray technology presents a robust tool in biomedical research. Particularly, DNA microarray profiling technology is very useful in disease diagnosis and forecast, as well as in subtype detection [6] [16]. A standard microarray experiment dataset contains expression levels of a large number of genes in a number of experimental samples or conditions [10]. The expression data is represented in a matrix form, where the rows are denoting genes and the columns are denoting samples. This matrix is termed as gene expression matrix [11].Gene expression data is often used in disease analysis, especially for cancer diagnosis [8]. Gene expression data from DNA microarrays are described by several variables (genes) with only a small number of observations (experiments) [7][17]. Prediction, classification, and clustering methods are employed IJCSI International Journal of Computer Science Issues, Vol. 9, Issue 6, No 2, November 2012 ISSN (Online): 1694-0814 www.IJCSI.org 246 Copyright (c) 2012 International Journal of Computer Science Issues. All Rights Reserved.