Classification of Micro Array Gene Expression Data using Statistical Analysis Approach with Personalized Fuzzy Inference System

Abstract

In this paper we describe a method to classify the micro array gene expression data based on their tissue sample types. Normally dimensionality reduction is performed over the micro array gene expression data set. Here, we propose a statistical approach for extracting significant genes from the gene expression data set. But, the statistical approach does not correctly identify the important genes. Hence, the ultimate objective is to solve the drawbacks in dimensionality reduction as they have a direct impact on the robustness of the generated fuzzy rules. Consequently, the goal is to generate fuzzy rules based on dimensionality reduced data. Hence, fuzzy inference is selected in our approach for classification and the fuzzy rules are utilized to train the fuzzy inference system (FIS). The classification performance of the fuzzy inference system (FIS) is similar to that of other classifiers, but simpler and easier to interpret. The classification performance of the FIS classifier is compared over the existing Fuzzy Genetic, Fuzzy Neural Network ProbPCA and PCA classifiers. The classification performance of the proposed technique is evaluated over the cancer datasets of Acute myeloid leukemia (AML) and Acute Lymphoblastic Leukemia (ALL).