Design of optimal fuzzy classification system using bio inspired algorithm for microarray data analysis

Abstract

Bioinformatics is a promising and innovative research field in the 21st century it can be defined as the application of information technology in the field of molecular biology different biological problems considered within the scope of bioinformatics involve the study of genes nucleic acid and proteins dna microarray is a technology for studying gene expression recently microarray data generated by this technology is more preferred by a physician for diagnosing a disease than morphological clinical data but the high dimensional low sample and one sidedness nature of microarray data pose a lot of difficulties in a computer based diagnostic system therefore careful examination of microarray data has an important influence on an identification of diseases gene selection and sample classification are the two major tasks considered in this research work for analyzing and extracting knowledge from the microarray data formulating a suitable function for calculating the relevancy between different gene expression profiles for micro array data analysis is a major problem this research work uses a novel idea of computing mutual information mi in stages the proposed mutual information computes mi, initially using all the samples and based on the classification performance produced by fuzzy expert system fes mi is repeatedly calculated using only the unclassified samples until there is no improvement in the classification accuracy. newline