A Survey on Solving Gene Expression Data Using FCM Clustering & Multiobjective Optimization Algorithm

The patterns unseen in genes avails to understand the functionality of genes. Although the immense amassment of genes in the biological networks, it is hard to study the volume of data which often contains millions of information. Data mining have been habituated with a promising latest area for database research. Microarray experiments bring about a substantial amount of data which is utilized to discover the genetic background of diseases and to ken the gene characteristics. Here three objective functions are utilized symmetry, compactness and separability present in the clusters and concurrently optimized by NSGA-2 Algorithm. The highest membership values of data points to dissimilar clusters, labeled in sequence are extracted by applying Fuzzy C-mean algorithm on the data set. The usefulness of this proposed clustering technique is verified on three publicly available standard gene expression data sets. Results are compared with subsisting techniques for gene expression data clustering. Moreover, the particular efficacy of a Pareto-predicated optimization approach can withal be visually perceived. In this paper, a novel interactive genetic algorithm-predicated Multiobjective approach is proposed that simultaneously finds the clustering solution as well as evolves the set of validity actions to facilitate to optimize simultaneously.