This paper is published in Volume-5, Issue-3, 2019
Area
Computer Science and Engineering
Author
K. Iswarya
Co-authors
C. Kanimozhi
Org/Univ
Anna University BIT-Campus, Tiruchirappalli, Tamil Nadu, India
Pub. Date
11 May, 2019
Paper ID
V5I3-1312
Publisher
Keywords
Feature selection, Mutual information, Pearson’s correlation, Genetic algorithm, Simulated annealing, SVM

Citationsacebook

IEEE
K. Iswarya, C. Kanimozhi. Dimensionality reduction and classification in gene expression data using hybrid approach, International Journal of Advance Research, Ideas and Innovations in Technology, www.IJARIIT.com.

APA
K. Iswarya, C. Kanimozhi (2019). Dimensionality reduction and classification in gene expression data using hybrid approach. International Journal of Advance Research, Ideas and Innovations in Technology, 5(3) www.IJARIIT.com.

MLA
K. Iswarya, C. Kanimozhi. "Dimensionality reduction and classification in gene expression data using hybrid approach." International Journal of Advance Research, Ideas and Innovations in Technology 5.3 (2019). www.IJARIIT.com.

Abstract

The microarray technology has modernized the approach of biological research in such a way that scientists can now measure the expression levels of thousands of genes simultaneously in a single experiment. With this large quantity of gene expression data, experts have started to discover the possibilities of disease classification using gene expression data. Quite a large number of methods have been planned in recent years with hopeful results. But there are still a set of issues which need to be addressed and understood. In order to gain insight into the disease classification difficulty, it is necessary to get a closer look at the problem, the proposed solutions, and the associated issues altogether. In this paper, we present a dimensionality reduction methods and classification method such as Mutual information, Pearson’s correlation, search algorithms (Recursive feature elimination, Genetic Algorithm, simulated annealing) with Support Vector Machine (SVM) classification algorithm and estimate them based on their evaluation time, classification accuracy and ability to reveal biologically meaningful gene expression. Our experimental results shows that classifier performance through graphs with improved accuracy in disease prediction.
Paper PDF