IJASEIT

International Journal on Advanced Science, Engineering and Information Technology, Vol. 8 (2018) No. 4-2: Special Issue on Empowering the Nation via 4IR (The Fourth Industrial Revolution)., pages: 1387-1393, Chief Editor: Khairuddin Omar | Editorial Boards : Shahnorbanun Sahran Hassan, Nor Samsiah Sani, Heuiseok Lim & Danial Hoosyar, DOI:10.18517/ijaseit.8.4-2.6790

Feature selection from colon cancer dataset for cancer classification using Artificial Neural Network

Md. Akizur Rahman, Ravie Chandren Muniyandi

Abstract

In the fast-growing field of medicine and its dynamic demand in research, a study that proves significant improvement to healthcare seems imperative especially when it is on cancer research. This research paved way to such significant findings by the inclusion of feature selection as one of its major components. Feature selection has become a vital task to apply data mining algorithms effectively in the real-world problems for classification. Feature selection has been the focus of interest for quite some time and much completed work related to it. Although much research conducted on the field, a study that proved a nearly perfect accuracy seems limited; hence, more scientifically driven results should be produced. Using various research on feature selection as basis for the choices in this study, the method was product of careful selection and planning. Specifically, this study used feature selection for improving classification accuracy on cancerous dataset. This study proposed Artificial Neural Network (ANN) for cancer classification with feature selection on colon cancer dataset. The study used best first search method in weka tools for feature selection. Through the process, a promising result has been achieved. The result of the experiment achieved 98.4 % accuracy for cancer classification after feature selection by using proposed algorithm. The result displayed that feature selection improved the classification accuracy based on the experiment conducted on the colon cancer dataset. The result of this experiment was comparable with the other studies on colon cancer research. It showed another significant improvement and can be considered promising for more future applications.