Title: Evolving Efficient Classification Patterns in Lymphography Using EasyNN
Authors: Ahmed Suhail Jaber, Ahmed Khalil Humid, Mohammed Ahmed Hussein, Samy S. Abu-Naser
Volume: 4
Issue: 9
Pages: 66-73
Publication Date: 2020/09/28
Abstract:
A neural network exploits the non-linearity of a problem to define a set of desired inputs. Neural networks are important in realizing a better way for classification in machine learning and finds application in various fields such as data mining, pattern recognition, forensics etc. In this paper, our focus is to classify of patient records obtained from clinical data. Feature selection is a supervised method that attempts to select a subset of the predictor features based on the information gain. The Lymphography dataset comprises of 18 attributes and 148 instances with the class label having four distinct values. This paper highlights the accuracy of EasyNN backbrapagation calssification algorithm in classifying predictor attributes and highlights its performance on Lymphography dataset. The accuracy we have reached is 97.78 percent in classification accuracy with the predictor feature.