Elsevier

Procedia Engineering

Volume 41, 2012, Pages 1818-1823
Procedia Engineering

Feature Selection in Ischemic Heart Disease Identification using Feed Forward Neural Networks

https://doi.org/10.1016/j.proeng.2012.08.109Get rights and content
Under a Creative Commons license
open access

Abstract

Feature Selection in Data Mining refers to an art of minimizing the number of inputs under evaluation. An artificial neural network is the simulation of a human brain which learns with experience. Efficiency of a model or a system in terms of cost, time and accuracy will greatly improve if proper features of a system are selected. This proposed method uses Artificial Neural Network for selecting the interesting or important features from the input layer of the network. A Multi Layer Perceptron Neural Network is used for selection of interesting features from a Ischemic Heart Disease (IHD) data base with 712 patients. Initially the number of attributes was 17 and after feature selection the number of attributes was reduced to 12. All combination of features are attempted as inputs of a Neural Network. When the input features is 12 the predicted accuracy during training is high as 89.4% and during testing is high as 82.2%. Further removal of features lowers the accuracy and hence the interesting features selected for prediction is concluded to be as 12 for this IHD data set.

Keywords

Data Mining
Feature Selection
Multi Layer Perceptron
Neural Network
Ischemic Heart Disease(IHD)

Cited by (0)