Neural Networks Classification Performance for Medical Dataset

Artificial neural networks (ANN) are designed to simulate the behavior of biological neural networks for several purposes. Neural networks (NN), with their remarkable ability to derive meaning from complicated or imprecise data, can be used to extract patterns and detect trends that are too complex...

Full description

Saved in:
Bibliographic Details
Main Author: Norsarini, Salim
Format: Thesis
Language:eng
eng
Published: 2005
Subjects:
Online Access:https://etd.uum.edu.my/1310/1/NORSARINI_BT._SALIM.pdf
https://etd.uum.edu.my/1310/2/1.NORSARINI_BT._SALIM.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Artificial neural networks (ANN) are designed to simulate the behavior of biological neural networks for several purposes. Neural networks (NN), with their remarkable ability to derive meaning from complicated or imprecise data, can be used to extract patterns and detect trends that are too complex to be noticed by either humans or other computer techniques. Multilayer Perceptron (MLP), Support Vector Machine (SVM) and Radial Basis Function (RBF) are classification techniques in neural networks that were used to train historical medical data. The study was based on different data set that obtained from UCI machine learning database and tested by the WEKA software machine learning tools. The comparison results of each method were based on the training performance of classifier in terms of accuracy, training time and complexity.