INVESTIGATION OF DATA MINING USING PRUNED ARTIFICIAL NEURAL NETWORK TREE

A major drawback associated with the use of artificial neural networks for data mining is their lack of explanation capability. While they can achieve a high predictive accuracy rate, the knowledge captured is not transparent and cannot be verified by domain experts. In this paper, Artificial Neural...

Full description

Saved in:
Bibliographic Details
Published inJournal of engineering science & technology Vol. 3; no. 3; pp. 243 - 255
Main Authors S.M.A.KALAIARASI, G.SAINARAYANAN, ALI CHEKIMA, JASON TEO
Format Journal Article
LanguageEnglish
Published Taylor's University 01.12.2008
Subjects
Artificial neural network
Comprehensibility
Data mining
Pruning
Online AccessGet full text

Cover

More Information
Summary:A major drawback associated with the use of artificial neural networks for data mining is their lack of explanation capability. While they can achieve a high predictive accuracy rate, the knowledge captured is not transparent and cannot be verified by domain experts. In this paper, Artificial Neural Network Tree (ANNT), i.e. ANN training preceded by Decision Tree rules extraction method is presented to overcome the comprehensibility problem of ANN. Two pruning techniques are used with the ANNT algorithm; one is to prune the neural network and another to prune the tree. Both of these pruning methods are evaluated to see the effect on ANNT in terms of accuracy, comprehensibility and fidelity.
ISSN:1823-4690