Bayesian network approach to classify damages and f -folds feature subset selection method in laminated composite materials

This paper is intended to introduce the Bayesian network in general and the Naïve-bayes in particular as one of the most successful classification systems to simulate damage detection in laminated composite materials. A method for feature subset selection based on intervals between the amplitudes of...

Full description

Bibliographic Details
Main Authors: Mohamed Addin, Addin Osman, Salit, Mohd Sapuan, Ebrahimi, Mahdi, Othman, Mohamed, Ismail, Napsiah
Format: Conference or Workshop Item
Language:English
Published: 2005
Online Access:http://psasir.upm.edu.my/id/eprint/38990/
http://psasir.upm.edu.my/id/eprint/38990/1/38990.pdf
Description
Summary:This paper is intended to introduce the Bayesian network in general and the Naïve-bayes in particular as one of the most successful classification systems to simulate damage detection in laminated composite materials. A method for feature subset selection based on intervals between the amplitudes of waves used for damage detection is also introduced. The method utilizes clustering in the process of feature subset selection. The Bayesian classification and the feature selection method are analyzed based on theoretical point of view and only preliminary tests were conducted based on artificial damages created in quasi-isotopic laminates of the AS4/3501-6 graphite/epoxy system.