Premium
Non‐destructive recognition of dielectric coated conducting objects by using WD type time–frequency transformation and PCA‐based fusion
Author(s) -
TurhanSayan Gonul,
Ergin Emre
Publication year - 2013
Publication title -
international journal of rf and microwave computer‐aided engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.335
H-Index - 39
eISSN - 1099-047X
pISSN - 1096-4290
DOI - 10.1002/mmce.20726
Subject(s) - principal component analysis , fusion , classifier (uml) , pattern recognition (psychology) , dielectric , artificial intelligence , transformation (genetics) , materials science , permittivity , computer science , noise (video) , microwave , spheres , optoelectronics , physics , chemistry , telecommunications , astronomy , philosophy , linguistics , biochemistry , image (mathematics) , gene
This article demonstrates the applications of a non‐destructive electromagnetic target recognition method, called Wigner distribution‐principal component analysis (WD‐PCA) method, to dielectric coated conducting spheres. These spheres are chosen to be highly similar having the same overall size but slightly different permittivity and thickness values in coating layers. Four different classifiers are simulated by using the WD‐PCA method for varying sizes of object libraries under different noise conditions. High correct decision rates are demonstrated even for challenging classifier libraries containing a large number of coated conductors while the method is also shown to be highly robust against noise both in design and test stages. © 2013 Wiley Periodicals, Inc. Int J RF and Microwave CAE, 2013.