Premium
A threshold electromagnetic classification approach for cylinders embedded in a lossy medium by using a neural network technique
Author(s) -
Bermani E.,
Caorsi S.,
Raffetto M.
Publication year - 2000
Publication title -
microwave and optical technology letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.304
H-Index - 76
eISSN - 1098-2760
pISSN - 0895-2477
DOI - 10.1002/(sici)1098-2760(20000105)24:1<13::aid-mop5>3.0.co;2-9
Subject(s) - lossy compression , microwave , artificial neural network , conductor , cylinder , dielectric , electric field , computer science , electromagnetic field , electronic engineering , acoustics , physics , artificial intelligence , engineering , electrical engineering , mathematics , telecommunications , mechanical engineering , geometry , quantum mechanics
In this letter, we propose a threshold classification approach to distinguish between conductor and dielectric cylindrical objects embedded in lossy media. The approach is based on the capability of a neural network (NN) to reconstruct the electric conductivity of the embedded cylinder starting from the values of the scattered electric field evaluated at a number of points near the illumination source. The approach is also shown to provide a high percentage of successful classification in the presence of noisy input data. © 2000 John Wiley & Sons, Inc. Microwave Opt Technol Lett 24: 13–16, 2000.