Premium
A neural‐network approach to the inverse‐scattering problem from a circular conducting cylindrical scatterer
Author(s) -
Hamid AK.
Publication year - 1996
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(19961220)13:6<380::aid-mop18>3.0.co;2-7
Subject(s) - cylinder , radius , inverse scattering problem , scattering , artificial neural network , inverse , physics , nonlinear system , field (mathematics) , inverse problem , optics , mathematical analysis , geometry , mathematics , computer science , quantum mechanics , computer security , pure mathematics , machine learning
A neural‐network approach is developed to investigate the inverse scattering from a perfectly conducting circular cylinder due to a normal field incidence. The neural network, is used to predict the electrical radius ka of a circular cylinder by recovering the complex coefficients of the cylindrical wave expansion of the scattered field. The neural network, therefore, is trained to model the nonlinear relation between the electrical radius and the numerical values of the complex expansion coefficients of the far field. © 1996 John Wiley & Sons, Inc.