Neural network approach to shape reconstruction of a conducting cylinder

Nemci Serkan Tezel*, Serkan Şimşek

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

3 Citations (Scopus)

Abstract

In this study, the shape reconstruction of a conducting cylinder by making use of electromagnetic scattered fields is presented. The problem is treated with the Method of Moment (MoM) and Feed Forward Neural Networks (FF-NN) is applied. The shape of the cylinder is represented by a Fourier series while applying MoM, a matrix equation is obtained whose elements are expressed numerically by using discrete points. The scattered field data and Fourier coefficients of the cylinder are used for training the NN as inputs and outputs respectively. The NN results are compared with exact shapes of some conducting cylinders; and good agreements with the original shapes are observed. The effect of the noise on the scattering field is also investigated.

Original languageEnglish
Pages (from-to)299-304
Number of pages6
JournalIstanbul University - Journal of Electrical and Electronics Engineering
Volume7
Issue number1
Publication statusPublished - 2007

Keywords

  • Inverse electromagnetic scattering
  • Neural network
  • Shape reconstruction

Fingerprint

Dive into the research topics of 'Neural network approach to shape reconstruction of a conducting cylinder'. Together they form a unique fingerprint.

Cite this