A multilayered perceptron neural network for a micro-coplanar strip line


Sagiroglu Ş., Yildiz C.

ELECTROMAGNETICS, cilt.22, sa.7, ss.553-563, 2002 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 22 Sayı: 7
  • Basım Tarihi: 2002
  • Doi Numarası: 10.1080/02726340290084111
  • Dergi Adı: ELECTROMAGNETICS
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.553-563
  • Gazi Üniversitesi Adresli: Hayır

Özet

This paper presents a new approach based on multilayered perceptrons (MLPs) to compute the characteristic impedance and the effective permittivity of the microcoplanar strip. Only one neural model is used to calculate the both parameters of the strip. An extended delta-bar-delta algorithm is used to train the MLP. The results obtained by using the MLP model are in very good agreement with the theoretical and experimental results reported elsewhere.