Premium
Adaptive‐network‐based fuzzy inference system models for computing the characteristic impedances of air‐suspended trapezoidal and rectangular‐shaped microshield lines
Author(s) -
Turkmen Mustafa,
Yildiz Celal,
Guney Kerim,
Kaya Sabri
Publication year - 2010
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/mop.24829
Subject(s) - adaptive neuro fuzzy inference system , hybrid learning , fuzzy inference system , simulated annealing , engineering , electrical impedance , fuzzy logic , inference system , algorithm , computer science , artificial intelligence , fuzzy control system , electrical engineering
In this article, adaptive‐network‐based fuzzy inference system (ANFIS) models are proposed to compute the characteristic impedances of air‐suspended trapezoidal‐shaped microshield lines (AS‐TSMLs) and air‐suspended rectangular‐shaped microshield lines (AS‐RSMLs). The ANFIS is a fuzzy inference system implemented within the architecture and optimization procedure of adaptive networks. Four optimization algorithms, hybrid learning, simulated annealing, genetic, and least‐squares, are used to determine optimally the design parameters of ANFIS. The characteristic impedance results of ANFIS models are in very good agreement with the results available in the literature. When the performances of ANFIS models are compared with each other, the best results are obtained from the ANFIS model trained by the hybrid learning algorithm. © 2009 Wiley Periodicals, Inc. Microwave Opt Technol Lett 52: 20–24, 2010; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/mop.24829