Detail výsledku

Methodology of neural design: applications in microwave engineering

Petr Poměnka, Zbyněk Raida. Methodology of neural design: applications in microwave engineering. Radioengineering, 2006, vol. 15, no. 2, 6 p. ISSN: 1210-2512.
Typ
článek v časopise
Jazyk
anglicky
Autoři
Poměnka Petr, Ing., Ph.D.
Raida Zbyněk, prof. Dr. Ing., UREL (FEKT)
Abstrakt

In the paper, an original methodology for the automatic creation of neural models of microwave structures is proposed and verified. Following the methodology, neural models of the prescribed accuracy are built within the minimum CPU time.
Validity of the proposed methodology is verified by developing neural models of selected microwave structures. Functionality of neural models is verified in a design – a neural model is joined with a genetic algorithm to find a global minimum of a formulated objective function. The objective function is minimized using different versions of genetic algorithms, and their mutual combinations.
The verified methodology of the automated creation of accurate neural models of microwave structures, and their association with global optimization routines are the most important original features of the paper.

Klíčová slova

Artificial neural networks, genetic algorithms, microwave structures.

Rok
2006
Strany
6
Časopis
Radioengineering, roč. 15, č. 2, ISSN 1210-2512
BibTeX 
@article{BUT43180,
  author="Petr {Poměnka} and Zbyněk {Raida}",
  title="Methodology of neural design: applications in microwave engineering",
  journal="Radioengineering",
  year="2006",
  volume="15",
  number="2",
  pages="6",
  issn="1210-2512"
}
Pracoviště
Ústav radioelektroniky (UREL)
Nahoru