Premium
Artificial neural network applications in improved noise wave modeling of microwave FETs
Author(s) -
Marinković Zlatica D.,
PronićRančić Olivera,
Marković Vera
Publication year - 2008
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.23771
Subject(s) - mesfet , microwave , high electron mobility transistor , artificial neural network , noise (video) , electronic engineering , multilayer perceptron , engineering , computer science , transistor , electrical engineering , field effect transistor , artificial intelligence , telecommunications , voltage , image (mathematics)
An application of artificial neural networks (ANNs) for accuracy improving of the microwave FETs (MESFET/HEMT, dual‐gate MESFET) noise modeling is presented in this paper. The proposed model is based on a basic transistor noise wave model, whose noise wave temperatures are assumed to be constant over the operating frequency range. A multilayer perceptron ANN is included in the model in order to adjust values of the noise parameters obtained by the original wave model to be more accurate. Numerical examples for noise parameters modeling are presented to show the validity and effectiveness of this approach. © 2008 Wiley Periodicals, Inc. Microwave Opt Technol Lett 50: 2512–2516, 2008; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/mop.23771