ANN modeling of synthetic cold loads

Author

Langoni, Diego ; Weatherspoon, Mark H.

Author_Institution

Dept. of Electr. & Comput. Eng., Florida A&M Univ., Tallahassee, FL, USA

fYear

2007

fDate

8-8 June 2007

Firstpage

1

Lastpage

8

Abstract

Preliminary results are presented for artificial neural network (ANN) models of the available output noise temperature of a FET-based synthetic cold load. Two different ANNs were studied for this application: the radial basis function (RBF) and the Levenberg-Marquardt (LM) backpropagation (BP). The best average relative error (ARE) and maximum local relative error (MLRE) results for the model of incident noise temperature versus load impedance were 0.1439% and 1.1544% respectively. The best ARE and MLRE results for the model of incident noise temperature versus load reflection coefficient were 0.1810% and 1.5044% respectively.

Keywords

Schottky gate field effect transistors; backpropagation; load (electric); radial basis function networks; ANN modeling; FET-based synthetic cold load; Levenberg-Marquardt backpropagation; artificial neural network models; average relative error; maximum local relative error; output noise temperature; radial basis function; synthetic cold loads; Calibration; Error analysis; Impedance measurement; Measurement standards; Numerical simulation; RF signals; Radio frequency; Reflection; Sensitivity analysis; Testing; Artificial neural networks (ANNs); Levenberg-Marquardt backpropagation; noise temperature; radial basis function (RBF); synthetic cold load;

fLanguage

English

Publisher

ieee

Conference_Titel

ARFTG Conference, 2007 69th

Conference_Location

Honolulu, HI

Print_ISBN

978-0-7803-9762-0

Electronic_ISBN

978-0-7803-9763-7

Type

conf

DOI

10.1109/ARFTG.2007.5456338

Filename

5456338