FET SMALL-SIGNAL MODELLING BASED ON THE DST AND MEL FREQUENCY CEPSTRAL COEFFICIENTS

In this paper, a new technique is proposed for fleld efiect transistor (FET) small-signal modeling using neural networks. This technique is based on the combination of the Mel frequency cepstral coe-cients (MFCCs) and discrete sine transform (DST) of the inputs to the neural networks. The input data sets to traditional neural systems for FET small-signal modeling are the scattering parameters and corresponding frequencies in a certain band, and the outputs are the circuit elements. In the proposed approach, these data sets are considered as forming random signals. The MFCCs of the random signals are used to generate a small number of features characterizing the signals. In addition, other MFCCs vectors are calculated from the DST of the random signals and appended to the MFCCs vectors calculated from the signals. The new feature vectors are used to train the neural networks. The objective of using these new vectors is to characterize the random input sequences with much more features to be robust against measurement errors. There are two beneflts

[1]  Naofumi Okubo,et al.  A large-signal characterization of an HEMT using a multilayered neural network , 1997 .

[2]  M.C.E. Yagoub,et al.  A robust algorithm for automatic development of neural network models for microwave applications , 2001, 2001 IEEE MTT-S International Microwave Sympsoium Digest (Cat. No.01CH37157).

[3]  Marcelino Lázaro,et al.  Neural networks for large- and small-signal modeling of MESFET/HEMT transistors , 2001, IEEE Trans. Instrum. Meas..

[4]  Gregory W. Wornell.  Emerging applications of multirate signal processing and wavelets in digital communications , 1996 .

[5]  G. Kompa,et al.  A new small-signal modeling approach applied to GaN devices , 2005, IEEE Transactions on Microwave Theory and Techniques.

[6]  G. D. Vendelin,et al.  Circuit model for the GaAs m.e.s.f.e.t. valid to 12 GHz , 1975 .

[7]  G. D. Vendelin.  Feedback Effects in the GaAs MESFET Model (Letters) , 1976 .

[8]  Mook-Seng Leong,et al.  Analytical Extraction of Extrinsic and Intrinsic FET Parameters , 2009, IEEE Transactions on Microwave Theory and Techniques.

[9]  Richard Kronland-Martinet,et al.  Characterization of acoustic signals through continuous linear time-frequency representations , 1996, Proc. IEEE.

[10]  M. Berroth,et al.  Broad-band determination of the FET small-signal equivalent circuit , 1990 .

[11]  S. Weinreb,et al.  A note on experimental determination of small-signal equivalent circuit of millimeter-wave FETs , 1993 .

[12]  W. R. Curtice,et al.  Self-Consistent GaAs FET Models for Amplifier Design and Device Diagnostics , 1984 .

[13]  Ban-Leong Ooi,et al.  A novel approach for determining the GaAs MESFET small-signal equivalent-circuit elements , 1997 .

[14]  Alexander I. Galushkin,et al.  Neural Networks Theory , 2007 .

[15]  Gérard Dreyfus,et al.  Neural networks - methodology and applications , 2005 .

[16]  Yoji Ohashi,et al.  An approach to determining an equivalent circuit for HEMTs , 1995 .