FET SMALL-SIGNAL MODELING USING MEL-FREQUENCY CEPSTRAL COEFFICIENTS AND THE DISCRETE COSINE TRANSFORM

• Published in: Journal of circuits, systems, and computers Vol. 19; no. 8; pp. 1835 - 1846
• Main Authors: ELSHARKAWY, R. R., HINDY, M., EL-RABAIE, S., DESSOUKY, M. I.
• Format: Journal Article
• Language: English
• Published: World Scientific Publishing Company 01.12.2010
• Subjects: DCT; FET small-signal modeling; MFCCs; neural networks
• ISSN: 0218-1266; 1793-6454
• DOI: 10.1142/S0218126610007158

In this paper, a novel neural technique is proposed for FET small-signal modeling. This technique is based on the discrete cosine transform (DCT) and the Mel-frequency cepstral coefficients (MFCCs). The input data to traditional neural systems for FET small-signal modeling are the scattering parameters and the corresponding frequencies in a certain band, and the outputs are the circuit elements. In the proposed technique, the input data are considered random, and the MFCCs are calculated from these inputs and their DCT. The MFCCs are used to give a few features from the input random data sequence to be used for the training of the neural networks. The objective of using MFCCs is to characterize the random input sequence with features that are robust against measurement errors. The MFCCs extracted from the DCT of the inputs increase the robustness against measurement errors. There are two benefits that can be achieved using the proposed technique; a reduction in the number of neural inputs and hence a faster convergence of the neural training algorithm and a robustness against measurement errors in the testing phase. Experimental results show that the technique based on the DCT and MFCCs is less sensitive to measurement errors than using the actual measured scattering parameters.