A new approach for small-signal modelling of the field effect transistor based on cepstral coefficients and discrete transforms

Abstract

In this article, a new technique for field effect transistor (FET) small-signal modelling using neural networks is proposed. This technique is based on the combination of the Mel-frequency cepstral coefficients (MFCCs) with different discrete transforms such as the discrete cosine transform (DCT), the discrete sine transform (DST) and the discrete wavelet transform (DWT) of the inputs to the neural networks. The input datasets to traditional neural systems for FET small-signal modelling are the scattering parameters and the corresponding frequencies in a certain band, and the output datasets are the circuit elements. In the proposed approach, these datasets are considered to form random signals. The MFCCs of the random signals are used to generate a small number of features characterising the signals. In addition, other vectors are calculated from the DCT, DST or DWT of the random signals and appended to the MFCC 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 characterise the random input sequences with more features, to encourage robustness against measurement errors. There are two benefits to these approaches: (1) a reduction in the number of neural network inputs, and hence a faster convergence of the neural training algorithm and (2) robustness against measurement errors in the testing phase. Experimental results show that the techniques based on the discrete transforms are less sensitive to measurement errors than using the traditional and MFCC methods.