Enabling the development of accurate intrinsic parameter extraction model for GaN HEMT using support vector regression (SVR)

Abstract

This study employs support vector regression (SVR) to develop an accurate and reliable intrinsic parameter extraction model for gallium nitride (GaN) high electron mobility transistors (HEMT) using two different geometries of 2 × 200 μm and 4 × 100 µm. The key aspect of the proposed approach is the use of nonlinear Gaussian kernel to transform the input space into a high‐dimensional feature space. It then allows the application of learning technique to develop a reliable procedure for parameter extraction. The proposed extraction model of GaN HEMT has been developed for a broad range of frequency, from 1 to 18 GHz, with multi‐biasing sets for HEMTs of two different geometries. Moreover, the proposed model is made scalable in terms of geometry parameters and therefore can be used to predict the intrinsic parameters and enumerate scaling efficiency of GaN HEMTs by investigating the geometry parameters. A good agreement is observed between the measured S‐parameters and the proposed model for the complete frequency range. It is shown that the proposed approach is simple, novel and can be readily incorporated into computer‐aided design tool for an accurate and expedited design process of RF and microwave circuits.

A Generic and Efficient Globalized Kernel Mapping-Based Small-Signal Behavioral Modeling for GaN HEMT

“…Subsequently, the proposed GaN HEMT model is developed using a distinct algorithm called Sequential Minimal Optimization (SMO) [25] for optimal set of kernel function and associated hyperparameters considering various additive noise functions. The SMO algorithm has a unique feature of solving quadratic programming (QP) without any numerical optimization steps and even without extra matrix storage.…”

“…Therefore, the alternative machine learning (ML) based small-signal modeling technique is gaining popularity as their turn-around time is fast with very good accuracy [22]- [23]. A key feature of ML is its ability to predict the outcome in real-time very quickly and this is very appealing for device modeling especially at RF and microwave frequencies where the inter-dependence of various device parameters on each other is huge [24]- [25]. Furthermore, device modeling by integrating various device geometry and learning device behavior with more features to build an automation model using numerous ML algorithms has the potential to bring a paradigm shift in the way device modelling is carried out.…”

“…More recently, Artificial Neural Network (ANN) and Support Vector Regression (SVR) techniques have been used in the development of small-signal model for GaN HEMT [27]- [34]. However, SVR is considered better than ANN as it enables the determination of global optimum which is superior to ANN that supports local optimum [23,25,[32][33][34][35][36][37]. Moreover, the SVR possesses geometrical interpretation whereas ANN is based on the tedious description of various parameters.…”

“…On the other hand, set of hyperparameters if not selected properly may lead to underfitting or overfitting. In addition, SVR is not appropriate while dealing with massive dataset due to large processing Gram matrices associated with kernels [25].…”

Small signal behavioral modeling technique of GaN high electron mobility transistor using artificial neural network: An accurate, fast, and reliable approach

“…ANN is generally based on the concept of empirical risk minimization; therefore, local minima can also appear instead of global minima in some cases. Though support vector regression (SVR) and Bayesian inference (BI)‐based technique focuses on global minima, yet ANN takes an edge over SVR and BI in terms of generalization capability and the convergence rate, respectively.…”