Comprehensive Investigation and Comparative Analysis of Machine Learning-Based Small-Signal Modelling Techniques for GaN HEMTs
Bibliographic record
Abstract
A number of machine learning (ML) algorithm based small signal modeling of Gallium Nitride (GaN) High Electron Mobility Transistors (HEMTs) have been reported in literature. However, these techniques rarely provide any inkling about their suitability in modeling GaN HEMTs under varied operating conditions. In this context, this paper thoroughly investigates various ML based techniques and identifies their suitability for specific application scenarios. At first, an array of commonly employed modeling techniques based around Artificial Neural Network, RANdom SAmple Consensus, Support Vector Regression, Gaussian Process Regression, Decision Tree, and Genetic algorithm assisted Artificial Neural Network are used for development of modeling framework to exploit the bias, frequency and geometry dependence on S-parameter based outputs. Subsequently, the ensemble techniques namely Bootstrap aggregating, Random Forests, Extremely Randomized Trees, AdaBoost, Gradient Tree Boosting, Histogram-based Gradient Boosting, and Extreme Gradient Boosting are also explored to understand the capability of these algorithms in the development of GaN HEMT small signal models. Thereafter, an exhaustive analysis of bias and variance is carried out to figure out the most appropriate algorithms for specific applications. The discrepancies during model development are removed by tuning the hyperparameters of the respective models using Random search optimization with 5-fold cross validation technique. Post tuning, the models are evaluated in terms of generalization capability, Advanced Design System compatibility, computational efficiency, training and simulation time, models’ capacity and parameters’tuning time.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".