Comprehensive Investigation and Comparative Analysis of Machine Learning-Based Small-Signal Modelling Techniques for GaN HEMTs
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 cond...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Journal of the Electron Devices Society |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9963557/ |
| _version_ | 1818296562005049344 |
|---|---|
| author | Saddam Husain Mohammad Hashmi Fadhel M. Ghannouchi |
| author_facet | Saddam Husain Mohammad Hashmi Fadhel M. Ghannouchi |
| author_sort | Saddam Husain |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-12-13T04:05:30Z |
| format | Article |
| id | doaj.art-b62148a0478148e5a4f45d949ad6999b |
| institution | Directory Open Access Journal |
| issn | 2168-6734 |
| language | English |
| last_indexed | 2024-12-13T04:05:30Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of the Electron Devices Society |
| spelling | doaj.art-b62148a0478148e5a4f45d949ad6999b2022-12-22T00:00:12ZengIEEEIEEE Journal of the Electron Devices Society2168-67342022-01-01101015103210.1109/JEDS.2022.32244339963557Comprehensive Investigation and Comparative Analysis of Machine Learning-Based Small-Signal Modelling Techniques for GaN HEMTsSaddam Husain0https://orcid.org/0000-0001-9830-5133Mohammad Hashmi1https://orcid.org/0000-0002-1772-588XFadhel M. Ghannouchi2https://orcid.org/0000-0001-6788-1656Department of Electrical and Computer Engineering, School of Engineering and Digital Sciences, Nazarbayev University, Nur-Sultan, KazakhstanDepartment of Electrical and Computer Engineering, School of Engineering and Digital Sciences, Nazarbayev University, Nur-Sultan, KazakhstanDepartment of Electrical and Computer Engineering, University of Calgary, Calgary, CanadaA 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.https://ieeexplore.ieee.org/document/9963557/ANNDTensemble methodsGA-ANNGaN HEMTGPR |
| spellingShingle | Saddam Husain Mohammad Hashmi Fadhel M. Ghannouchi Comprehensive Investigation and Comparative Analysis of Machine Learning-Based Small-Signal Modelling Techniques for GaN HEMTs IEEE Journal of the Electron Devices Society ANN DT ensemble methods GA-ANN GaN HEMT GPR |
| title | Comprehensive Investigation and Comparative Analysis of Machine Learning-Based Small-Signal Modelling Techniques for GaN HEMTs |
| title_full | Comprehensive Investigation and Comparative Analysis of Machine Learning-Based Small-Signal Modelling Techniques for GaN HEMTs |
| title_fullStr | Comprehensive Investigation and Comparative Analysis of Machine Learning-Based Small-Signal Modelling Techniques for GaN HEMTs |
| title_full_unstemmed | Comprehensive Investigation and Comparative Analysis of Machine Learning-Based Small-Signal Modelling Techniques for GaN HEMTs |
| title_short | Comprehensive Investigation and Comparative Analysis of Machine Learning-Based Small-Signal Modelling Techniques for GaN HEMTs |
| title_sort | comprehensive investigation and comparative analysis of machine learning based small signal modelling techniques for gan hemts |
| topic | ANN DT ensemble methods GA-ANN GaN HEMT GPR |
| url | https://ieeexplore.ieee.org/document/9963557/ |
| work_keys_str_mv | AT saddamhusain comprehensiveinvestigationandcomparativeanalysisofmachinelearningbasedsmallsignalmodellingtechniquesforganhemts AT mohammadhashmi comprehensiveinvestigationandcomparativeanalysisofmachinelearningbasedsmallsignalmodellingtechniquesforganhemts AT fadhelmghannouchi comprehensiveinvestigationandcomparativeanalysisofmachinelearningbasedsmallsignalmodellingtechniquesforganhemts |