Evaluating Nine Machine Learning Algorithms for GaN HEMT Small Signal Behavioral Modeling through K-fold Cross-Validation

Authors

  • Neda Ahmad University School of Information, Communication and Technology, Guru Gobind Singh Indraprastha University, New Delhi, India
  • Vandana Nath University School of Information, Communication and Technology, Guru Gobind Singh Indraprastha University, New Delhi, India https://orcid.org/0000-0002-2952-898X
Volume: 14 | Issue: 4 | Pages: 15784-15790 | August 2024 | https://doi.org/10.48084/etasr.7726

Abstract

This paper presents an investigation into the modeling of Gallium Nitride (GaN) High Electron Mobility Transistors (HEMTs) using multiple Machine Learning (ML) algorithms. Despite the documented use of various ML techniques, a thorough comparison and performance analysis under different operating conditions were lacking. This study fills this gap by conducting a rigorous evaluation of nine ML models using TCAD-generated data of Pseudomorphic AlGaN/InGaN/GaN HEMT. The research focuses on Small Signal Behavioral Modeling and examines regression techniques such as Multiple Linear Regression (MLR), Multivariate Linear Regression (MVLR), Ridge Regression (L2), Lasso Regression (L1), Elastic Net Regression (ENR), Decision Trees (DT), Random Forest (RF), Gradient Boosting Regression(GBR), and Support Vector Regression (SVR). These methods use biases, frequency, and device geometry as independent variables, with S-parameters being the dependent variables. K-fold cross-validation was employed to ensure model reliability and accuracy across diverse operating conditions. Results reveal that the RF, coupled with 10-fold cross-validation, exhibits superior performance giving 99.7% accurate results, with a Mean Squared Error (MSE) of 4.6375×10-5, and a coefficient of determination (R2) of 0.9977. Conversely, SVR, L1, and ENR fall short of expectations. This study underscores the significance of methodological advancements in ML-based GaN HEMT modeling and provides valuable insights for future research in this domain.

Keywords:

regression, S-parameters, machine learning, HEMT, neural networks, modeling

Downloads

Download data is not yet available.

References

R. Chu and K. Shinohara, III-Nitride Electronic Devices. Cambridge, MA, USA: Academic Press, 2019.

J. Xu and D. Chen, "A Performance Comparison of GaN E-HEMTs Versus SiC MOSFETs in Power Switching Applications," Bodo´s Power Systems, pp. 36–39, Jun. 2017.

M. Haziq, S. Falina, A. A. Manaf, H. Kawarada, and M. Syamsul, "Challenges and Opportunities for High-Power and High-Frequency AlGaN/GaN High-Electron-Mobility Transistor (HEMT) Applications: A Review," Micromachines, vol. 13, no. 12, Dec. 2022, Art. no. 2133.

M. Asif Khan, A. Bhattarai, J. N. Kuznia, and D. T. Olson, "High electron mobility transistor based on a GaN‐AlxGa1−xN heterojunction," Applied Physics Letters, vol. 63, no. 9, pp. 1214–1215, Aug. 1993.

T. Fernandez et al., "Modelling reliability in GaN HEMT devices," in 8th Conference on Simulation, Modelling and Optimization, Stevens Point, WI, USA, Sep. 2008, pp. 315–318.

G. Crupi et al., "Accurate Multibias Equivalent-Circuit Extraction for GaN HEMTs," IEEE Transactions on Microwave Theory and Techniques, vol. 54, no. 10, pp. 3616–3622, Oct. 2006.

A. Jarndal and G. Kompa, "A new small-signal modeling approach applied to GaN devices," IEEE Transactions on Microwave Theory and Techniques, vol. 53, no. 11, pp. 3440–3448, Nov. 2005.

R. G. Brady, C. H. Oxley, and T. J. Brazil, "An Improved Small-Signal Parameter-Extraction Algorithm for GaN HEMT Devices," IEEE Transactions on Microwave Theory and Techniques, vol. 56, no. 7, pp. 1535–1544, Jul. 2008.

A. Zarate-de Landa, J. E. Zuniga-Juarez, J. R. Loo-Yau, J. A. Reynoso-Hernandez, M. del C. Maya-Sanchez, and J. L. del Valle-Padilla, "Advances in Linear Modeling of Microwave Transistors," IEEE Microwave Magazine, vol. 10, no. 2, pp. 100, 102–111, 146, Apr. 2009.

G. Crupi, D. M. M.-P. Schreurs, and A. Caddemi, "On the small signal modeling of advanced microwave FETs: A comparative study," International Journal of RF and Microwave Computer-Aided Engineering, vol. 18, no. 5, pp. 417–425, 2008.

G. Crupi, A. Caddemi, D. M. M.-P. Schreurs, and G. Dambrine, "The large world of FET small-signal equivalent circuits," International Journal of RF and Microwave Computer-Aided Engineering, vol. 26, no. 9, pp. 749–762, 2016.

G. Crupi et al., "High-Frequency Extraction of the Extrinsic Capacitances for GaN HEMT Technology," IEEE Microwave and Wireless Components Letters, vol. 21, no. 8, pp. 445–447, Aug. 2011.

A. R. Alt, D. Marti, and C. R. Bolognesi, "Transistor Modeling: Robust Small-Signal Equivalent Circuit Extraction in Various HEMT Technologies," IEEE Microwave Magazine, vol. 14, no. 4, pp. 83–101, Jun. 2013.

V. Dordevic, Z. Marinkovic, V. Markovic, and O. Pronic-Rancic, "Development and validation of ANN approach for extraction of MESFET/HEMT noise model parameters," Electrical Engineering, vol. 100, no. 2, pp. 645–651, Jun. 2018.

A. Abubakr, A. Hassan, A. Ragab, S. Yacout, Y. Savaria, and M. Sawan, "High-Temperature Modeling of the I-V Characteristics of GaN150 HEMT Using Machine Learning Techniques," in IEEE International Symposium on Circuits and Systems, Florence, Italy, Dec. 2018, pp. 1–5.

Z. Marinkovic et al., "Neural approach for temperature-dependent modeling of GaN HEMTs," International Journal of Numerical Modelling: Electronic Networks, Devices and Fields, vol. 28, no. 4, pp. 359–370, 2015.

A. Jarndal, S. Hamdan, and M. Bettayeb, "On Neural Networks Modeling Based on GA, PSO and GW Optimization Techniques," in 8th International Conference on Modeling Simulation and Applied Optimization, Manama, Bahrain, Apr. 2019, pp. 1–5.

S. Husain, B. Kadirbay, A. Jarndal, and M. Hashmi, "Comprehensive Investigation of ANN Algorithms Implemented in MATLAB, Python, and R for Small-Signal Behavioral Modeling of GaN HEMTs," IEEE Journal of the Electron Devices Society, vol. 11, pp. 559–572, 2023.

Z. Marinkovic, G. Crupi, A. Caddemi, V. Markovic, and D. M. M.-P. Schreurs, "A review on the artificial neural network applications for small-signal modeling of microwave FETs," International Journal of Numerical Modelling: Electronic Networks, Devices and Fields, vol. 33, no. 3, 2020, Art. no. e2668.

M. Geng et al., "Modified small-signal behavioral model for GaN HEMTs based on support vector regression," International Journal of RF and Microwave Computer-Aided Engineering, vol. 31, no. 9, 2021, Art. no. e22774.

M. Geng, J. Cai, C. Yu, J. Su, and J. Liu, "Piecewise Small Signal Behavioral Model for GaN HEMTs based on Support Vector Regression," in IEEE MTT-S International Conference on Numerical Electromagnetic and Multiphysics Modeling and Optimization (NEMO), Hangzhou, China, Dec. 2020, pp. 1–3.

A. Jarndal, S. Husain, and M. Hashmi, "Genetic algorithm initialized artificial neural network based temperature dependent small-signal modeling technique for GaN high electron mobility transistors," International Journal of RF and Microwave Computer-Aided Engineering, vol. 31, no. 3, 2021, Art. no. e22542.

A. Jarndal, S. Husain, and M. Hashmi, "On temperature-dependent small-signal modelling of GaN HEMTs using artificial neural networks and support vector regression," IET Microwaves, Antennas & Propagation, vol. 15, no. 8, pp. 937–953, 2021.

A. Jarndal, S. Husain, M. Hashmi, and F. M. Ghannouchi, "Large-Signal Modeling of GaN HEMTs Using Hybrid GA-ANN, PSO-SVR, and GPR-Based Approaches," IEEE Journal of the Electron Devices Society, vol. 9, pp. 195–208, 2021.

A. S. Hussein and A. H. Jarndal, "On hybrid model parameter extraction of GaN HEMTs based on GA, PSO, and ABC optimization," in International Conference on Electrical and Computing Technologies and Applications, Ras Al Khaimah, United Arab Emirates, Nov. 2017, pp. 1–5.

A. Jarndal, "On neural networks based electrothermal modeling of GaN devices," IEEE Access, vol. 7, pp. 94205–94214, Jul. 2019.

A. Khusro, M. S. Hashmi, and A. Q. Ansari, "Exploring Support Vector Regression for Modeling of GaN HEMT," in IEEE MTT-S International Microwave and RF Conference, Kolkata, India, Nov. 2018, pp. 1–3.

A. Khusro, M. S. Hashmi, A. Q. Ansari, and M. Auyenur, "A new and Reliable Decision Tree Based Small-Signal Behavioral Modeling of GaN HEMT," in 62nd International Midwest Symposium on Circuits and Systems, Dallas, TX, USA, Aug. 2019, pp. 303–306.

A. Khusro, S. Husain, M. S. Hashmi, M. Auyuneur, and A. Q. Ansari, "A Reliable and Fast ANN Based Behavioral Modeling Approach for GaN HEMT," in 16th International Conference on Synthesis, Modeling, Analysis and Simulation Methods and Applications to Circuit Design, Lausanne, Switzerland, Jul. 2019, pp. 277–280.

A. Khusro, M. S. Hashmi, and A. Q. Ansari, "Enabling the development of accurate intrinsic parameter extraction model for GaN HEMT using support vector regression (SVR)," IET Microwaves, Antennas & Propagation, vol. 13, no. 9, pp. 1457–1466, 2019.

A. Khusro, S. Husain, M. S. Hashmi, and A. Q. Ansari, "Small signal behavioral modeling technique of GaN high electron mobility transistor using artificial neural network: An accurate, fast, and reliable approach," International Journal of RF and Microwave Computer-Aided Engineering, vol. 30, no. 4, 2020, Art. no. e22112.

A. Khusro, S. Husain, M. S. Hashmi, A. Q. Ansari, and S. Arzykulov, "A Generic and Efficient Globalized Kernel Mapping-Based Small-Signal Behavioral Modeling for GaN HEMT," IEEE Access, vol. 8, pp. 195046–195061, 2020.

S. Husain, A. Khusro, M. Hashmi, G. Nauryzbayev, and M. A. Chaudhary, "Demonstration of CAD Deployability for GPR Based Small-Signal Modelling of GaN HEMT," in IEEE International Symposium on Circuits and Systems, Daegu, Korea, Dec. 2021, pp. 1–5.

S. Husain, M. Hashmi, A. Jarndal, M. Chaudhary, and G. Nauryzbayev, "Comparative Analysis of ANN Architectures for the Development of GaN HEMT Small-Signal Model," in IEEE MTT-S International Microwave and RF Conference, Kanpur, India, Dec. 2021, pp. 1–4.

A. Mishra et al., "Multilayer perceptron–random forest based hybrid machine learning–neural network model for GaN high electron mobility transistor’s parameter estimations," International Journal of RF and Microwave Computer-Aided Engineering, vol. 32, no. 7, 2022, Art. no. e23191.

S. Husain, M. Hashmi, and F. 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, vol. 10, pp. 1015–1032, 2022.

S. Husain, A. Jarndal, M. Hashmi, and F. M. Ghannouchi, "Accurate, Efficient and Reliable Small-Signal Modeling Approaches for GaN HEMTs," IEEE Access, vol. 11, pp. 106833–106846, 2023.

M. Pal and P. Bharati, Applications of Regression Techniques. Berlin, Germany: Springer, 2019.

D. Chicco, M. J. Warrens, and G. Jurman, "The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation," PeerJ Computer Science, vol. 7, Jul. 2021, Art. no. e62.

A. S. Alkarim, A. S. A.-M. Al-Ghamdi, and M. Ragab, "Ensemble Learning-based Algorithms for Traffic Flow Prediction in Smart Traffic Systems," Engineering, Technology & Applied Science Research, vol. 14, no. 2, pp. 13090–13094, Apr. 2024.

F. Bagheri, N. Ghafarnia, and F. Bahrami, "Electrocardiogram (ECG) Signal Modeling and Noise Reduction Using Hopfield Neural Networks," Engineering, Technology & Applied Science Research, vol. 3, no. 1, pp. 345–348, Feb. 2013.

N. K. Al-Shammari et al., "Cardiac Stroke Prediction Framework using Hybrid Optimization Algorithm under DNN," Engineering, Technology & Applied Science Research, vol. 11, no. 4, pp. 7436–7441, Aug. 2021.

Downloads

How to Cite

[1]
Ahmad, N. and Nath, V. 2024. Evaluating Nine Machine Learning Algorithms for GaN HEMT Small Signal Behavioral Modeling through K-fold Cross-Validation. Engineering, Technology & Applied Science Research. 14, 4 (Aug. 2024), 15784–15790. DOI:https://doi.org/10.48084/etasr.7726.

Metrics

Abstract Views: 235
PDF Downloads: 337

Metrics Information