Jie Wang, Censong Liu, Shunzhen You, Dawei Wang, Zhiping Yu
{"title":"Physics-Guided Machine Learning Assisted Characteristic Prediction and Optimization of p-GaN Gate HEMTs","authors":"Jie Wang, Censong Liu, Shunzhen You, Dawei Wang, Zhiping Yu","doi":"10.1002/jnm.70081","DOIUrl":"https://doi.org/10.1002/jnm.70081","url":null,"abstract":"<div>\u0000 \u0000 <p>In this study, we demonstrate the feasibility of predicting and optimizing GaN-based high-electron-mobility field-effect transistors (GaN HEMTs) devices using the physics-guided machine learning (PGML) method. This paper presents a physics-guided artificial neural network (PG-ANN) comprising three networks: Para-net, Vol-net, and G-net, which are trained on a dataset generated through Technology Computer-Aided Design (TCAD) simulations. Our approach emphasizes the importance of first-order derivative characteristics (<span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <msub>\u0000 <mi>g</mi>\u0000 <mi>x</mi>\u0000 </msub>\u0000 <mo>=</mo>\u0000 <mi>∂</mi>\u0000 <mi>I</mi>\u0000 <mo>/</mo>\u0000 <mi>∂</mi>\u0000 <msub>\u0000 <mi>V</mi>\u0000 <mi>x</mi>\u0000 </msub>\u0000 </mrow>\u0000 <annotation>$$ {g}_x=partial I/partial {V}_x $$</annotation>\u0000 </semantics></math>) correlated with physical parameters for enhanced accuracy of IV curve predictions and employs a physics-based loss function to guide the PG-ANN toward accurate solutions. Using PG-ANN, we present the DerivNet model which accurately predicts device characteristics and captures key performance indicators, the threshold voltage <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <msub>\u0000 <mi>V</mi>\u0000 <mi>th</mi>\u0000 </msub>\u0000 </mrow>\u0000 <annotation>$$ {V}_{th} $$</annotation>\u0000 </semantics></math>, on-state resistance <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <msub>\u0000 <mi>R</mi>\u0000 <mi>on</mi>\u0000 </msub>\u0000 </mrow>\u0000 <annotation>$$ {R}_{on} $$</annotation>\u0000 </semantics></math>, and the maximum drain current <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <msub>\u0000 <mi>I</mi>\u0000 <mtext>dmax</mtext>\u0000 </msub>\u0000 </mrow>\u0000 <annotation>$$ {I}_{dmax} $$</annotation>\u0000 </semantics></math>. The PGML method has the potential to significantly expedite device process optimization and is a promising numerical methodology to assist the modeling framework in Design Technology Co-Optimization (DTCO) flow.</p>\u0000 </div>","PeriodicalId":50300,"journal":{"name":"International Journal of Numerical Modelling-Electronic Networks Devices and Fields","volume":"38 4","pages":""},"PeriodicalIF":1.6,"publicationDate":"2025-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144666392","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"An Ingenious DGS Based Door Lever Shaped–Flexible Ultra-Wide Band Antenna With Reduced SAR for Remote Healthcare, Bioelectronics, and Advancing Future AR and VR Technology","authors":"Aparna Singh, R. K. Dwivedi, V. K. Singh","doi":"10.1002/jnm.70088","DOIUrl":"https://doi.org/10.1002/jnm.70088","url":null,"abstract":"<div>\u0000 \u0000 <p>Conventional antennas are typically made from rigid materials, limiting their flexibility and adaptability for wearable applications. This work presents a novel flexible ultra-wideband (UWB) antenna integrated with electro-textiles, operating over the 3.55–14.3 GHz frequency range. The proposed antenna, made from jeans fabric with low dielectric properties, ensures a reduced specific absorption rate (SAR) and is optimized for multiple applications. These include consumer bioelectronics for real-time health monitoring, biomedical devices for drug delivery, and C-band communications used on satellites. Moreover, these applications incorporate augmented and virtual reality (AR/VR) technology for psychiatric care and the Industrial Internet of Things (IIoT). The antenna also supports Wireless Local Area Network (WLAN) and Rapid Auto Steering (RAS) systems, which were also used for cancer detection. The antenna attains an impedance bandwidth of 120% within the 3.55–14.3 GHz range, with resonance frequencies at 3.73, 8.8, and 12.8 GHz, all exhibiting a return loss below −10 dB (i.e., −19.8, −23.7, and 16.7 dB). It features an omnidirectional and isotropic radiation pattern, ensuring reliable performance across various operational environments. The compact prototype measures 52.8 × 60 × 1.076 mm<sup>3</sup> (0.65<i>λ</i><sub>0</sub> × 0.74<i>λ</i><sub>0</sub> × 0.013<i>λ</i><sub>0</sub> at 3.73 GHz), achieving a peak gain of 4.6 dB and an efficiency of 97.12% at 3.73 GHz. Including a Defective Ground Structure (DGS) and a line feed at the lower edge enhances impedance matching and overall antenna performance. Bending tests and SAR analysis confirm safe exposure levels, with a measured SAR of 0.99 W/kg at 12.8 GHz for 10 g of tissue, ensuring nominal health risks analogous to prolonged RF exposure. This study highlights the potential of flexible textile-based antennas for advanced healthcare, wireless communication, and wearable electronics.</p>\u0000 </div>","PeriodicalId":50300,"journal":{"name":"International Journal of Numerical Modelling-Electronic Networks Devices and Fields","volume":"38 4","pages":""},"PeriodicalIF":1.6,"publicationDate":"2025-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144666391","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Lanlong Liu, Qian Zhao, Lu Liu, Yingxiao Qiao, Jingjing Gao
{"title":"A Lightweight Network Based on Multi-Scale Convolutional Neural Network and Gated Transformer for EEG Emotion Classification","authors":"Lanlong Liu, Qian Zhao, Lu Liu, Yingxiao Qiao, Jingjing Gao","doi":"10.1002/jnm.70087","DOIUrl":"https://doi.org/10.1002/jnm.70087","url":null,"abstract":"<div>\u0000 \u0000 <p>To address the complementary advantages of local feature extraction in EEG signals and global dependency modeling while overcoming the high computational demands of conventional Transformers, this study proposes an innovative Multi-scale Convolutional and Gated Transformer Fusion Model (MC-GTF). The model leverages the parallel processing capability of multi-scale convolutional networks for efficient local feature extraction, combined with a gated Transformer mechanism that effectively captures long-range dependencies with reduced computational complexity. Using power spectral density (PSD) features from 11-channel DEAP dataset EEG recordings as input, our approach strategically groups the electrodes into three functional brain regions for parallel spatial feature processing. The architecture employs a sequential design where multi-scale convolutional layers perform local inter-channel feature extraction, followed by gated Transformer layers that learn global inter-region relationships. This hybrid design achieves competitive performance while maintaining significantly lower parameter requirements than conventional approaches, offering a practical and efficient solution for real-world EEG-based emotion recognition applications. The model achieved good classification results even with less parameters, as indicated by accuracy and <i>F</i>1 score for cross-subject classification on the DEAP dataset. In addition, its classification efficiency was significantly improved.</p>\u0000 </div>","PeriodicalId":50300,"journal":{"name":"International Journal of Numerical Modelling-Electronic Networks Devices and Fields","volume":"38 4","pages":""},"PeriodicalIF":1.6,"publicationDate":"2025-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144635330","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Indirect IMC-PID Controller Design With Zero Relative Order–IMC Filter","authors":"Bipin Singh, Bharat Verma, Prabin Kumar Padhy","doi":"10.1002/jnm.70086","DOIUrl":"https://doi.org/10.1002/jnm.70086","url":null,"abstract":"<div>\u0000 \u0000 <p>In this manuscript, a new indirect internal model control (IMC)-based proportional-integral-derivative (PID) controller is designed for stable, integral, and unstable processes with time delay. A zero relative order (ZRO)–IMC filter is introduced, which acts as a lead compensator, enhancing the controller's performance. The proposed method ensures a higher phase margin and improves transient performance. The tuning method allows flexibility in changing system robustness by adjusting the value of the proposed tuning variable <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mfenced>\u0000 <mi>p</mi>\u0000 </mfenced>\u0000 </mrow>\u0000 <annotation>$$ left(boldsymbol{p}right) $$</annotation>\u0000 </semantics></math>, resulting in good set-point tracking and disturbance rejection. This tuning parameter has a monotonous relationship with system robustness within the specified range. The efficacy of the proposed tuning method is validated through simulation studies and an experimental case study on a DC motor for speed control, and the results are compared with existing IMC-PID controllers.</p>\u0000 </div>","PeriodicalId":50300,"journal":{"name":"International Journal of Numerical Modelling-Electronic Networks Devices and Fields","volume":"38 4","pages":""},"PeriodicalIF":1.6,"publicationDate":"2025-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144647235","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Benhao Jin, Zefang Hao, Giovanni Crupi, Jialin Cai
{"title":"Design of A Broadband Asymmetric Doherty PA Using PSO Algorithm With Dynamic Variable Hyperparameters","authors":"Benhao Jin, Zefang Hao, Giovanni Crupi, Jialin Cai","doi":"10.1002/jnm.70085","DOIUrl":"https://doi.org/10.1002/jnm.70085","url":null,"abstract":"<div>\u0000 \u0000 <p>In this article, a particle swarm optimization algorithm with dynamic variable hyperparameter is proposed and applied to the optimization design of a wideband asymmetric Doherty power amplifier (DPA). Compared with the optimization algorithm in the common electronic design automation software and the traditional PSO algorithm, the proposed algorithm has stronger convergence and higher optimization performance. The test results show that in the operating frequency band of 1.5–2.2 GHz, the saturation output power (Pout) reaches 43.9–45.1 dBm, and the saturation drain efficiency (DE) reaches 60.3%–64.9%. Additionally, the DE can reach 48%–56% when the back-off is greater than 9 dB. An evaluation of linearity and digital predistortion has also been conducted under the excitation of a 20-MHz 5G new radio (NR) signal. For this DPA, excellent linearity is demonstrated.</p>\u0000 </div>","PeriodicalId":50300,"journal":{"name":"International Journal of Numerical Modelling-Electronic Networks Devices and Fields","volume":"38 4","pages":""},"PeriodicalIF":1.6,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144635236","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xin Liu, Xiao Huang, Yuhong Wei, Huanhuan Jia, Yang Lu, Ziyue Zhao, Chupeng Yi, Ting Feng, Xiao'ou Song, Xiaohua Ma
{"title":"A Complexity-Reduced TD-PHD Model for Digital Predistortion of 5G Handset Power Amplifiers With Load Mismatch","authors":"Xin Liu, Xiao Huang, Yuhong Wei, Huanhuan Jia, Yang Lu, Ziyue Zhao, Chupeng Yi, Ting Feng, Xiao'ou Song, Xiaohua Ma","doi":"10.1002/jnm.70077","DOIUrl":"https://doi.org/10.1002/jnm.70077","url":null,"abstract":"<div>\u0000 \u0000 <p>Power amplifiers (PAs) in mobile handsets are sensitive to changes in antenna impedance, thus suffering from load mismatch and generating complicated nonlinear distortion frequently. To solve this issue, a complexity-reduced time domain poly-harmonic distortion (CR-TD-PHD) model is proposed for the digital predistortion (DPD) linearization of handset PAs with load mismatch. By implementing a set of modified dual-input magnitude-selective affine (MSA) functions, the proposed CR-TD-PHD model can describe the inter-modulation terms of the input signal and reflection signal accurately while avoiding the use of high-order polynomial functions. Experimental tests are carried out on a load-mismatched PA with a 100-MHz 5G NR signal, and the results demonstrate that the proposed CR-TD-PHD model not only successfully reduces the complexity but also retains high linearization accuracy.</p>\u0000 </div>","PeriodicalId":50300,"journal":{"name":"International Journal of Numerical Modelling-Electronic Networks Devices and Fields","volume":"38 4","pages":""},"PeriodicalIF":1.6,"publicationDate":"2025-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144598689","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Operational Amplifier-Based Memcapacitor Emulators and Their Applications","authors":"Shalini, Kunwar Singh, Shireesh Kumar Rai","doi":"10.1002/jnm.70078","DOIUrl":"https://doi.org/10.1002/jnm.70078","url":null,"abstract":"<div>\u0000 \u0000 <p>This work proposes three configurations of memcapacitor emulators based on operational amplifiers. The first two configurations utilize two operational amplifiers, three memristors, one resistor, and one capacitor. The third configuration requires two operational amplifiers, one capacitor, one memristor, and three resistors for its realization. The key innovation of the proposed circuits lies in integrating a memristor, which introduces non-linearity and memory capabilities, making it ideal for emulating memcapacitive behavior. The proposed circuits demonstrate simplified structures compared to most existing designs while achieving reliable performance across a frequency range of up to 6 kHz. The LTspice tool has been utilized to perform all simulations. The pinched hysteresis loops are plotted to validate the memcapacitive behavior, the memory-retaining property is evaluated using a non-volatile plot, and robustness is verified by performing the Monte Carlo simulations. The proposed emulators are validated utilizing both the SPICE model of the memristor and a memristor emulator circuit. Experimental results have been included to validate the key fingerprint, that is, pinched hysteresis loop of the circuit using commercially available <span>AD</span>711 ICs. Additionally, three applications—neural spike generation, adaptive learning circuit, and chaotic oscillator—are demonstrated, highlighting the emulator's versatility in neuromorphic computing and adaptive systems.</p>\u0000 </div>","PeriodicalId":50300,"journal":{"name":"International Journal of Numerical Modelling-Electronic Networks Devices and Fields","volume":"38 4","pages":""},"PeriodicalIF":1.6,"publicationDate":"2025-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144589515","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Rajan Singh, V. Radhika Devi, Trupti R. Lenka, Rohit Choudhary, Pulkit Singh, Ashutosh Srivastava, Prabhakar Agarwal, Giovanni Crupi
{"title":"Polarization-Induced Versus Delta-Doped β-Ga2O3 HEMTs—A Performance Comparison","authors":"Rajan Singh, V. Radhika Devi, Trupti R. Lenka, Rohit Choudhary, Pulkit Singh, Ashutosh Srivastava, Prabhakar Agarwal, Giovanni Crupi","doi":"10.1002/jnm.70080","DOIUrl":"https://doi.org/10.1002/jnm.70080","url":null,"abstract":"<div>\u0000 \u0000 <p>This report presents a performance comparison between two types of β-Ga<sub>2</sub>O<sub>3</sub>-based high electron mobility transistors (BGO-HEMTs), where channel doping is achieved through either polarization-induced doping (PID) or delta-doped (DD) modulation doping. The study evaluates and contrasts the performance characteristics of these two types of BGO-HEMTs. Using an optical phonon model to capture enhanced electron–phonon interactions in wide bandgap semiconductors, the maximum current density is estimated in both devices. Highly polarized AlN employed as barrier layers in PID BGO-HEMTs results in significantly higher conduction band offsets, thus achieving an order of magnitude higher sheet carrier density compared to DD BGO-HEMTs. Higher 2-DEG density ensures 2.5× higher current density and one order lower on-resistance in PID over DD BGO-HEMTs. Furthermore, PID BGO-HEMTs outperform as DC switches and require 13× lower gate periphery compared to DD BGO-HEMTs for the equal power rating. In addition, AlN as a gate barrier in PID BGO-HEMTs facilitates better thermal conductivity over DD BGO-HEMTs. The achieved results show the potential of PID β-Ga<sub>2</sub>O<sub>3</sub> HEMTs for emerging DC power switching and compact high-power RF electronics applications.</p>\u0000 </div>","PeriodicalId":50300,"journal":{"name":"International Journal of Numerical Modelling-Electronic Networks Devices and Fields","volume":"38 4","pages":""},"PeriodicalIF":1.6,"publicationDate":"2025-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144582107","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Multilayer Neural Networks Enhanced With Hybrid Methods for Solving Fractional Partial Differential Equations","authors":"Amina Hassan Ali, Norazak Senu, Ali Ahmadian","doi":"10.1002/jnm.70073","DOIUrl":"https://doi.org/10.1002/jnm.70073","url":null,"abstract":"<div>\u0000 \u0000 <p>This paper introduces a novel multilayer neural network technique to solve partial differential equations with non-integer derivatives (FPDEs). The proposed model is a deep feed-forward multiple layer neural network (DFMLNN) that is trained using advanced optimization approaches, namely adaptive moment estimation (Adam) and limited-memory Broyden-Fletcher-Goldfarb-Shanno (L-BFGS), which integrate neural networks. First, the Adam method is employed for training, and then the model is further improved using L-BFGS. The Laplace transform is used, concentrating on the Caputo fractional derivative, to approximate the FPDE. The efficacy of this strategy is confirmed through rigorous testing, which involves making predictions and comparing the outcomes with exact solutions. The results illustrate that this combined approach greatly improves both precision and effectiveness. This proposed multilayer neural network offers a robust and reliable framework for solving FPDEs.</p>\u0000 </div>","PeriodicalId":50300,"journal":{"name":"International Journal of Numerical Modelling-Electronic Networks Devices and Fields","volume":"38 4","pages":""},"PeriodicalIF":1.6,"publicationDate":"2025-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144551014","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"QUDEN: A Matlab Package for First-Principles Quantum-Transport Engineering of 2D Material-Based Nanodevices","authors":"Mislav Matić, Mirko Poljak","doi":"10.1002/jnm.70079","DOIUrl":"https://doi.org/10.1002/jnm.70079","url":null,"abstract":"<div>\u0000 \u0000 <p>The simulation of nanotransistors and the inclusion of all relevant physics is a challenging task, especially when working with one-dimensional (1D) nanomaterials in which quantum confinement strongly influences the material properties and device performance. Several groups have already developed state-of-the-art quantum transport simulators based on the first principles non-equilibrium Green's function (NEGF) formalism, and a few have been commercialized. However, these tools are computationally demanding as they require solving the NEGF and the 3D Poisson equation. Here we present an open-source quantum-transport solver for the first principles device engineering for nanoelectronics (QUDEN) implemented in <span>Matlab</span>. QUDEN uses NEGF and the ballistic top-of-the-barrier model to simulate ultrascaled field-effect transistors (FETs) with channels made of nanoribbons of 2D materials, while the device Hamiltonian is obtained using first principles density functional theory (DFT) in combination with maximally localized Wannier functions (MLWFs). This approach preserves the accuracy of the full NEGF-3D Poisson simulation in the on-state while using a simplified self-consistent electrostatics that leads to a much lower computational burden. Taking monolayer germanium-selenide (GeSe) nanoribbons as an example, we show that QUDEN can be used for fast screening and accurate evaluation of numerous 2D/1D materials for future FETs.</p>\u0000 </div>","PeriodicalId":50300,"journal":{"name":"International Journal of Numerical Modelling-Electronic Networks Devices and Fields","volume":"38 4","pages":""},"PeriodicalIF":1.6,"publicationDate":"2025-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144551015","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}