检索结果-内蒙古大学图书馆

A Physical-Based Artificial Neural Networks Compact Modeling Framework for Emerging FETs

IEEE Transactions on Electron Devices 2024年第1期71卷 223-230页

作者： Yang, Ya-Shu Li, Yiming Kola, Sekhar Reddy Reddy National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory The Institute of Communications Engineering Hsinchu300093 Taiwan National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory Institute of Communications Engineering Institute of Biomedical Engineering Department of Electronics and Electrical Engineering Hsinchu300093 Taiwan National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory Electrical Engineering and Computer Science International Graduate Program Hsinchu300093 Taiwan

We report a compact modeling framework based on the Grove-Frohman (GF) model and artificial neural networks (ANNs) for emerging gate-all-around (GAA) MOSFETs. The framework consists of two ANNs;the first ANN constructed with the drain current model not only can capture the main trend of device I - V characteristics but also can predict its variation even when the amount of training data for the ANN is insufficient or outside the range of applied biases. The second one is then designed to improve the model accuracy by further minimizing the errors between the target and the model outputs. We implement the proposed framework to accurately model emerging GAA nanosheet (NS) MOSFETs and complementary FETs (CFETs) without suffering from divergent issues in circuit simulation. In addition, nonphysical behaviors, such as nonzero current at zero bias, do not occur in the modeling framework. Compared to recently reported machine-learning (ML) models, our approach can achieve a similar level of model accuracy with merely 20% amount of the training data. © 1963-2012 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Prediction of compressive strength of high-performance concrete using optimization machine learning approaches with SHAP analysis

引用

Journal of Building Pathology and Rehabilitation 2024年第2期9卷 1-20页

作者： Islam, Md Mahamodul Das, Pobithra Rahman, Md Mahbubur Naz, Fasiha Kashem, Abul Nishat, Mosaraf Hosan Tabassum, Nujhat Department of Informatics University of Oslo Oslo Norway Department of Civil Engineering Leading University Sylhet Bangladesh Department of Industrial and Systems Engineering Lamar University Beaumont United States Department of Computer Science University of Agriculture Faisalabad Faisalabad Pakistan Department of Civil and Environmental Engineering Shahjalal University of Science & amp Technology Sylhet Bangladesh Department of Civil and Environmental Engineering Islamic University Of Technology -IUT(OIC) Gazipur Bangladesh Department of Electrical and Computer Engineering North South University Dhaka Bangladesh

Forecasting the compressive strength of high-performance concrete (HPC) is crucial for its practical applications. However, conducting experimental tests for this purpose demands significant resources and time. In recent times, data-driven modeling, particularly machine learning, has become prominent in this field. Thus, this study employed machine learning methods, including Gradient Boosting, Random Forest, and CatBoost algorithms, to predict the compressive strength of high-performance concrete (HPC). Furthermore, interpretable algorithms like SHapley Additive exPlanations (SHAP) were utilized in this study to assess the contribution of input variables to predictions. The dataset includes parameters such as cement, blast furnace slag, fly ash, water, coarse aggregate, sand, and age as input variables, with compressive strength as the output variable for models development. The CatBoost model performance was superior to GBM and RF models, with R² values of 0.979 for the training stage and 0.959 for the testing stage. Moreover, it demonstrated minimal mean absolute errors (MAE) of 2.37 MPa and 3 MPa for compressive strength prediction in the training and testing stages, respectively. Furthermore, the SHAP analysis revealed that age, cement, and superplasticizer are the primary influencers in determining compressive strength. The machine learning models presented in this study exhibit promising potential for practical implementation in different engineering applications. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Compressive strength High-performance concrete Machine learning SHAP analysis

来源：评论

学校读者我要写书评

暂无评论

Phase Shift Design of Three Phase Transformers for Soft Switching of Three Phase Dual Active Bridge

Phase Shift Design of Three Phase Transformers for Soft Swit...

引用

2023 IEEE Energy Conversion Congress and Exposition, ECCE 2023

作者： Mansour, Mohamed Ojo, Joseph Olorunfemi Tennessee Tech University Laboratory of Power Electronics and Electric Machines Department of Electrical and Computer Engineering CookevilleTN38505 United States

ISBN: (纸本)9798350316445

The three-phase dual active bridge plays a pivotal role in the power transfer, owing to its higher-power density with respect to single phase variant. However, it suffers from a low efficiency during operation at light load conditions due to loss of soft device switching. By dividing the phase secondary winding into two, unevenly, the efficiency can be improved by ensuring soft switching at low load conditions with appropriate phase shift angles between the primary and secondary voltages. Thus, this paper provides a detailed mathematical analysis for three phase transformers, which shows the effect of phase secondary windings partitioning on the phase shift angles of induced voltages. © 2023 IEEE.

关键词： Three phase dual active bridge wye-extended delta connection wye-zigzag transformer zero voltage switching

来源：评论

学校读者我要写书评

暂无评论

Managing natural disasters: An analysis of technological advancements, opportunities, and challenges

引用

Internet of Things and Cyber-Physical systems 2024年第1期4卷 99-109页

作者： Krichen, Moez Abdalzaher, Mohamed S. Elwekeil, Mohamed Fouda, Mostafa M. Al-Baha University Al-Baha65528 Saudi Arabia ReDCAD Laboratory University of Sfax Sfax3029 Tunisia Seismology Department National Research Institute of Astronomy and Geophysics Helwan Cairo11421 Egypt Department of Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University. Menoufia Menouf32952 Egypt Department of Electrical and Computer Engineering College of Science and Engineering Idaho State University PocatelloID83209 United States

Natural disasters (NDs) have always been a major threat to human lives and infrastructure, causing immense damage and loss. In recent years, the increasing frequency and severity of natural disasters have highlighted the need for more effective and efficient disaster management strategies. In this context, the use of technology has emerged as a promising solution. In this survey paper, we explore the employment of recent technologies in order to relieve the impacts of various natural disasters. We provide an overview of how different technologies such as Remote Sensing, Radars and Satellite Imaging, internet-of-things (IoT), Smartphones, and Social Media can be utilized in the management of NDs. By utilizing these technologies, we can predict, respond, and recover from NDs more effectively, potentially saving human lives and minimizing infrastructure damage. The paper also highlights the potential benefits, limitations, and challenges associated with the implementation of these technologies for natural disaster management purposes. While the use of technology can significantly improve NDM, there are also various challenges that need to be addressed, such as the cost of implementation and the need for specialized knowledge and skills. Overall, this survey paper provides a comprehensive overview of the use of technology in managing NDs and sheds light on the important role such technologies can play in NDM. By exploring the potential applications of different technologies, this paper aims to contribute to the development of more effective and sustainable disaster management strategies. © 2023 The Authors

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Robust Load Frequency Control of Two-Area Interconnected Power System Using Fuzzy-I Controller

Robust Load Frequency Control of Two-Area Interconnected Pow...

引用

2023 IEEE IAS Global Conference on Emerging Technologies, GlobConET 2023

作者： Wazir, Awadh Ba Alhussainy, Abdullah Ali Alghamdi, Sultan Rawa, Muhyaddin Sindi, Hatem F. King Abdulaziz University K. A. CARE Energy Research and Innovation Center Smart Grids Research Group Center of Research Excellence in Renewable Energy and Power Systems Department of Electrical and Computer Engineering Jeddah Saudi Arabia King Abdulaziz University Smart Grids Research Group Center of Research Excellence in Renewable Energy and Power Systems Department of Electrical and Computer Engineering Jeddah Saudi Arabia King Abdulaziz University Electrical and Computer Engineering Jeddah Saudi Arabia

ISBN: (纸本)9798350331790

The paper proposes a Fuzzy-I controller for optimal load frequency control (LFC) in a two-area interconnected power system. The proposed controller is composed of a fuzzy logic controller (FLC) and an integral (I) controller. To achieve a better dynamic response for the LFC, the integral controller and frequency bias parameters of the secondary loop are tuned using the Particle Swarm Optimization (PSO) technique. To boost the efficiency of the optimization, a proposed objective function using the integral of squared error (ISE) and settling time is used. A comparative study and analysis are conducted between the base system controller, optimized I controller, and the proposed controller under three different scenarios of load disturbances. The robustness of the proposed controller is shown by performing a sensitivity analysis for various system parameters and operating conditions. Moreover, the performance of the proposed controller was compared with the previous LFC approaches published in the literature. The simulation outcomes demonstrate that the proposed method has an outstanding performance. The work results are presented as time-domain simulations using MATLAB/SIMULINK tool. © 2023 IEEE.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Power-Measurement-Based Channel Autocorrelation Estimation for IRS-Assisted Wideband Communications

引用

IEEE Transactions on Wireless Communications 2025年第6期24卷 4647-4662页

作者： Sun, He Zhu, Lipeng Mei, Weidong Zhang, Rui National University of Singapore Department of Electrical and Computer Engineering 117583 Singapore University of Electronic Science and Technology of China National Key Laboratory of Wireless Communications 611731 China The Chinese University of Hon g Kong School of Science and Engineering Shenzhen Research Institute of Big Data Guangdong Shenzhen518172 China

Channel state information (CSI) is essential to the performance optimization of intelligent reflecting surface (IRS)-aided wireless communication systems. However, the passive and frequency-flat reflection of IRS, as well as the high-dimensional IRS-reflected channels, have posed practical challenges for efficient IRS channel estimation, especially in wideband communication systems with significant multi-path channel delay spread. To tackle the above challenge, we propose a novel neural network (NN)-empowered IRS channel estimation and passive reflection design framework for the wideband orthogonal frequency division multiplexing (OFDM) communication system based only on the user’s reference signal received power (RSRP) measurements with time-varying random IRS training reflections. As RSRP is readily accessible in existing communication systems, our proposed channel estimation method does not require additional pilot transmission in IRS-aided wideband communication systems. In particular, we show that the average received signal power over all OFDM subcarriers at the user terminal can be represented as the prediction of a single-layer NN composed of multiple subnetworks with the same structure, such that the autocorrelation matrix of the wideband IRS channel can be recovered as their weights via supervised learning. To exploit the potential sparsity of the channel autocorrelation matrix, a progressive training method is proposed by gradually increasing the number of subnetworks until a desired accuracy is achieved, thus reducing the training complexity. Based on the estimates of IRS channel autocorrelation matrix, the IRS passive reflection is then optimized to maximize the average channel power gain over all subcarriers. Numerical results indicate the effectiveness of the proposed IRS channel autocorrelation matrix estimation and passive reflection design under wideband channels, which can achieve significant performance improvement compared to the existing IRS re

关键词： Orthogonal frequency division multiplexing

来源：评论

学校读者我要写书评

暂无评论

SmokerViT: A Transformer-Based Method for Smoker Recognition

引用

computers, Materials & Continua 2023年第10期77卷 403-424页

作者： Ali Khan Somaiya Khan Bilal Hassan Rizwan Khan Zhonglong Zheng College of Mathematics and Computer Science Zhejiang Normal UniversityJinhua321004China School of Electronics Engineering Beijing University of Posts and TelecommunicationsBeijing100876China Department of Electrical Engineering and Computer Science Khalifa University of Science and TechnologyAbu Dhabi127788United Arab Emirates Key Laboratory of Intelligent Education of Zhejiang Province Zhejiang Normal UniversityJinhua321004China

Smoking has an economic and environmental impact on society due to the toxic substances it *** Neural Networks(CNNs)need help describing low-level features and can miss important ***,accurate smoker detection is vital with minimum false *** answer the issue,the researchers of this paper have turned to a self-attention mechanism inspired by the ViT,which has displayed state-of-the-art performance in the classification *** effectively enforce the smoking prohibition in non-smoking locations,this work presents a Vision Transformer-inspired model called SmokerViT for detecting ***,this research utilizes a locally curated dataset of 1120 images evenly distributed among the two classes(Smoking and NotSmoking).Further,this research performs augmentations on the smoker detection dataset to have many images with various representations to overcome the dataset size *** convolutional operations used in most existing works,the proposed SmokerViT model employs a self-attention mechanism in the Transformer block,making it suitable for the smoker classification ***,this work integrates the multi-layer perceptron head block in the SmokerViT model,which contains dense layers with rectified linear activation and linear kernel regularizer with L2 for the recognition *** work presents an exhaustive analysis to prove the efficiency of the proposed SmokerViT *** performance of the proposed SmokerViT performance is evaluated and compared with the existing methods,where it achieves an overall classification accuracy of 97.77%,with 98.21%recall and 97.35%precision,outperforming the state-of-the-art deep learning models,including convolutional neural networks(CNNs)and other vision transformer-based models.

关键词： Smoker recognition SmokerViT deep learning transformer for vision

来源：评论

学校读者我要写书评

暂无评论

Data-driven Power Flow Method Based on Exact Linear Regression Equations

引用

Journal of Modern Power systems and Clean Energy 2022年第3期10卷 800-804页

作者： Yanbo Chen Chao Wu Junjian Qi State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources School of Electrical&Electronic EngineeringNorth China Electric Power UniversityBeijing 102206China Department of Electrical and Computer Engineering Stevens Institute of TechnologyHobokenNJ 07030USA

Power flow(PF)is one of the most important calculations in power *** widely-used PF methods are the Newton-Raphson PF(NRPF)method and the fast-decoupled PF(FDPF)*** smart grids,power generations and loads become intermittent and much more uncertain,and the topology also changes more frequently,which may result in significant state shifts and further make NRPF or FDPF difficult to *** address this problem,we propose a data-driven PF(DDPF)method based on historical/simulated data that includes an offline learning stage and an online computing *** the offline learning stage,a learning model is constructed based on the proposed exact linear regression equations,and then the proposed learning model is solved by the ridge regression(RR)method to suppress the effect of data *** online computing stage,the nonlinear iterative calculation is not *** results demonstrate that the proposed DDPF method has no convergence problem and has much higher calculation efficiency than NRPF or FDPF while ensuring similar calculation accuracy.

关键词： Data driven exact linear regression equation Fast-decoupled power flow Newton-Raphson method

来源：评论

学校读者我要写书评

暂无评论

Improvement of dynamic phosphene presentation for a cortical visual prosthesis is task-specific

Improvement of dynamic phosphene presentation for a cortical...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Haozhe Zac Wang Yan Tat Wong Department of Electrical and Computer Systems Engineering Monash University Clayton VIC Australia Department of Electrical and Computer Systems Engineering and Department of Physiology Clayton Monash University Clayton VIC Australia

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

Cortical visual prostheses can restore vision by directly stimulating the neurons in the visual cortex. The goal of these prostheses is to elicit sufficient light perception, known as phosphenes, to represent complex scenes. However, stimulating a large number of electrodes in cortical visual prostheses can be problematic. This may result in distorted visual perception and failure to present the desired visual stimuli. Previous studies have successfully presented simple patterns, such as letters, by dynamically utilizing a single phosphene. To represent more complex scenes, we propose a new method of information presentation. This method limits the number of phosphenes elicited simultaneously while sequentially presenting the contours of a visual scene. We evaluated its effectiveness with 8 participants across four different tasks. We found that the improvement provided by this method is task-specific. Our findings underscore the importance of considering the temporal features of prosthetic vision in future designs.

关键词： Electrodes Visualization Neurons Visual prosthesis engineering in medicine and biology Visual perception

来源：评论

学校读者我要写书评

暂无评论

Literature Review of Circulating Current of Parallel Voltage Source Converters

Literature Review of Circulating Current of Parallel Voltage...

引用

2023 IEEE PELS Students and Young Professionals Symposium, SYPS 2023

作者： Zhang, Haoyu Wong, Man-Chung University of Macau State Key Laboratory of Internet of Things for Smart City Department of Electrical and Computer Engineering Faculty of Science and Technology China

ISBN: (纸本)9798350307832

To increase the power density of voltage source converters (VSC) usually use parallel structures. However, parallel VSC will easily introduce circulating current, which can cause a power efficiency decline. This paper gives a review of the circulating current and the solutions of it. Through the analysis of the principle of circulating current generation and the detail of the solutions, this paper gives an overview of the current research stage of circulating current. The technology can be divided into hardware solutions and software solutions are then analyzed and evaluated. © 2023 IEEE.

关键词： Power converters

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：