检索结果-内蒙古大学图书馆

4th IEEE Global Conference for Advancement in technology, GCAT 2023

作者： Sajedul Islam, Md. Tabassum, Fariya Dept. of Electrical & Computer Engineering Rajshahi University of Engineering & Technology Rajshahi Bangladesh

ISBN: (纸本)9798350305258

Wide bandgap (WBG) semiconductor devices namely SiC-MOSFET enable high-frequency power converters, which have benefits over many other switching devices in terms of power density and dynamic performance. However, switching oscillation is a common problem for this class of devices, and it has a lot of unfavorable effects. This work examines the underlying causes of the switching oscillation, its effects on the system, and modeling analysis to derive control mechanisms to prevent undesirable outcomes. This work discusses the underlying causes of the switching oscillation, which are: (1) di/dt or/and dv/dt -induced damped oscillation in the presence of parasitic factors;(2) undamped oscillation brought on by the switch's negative resistance;(3) effect of the negative capacitance phenomena brought on by the semiconductor devices' physical orientation. An effective control approach is proposed in this research work to inhibit the switching oscillation of SiC-MOSFET. The proposed integrator-based damper takes into account the turn on switching oscillation. The performance of the proposed damper is compared with the integral and proportional-integral-derivative (PID) controller for justifying its effectiveness. © 2023 IEEE.

关键词： Control System Power Converter Semiconductor WBG Device

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Feature Selection Techniques and Machine Learning Classifiers for Accurate Classification of Pumpkin Seeds 2

Comparative Analysis of Feature Selection Techniques and Mac...

引用

2nd International Conference on Information and Communication technology for Sustainable Development, ICICT4SD 2023

作者： Siddique, Md Abu Ismail Haque, Fariha Shojol, Md. Shojeb Hossain Rajshahi University of Engineering and Technology Dept. of Electrical and Computer Engineering Rajshahi Bangladesh

ISBN: (纸本)9798350358667

Pumpkin seeds are widely consumed due to their nutritional content and potential health advantages. Accurately categorizing pumpkin seeds based on their diversity and distinct physical properties, such as size, compactness, roundness, and others, is crucial in agriculture, food processing, and research. In this work, two approaches were used to categorize a dataset of pumpkin seeds and establish their relative performance. The first method used a typical machine learning methodology, whereas the second used a filter-based feature selection technique. The filter-based technique used principal component analysis (PCA) and recursive feature elimination (RFE) to extract the most significant features for identifying two varieties of pumpkin seeds. Machine learning classifiers were then used to assess the performance of each strategy. Machine learning classifiers were then applied to evaluate the performance of the approach where Random Forest performed best among all others and achieved 91.80% validation accuracy. On the other hand for the conventional machine learning classifier method, six classifiers were used to evaluate the performance of this approach where the XgBoost classifier performed the best and achieved 95% as training accuracy and 94.87% as validation accuracy. © 2023 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Flexible GTVSG Power Quality Enhancement Using Resilient Heterogeneous Voltage and Current Control 3

Flexible GTVSG Power Quality Enhancement Using Resilient Het...

引用

3rd International Conference on Power, Control and Computing Technologies, ICPC2T 2024

作者： Behera, Sameer Kumar Panda, Anup Kumar Venkataramana Naik, N. Pattnaik, Swapnajit Mohapatra, Prerana Karthik, Markala National Institute of Technology Dept. of Electrical Engineering Rourkela India National Institute of Technology Dept. of Electrical Engineering Raipur India

ISBN: (纸本)9798350349207

This article proposes an resilient heterogeneous voltage and current control scheme (RHVCS) for a three-phase grid-tied virtual synchronous generator (GTVSG) system to provide harmonic compensation and consequently improve the system's power quality. The GTVSG system, as mentioned above, incorporates renewable energy-based distributed generation units (REDG) profoundly photovoltaic generators (PVGs) on the source terminal, having dynamic input characteristics. Considering the control aspects for GTVSG, it adopts various current and voltage control methods discussed in the literature. However, the proposed RHVCS implemented in the GTVSG digital controller helps reduce the number of lowpass/band-pass filter involved. Furthermore, the proposed controller uses a phase lock loop (PLL) less strategy which automatically necessitates the identification of the deviation in the GTVSG system frequency from the power control loop. The proposed RHVCS incorporates three different harmonic compensation objectives illustrated in different sections. Additionally, the proposed control strategy minimizes the digital controller's complexity without infringing on the harmonic compensation's performance, which is commendable. Finally, the above controller is implemented in MATLAB/Simulink platform © 2024 IEEE.

关键词： Power quality

来源：评论

学校读者我要写书评

暂无评论

A Case for Speculative Address Translation with Rapid Validation for GPUs 57

A Case for Speculative Address Translation with Rapid Valida...

引用

57th Annual IEEE/ACM International Symposium on Microarchitecture, MICRO 2024

作者： Park, Junhyeok Kwon, Osang Lee, Yongho Kim, Seongwook Byeon, Gwangeun Yoon, Jihun Nair, Prashant J. Hong, Seokin Sungkyunkwan University Dept. of Electrical and Computer Engineering Korea Republic of Sungkyunkwan University Dept. of Semiconductor Convergence Engineering Korea Republic of University of British Columbia Dept. of Electrical and Computer Engineering Canada

ISBN: (纸本)9798350350579

A unified address space is vital for heterogeneous systems as it enables efficient data sharing between CPUs and GPUs. However, GPU address translation faces challenges due to high TLB pressure, particularly with irregular and memory-intensive applications. Compared to an ideal scenario, we observe that address translation overheads cause a slowdown of up to 34.5% in modern heterogeneous systems. This paper introduces Avatar, a novel framework to accelerate address translation in GPUs. Avatar comprises two key components: Contiguity-Aware Speculative Translation (CAST) and In-Cache Validation (CAVA) mechanisms. Avatar identifies the potential for predicting virtual-to-physical address mapping by monitoring contiguous pages that lie in both virtual and physical address spaces. Leveraging this insight, CAST speculatively translates virtual addresses into physical addresses. This speculative address translation enables immediate data fetching into GPUs while addressing translation occurs in the background, reducing TLB-miss overhead. Unfortunately, modern GPUs lack support for speculative execution, which limits CAST's performance gain. Data fetched from speculated physical addresses is unusable until validation. CAVA addresses this limitation by quickly validating speculated physical addresses. To this end, CAVA embeds page mapping information into each 32B sector of 128B cache lines. Thus, CAVA enables fetching a sector block from memory for a speculated address and rapidly validating the speculative translation using the embedded mapping information. Our experiments show that Avatar achieves a 90.3% (high) speculation accuracy and improves GPU performance by 37.2% (on average). © 2024 IEEE.

关键词： Virtual addresses

来源：评论

学校读者我要写书评

暂无评论

Exactly Discretized Model of FitzHugh Nagumo Oscillator Using Taylor-Lie Approach 6

Exactly Discretized Model of FitzHugh Nagumo Oscillator Usin...

引用

6th International Conference on Energy, Power and Environment, ICEPE 2024

作者： Meena, Gagan Deep Janardhanan, S. National Institute of Technology Dept. of Electrical Engineering Patna India Indian Institute of Technology Dept. of Electrical Engineering Delhi India

ISBN: (纸本)9798350379297

This paper proposes an exactly discretized model for FitzHugh-Nagumo oscillatory system. A recent technique of discretization, Taylor-Lie discretization is used for the exact discretized model. Exact discretization for nonlinear models is new and the proposed model has been compared with canonical discretization technique to establish the quality of Taylor-Lie discretization approach. A set of system theoretic analyses supports the obtained results which includes time response analysis, phase portrait analysis, effects of sampling time T and external stimulus Iext on the system state trajectories have been presented and discussed. The efficiency of the proposed approach have been explored on the basis of approximation error visible in simulation results. © 2024 IEEE.

关键词： Nonlinear simulations

来源：评论

学校读者我要写书评

暂无评论

TRANSFORMER FAULT DIAGNOSIS METHOD BASED ON ReliefF AND HPO-SVM

UPB Scientific Bulletin, Series C: Electrical Engineering an...

引用

UPB Scientific Bulletin, Series C: electrical engineering and computer Science 2023年第3期85卷 137-152页

作者： Zhang, Xiaohu Ning, Huanyu Dept. of Electrical and Information Engineering Hunan University of Technology China College of Electrical and Information Engineering Hunan University of Technology Zhuzhou China

In order to improve the correct judgment rate of fault diagnosis of oil-immersed power transformers, this paper proposes a fault diagnosis method using the combination of the relief feature weight method, HPO-SVM model, and dissolved gas analysis in oil (DGA). First, the method introduces the feature weight algorithm to filter and reduce the dimensionality of the input quantity;second, the probabilistic neural network model is optimized using the predator optimization algorithm, and the SVM model is used to process the DGA ratio set to finally obtain the fault diagnosis results of the transformer. The experiments show that the model with dimensionality reduction using the reliefF feature weight algorithm has higher diagnostic accuracy. The average fault judgment accuracy of HPO-SVM, GWO-SVM, WOA-SVM, and PSO-SVM is 94%, 91.33%, 90%, and 83.33%, respectively, and the average number of iterations is 6.5, 8.9, 12.5, and 15.1, respectively, and the simulation results show that the preferred hybrid feature model has higher correct diagnosis rate and faster convergence seeking speed The simulation results show that the superiority of this scheme is confirmed. © 2023, Politechnica University of Bucharest. All rights reserved.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Reverse engineering for Accurate Standard Drawings of Electric Railway Components: A Case Study with Catenary Clamps

引用

Transactions of the Korean Institute of electrical Engineers 2024年第6期73卷 1038-1041页

作者： Sung, Dong-IL Lee, Jongwoo Oh, Wan-Shik Lee, Hunseo Park, Young Korea National Railway Korea Republic of Dept. of Electrical System Engineering Hanbat National University Korea Republic of Dept. of Railway Electrical Signaling Engineering Graduate School of Railway Seoul National University of Science and Technology Korea Republic of Dept. of Korea Railway Electrification Technology Association Korea Republic of Dept. of Electrical Engineering Hanbat National University Korea Republic of

Accurate design drawings are crucial for the safe and efficient operation of railway systems. However, inconsistencies, errors, and missing dimensions in existing drawings can hinder the manufacturing of identical parts. To address this challenge, this paper proposes a reverse engineering (RE) process to extract standard drawings of electric railway system components based on the Korea Rail Standard Authority (KRSA) specifications. We demonstrate the effectiveness of the proposed RE process by applying it to a high-speed railway catenary clamp. The 3D scanning data was accurately processed, resulting in a high-precision CAD model with an error margin of ±0.8 mm. The generated 2D drawing includes all the necessary details for manufacturing, assembly, and inspection. The results show that the proposed RE process can effectively extract standard drawings of electric railway system components from 3D scanning data. These generated 2D drawings can be used for various purposes, such as manufacturing, maintenance, and BIM (Building Information Modeling) model creation. © The Korean Institute of electrical Engineers.

关键词： Railroads

来源：评论

学校读者我要写书评

暂无评论

Polarimetric Image Fusion Strategies for Improving Target Shape and Contrast in Remote Sensing Applications 21

Polarimetric Image Fusion Strategies for Improving Target Sh...

引用

Electro-Optical and Infrared Systems: technology and Applications XXI 2024

作者： Ratliff, Bradley M. Tyo, J. Scott Taylor, Michael Prikkel, Connor Dept. Electrical & Computer Engineering Dayton University DaytonOH United States Electrical & Computer Systems Engineering Dept. Monash University Melbourne Australia

ISBN: (纸本)9781510681088

Images from passive imaging polarimeters are often displayed in terms of their intensity (s0), degree of linear polarization (DoLP), and angle of polarization (AOP). The AOP and DoLP together generally provide information about shape and surface quality of imaged objects;however, the information conveyed in these images are often difficult to interpret, especially to an analyst unfamiliar with polarization phenomenology. Furthermore, it can be challenging to train machine learning approaches with direct polarimetric information due to the limited availability of application-specific data. Augmenting s0 images with polarimetric information in the form of contrast and shape enhancement thus allows for the data to remain in the domain of traditional EO-IR intensity imagery that is more familiar for both humans and trained networks. In this work we explore several strategies for effectively fusing polarimetric information into s0 imagery to improve target shape and contrast for both human and algorithmic consumption, with a particular focus on remote sensing and target detection applications. © 2024 SPIE.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Deep Variational Sequential Monte Carlo for High-Dimensional Observations

Deep Variational Sequential Monte Carlo for High-Dimensional...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： van Nierop, Wessel L. Shlezinger, Nir van Sloun, Ruud J.G. Dept. of Electrical Engineering Eindhoven University of Technology Eindhoven Netherlands Dept. of Electrical and Computer Engineering Ben-Gurion University of the Negev Beer-Sheva Israel

ISBN: (纸本)9798350368741

Sequential Monte Carlo (SMC), or particle filtering, is widely used in nonlinear state-space systems, but its performance often suffers from poorly approximated proposal and state-transition distributions. This work introduces a differentiable particle filter that leverages the unsupervised variational SMC objective to parameterize the proposal and transition distributions with a neural network, designed to learn from high-dimensional observations. Experimental results demonstrate that our approach outperforms established baselines in tracking the challenging Lorenz attractor from high-dimensional and partial observations. Furthermore, an evidence lower bound based evaluation indicates that our method offers a more accurate representation of the posterior distribution. © 2025 IEEE.

关键词： Particle Filters Sequential Monte Carlo Variational Inference

来源：评论

学校读者我要写书评

暂无评论

High-Performance Face Identification Using Randomly Selected Channels from Hyperspectral Images

High-Performance Face Identification Using Randomly Selected...

引用

2024 IEEE International Conference on Imaging Systems and Techniques, IST 2024

作者： Furusawa, Sota Premachandra, Chinthaka Graduate School of Engineering and Science Shibaura Institute of Technology Dept. of Electrical Engineering and Computer Science Tokyo Japan

ISBN: (纸本)9798350378214

With the recent development of information technology, the importance of protecting personal information has increased. Because of the vulnerability in passwords, biometric authentication is now being used as a method of personal information protection. However, biometric authentication has the possibility of malicious authentication due to the emergence of technology that can generate biometric data that is difficult to duplicate. Therefore, this study aimed to solve the security problems posed by Generative Adversarial Networks (GANs) in biometric authentication by using Hyperspectral Images (HSI). We searched for solutions to the problems identified in previous studies, such as the inability to correctly identify individuals who have not been previously learned and the length of time required for identification. In this paper, we used three channels of data randomly selected from hyperspectral face images for learning to identify individuals by binary classification into 'learned subject (class)' and 'unlearned subjects (classes)'. In this case, discriminators based on the least-squares generative adversarial network (LSGAN) model was developed for each class using three randomly selected channels of data from the HSI for two class classification. The proposed method significantly reduced the identification time and achieved very high discrimination accuracy in all classes. In addition, the results showed high accuracy throughout multiple face identification experiments. © 2024 IEEE.

关键词： Generative adversarial networks

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：