检索结果-内蒙古大学图书馆

58th Asilomar Conference on Signals, systems and Computers, ACSSC 2024

作者： Faiz, Mohammed Mujahid Ulla Zerguine, Azzedine Kale, Izzet Presidency University Department of Electrical and Computer Engineering Karnataka Bengaluru560064 India Interdisciplinary Research Center for Communication Systems and Sensing Kfupm Electrical Engineering Department Dhahran31261 Saudi Arabia Department of Computer Science and Engineering LondonW1W 6UW United Kingdom

ISBN: (纸本)9798350354058

Normally, the electrocardiogram (ECG) signal artifacts are removed in a particular sequence starting with baseline wander removal at the beginning. In this work, a methodology has been proposed using a novel algorithm called the Normalized Leaky Sign Regressor Least Mean Mixed Norm (NLSRLMMN) algorithm to remove multiple ECG artifacts such as baseline wander, motion artifacts, muscle artifacts, and power line interference randomly without following a particular sequence. Through rigorous simulations we have shown that if we remove multiple ECG artifacts randomly using our proposed approach then an improvement in signal to noise ratio and mean square error is observed as opposed to a conventional method that employs the Least Mean Square (LMS) algorithm in all the cascaded adaptive noise canceller stages. © 2024 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Sign Language Recognition using PCA and Hu-Moment Features 5

Sign Language Recognition using PCA and Hu-Moment Features

引用

5th International Conference on electrical, Communication and Computer engineering, ICECCE 2024

作者： Khan, Jamal Khan, Sikandar Saeed, Muhammad Ullah, Sami Iqbal, Naveed Sher, Madiha Qureshi, Khurram Karim University of Engineering and Technology Peshawar Department of Computer Systems Engineering Peshawar Pakistan King Fahd University of Petroleum and Minerals Department of Mechanical Engineering Dhahran Saudi Arabia King Fahd University of Petroleum and Minerals Department of Global Studies Dhahran Saudi Arabia Al Fayha College Faculty of Engineering and Technology Department of Electrical Engineering Al Jubail Saudi Arabia King Fahd University of Petroleum and Minerals Department of Electrical Engineering Dhahran Saudi Arabia

ISBN: (纸本)9798331529437

The deaf community commonly uses sign language for communication, a highly flexible way of conveying messages. Sign language involves a limited number of core concepts and assigned gestures. This paper aims to create a sign language system that will enhance communication within the deaf community. The focus is to implement a software model for sign language recognition using a classifier. The approach involves recognizing and analyzing gestures using principal component analysis features and Hu-Moment features. Several classifiers are utilized to measure accuracy and performance. © 2024 IEEE.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Developing a Micro-Grid modeling approach for Nasser Medical Complex energy demand in the Gaza Strip 8

Developing a Micro-Grid modeling approach for Nasser Medical...

引用

8th International engineering Conference on Renewable Energy and Sustainability, ieCRES 2023

作者： Abu-Taha, Jawdat Shaheen, Husam Islamic University of Gaza Electrical Engineering and Smart Systems Department Gaza Palestine Engineering and Maintenance Administration Ministry of Health Gaza Palestine

ISBN: (纸本)9798350300758

In Gaza Strip, power outages lasting several hours daily are very common. In addition, today's power systems are facing challenges of environmental protection, increasing global power demand, and high reliability requirements. Centralized plants are now being replaced by smaller, distributed plants to pave the way to green and intelligent energy systems. The microgrid concept can therefore be viewed as a group of distributed energy loads and resources that can operate as a single controllable system and encompass many renewable energy sources and energy storage systems. For the microgrid system to operate reliably, energy management of a large number of distributed energy resources is required. As a result, energy management is a critical component of microgrid operation for economic and sustainable development. In this paper, the primary goal is to look into the feasibility of installing a microgrid system for Nasser medical complex. A techno-economic analysis of the capex, savings, and financial benefit of numerous microgrid possibilities is used to justify the final design. Using the HOMER Pro tools, several scenarios and architectures were simulated and discussed in terms of their specific requirements, features, and drawbacks. The scenarios are based on different alternatives, such as replacing a plant (which consists of a diesel generator) with a solar photovoltaic (PV) system and a battery-backed energy storage system (BESS). The simulations show that Scenario 4 (Hybrid PV system with Li-Ion batteries) is the optimal configuration regarding the economic indicators. The results clearly demonstrate that an annual grid power cost of 1.70M $, fuel costs of 0.40 M $, and operating costs of 0.66M $, with an annualized savings of 0.36 M$. The hybrid approach proposed in this situation has a 48.5% IRR, a payback period of 2.06 years, and an LCOE of 181 $/MWh. © 2023 IEEE.

关键词： Electric loads

来源：评论

学校读者我要写书评

暂无评论

Fundamental Limits of Distributed Covariance Matrix Estimation Under Communication Constraints 41

Fundamental Limits of Distributed Covariance Matrix Estimati...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Rahmani, Mohammad Reza Yassaee, Mohammad Hossein Maddah-Ali, Mohammad Ali Aref, Mohammad Reza Department of Electrical Engineering Sharif University of Technology Tehran Iran Sharif Center for Information Systems and Data Science Sharif Institute for Convergence Science & Technology Tehran Iran Department of Electrical and Computer Engineering University of Minnesota Minneapolis United States

Estimating high-dimensional covariance matrices is crucial in various domains. This work considers a scenario where two collaborating agents access disjoint dimensions of m samples from a high-dimensional random vector, and they can only communicate a limited number of bits to a central server, which wants to accurately approximate the covariance matrix. We analyze the fundamental trade-off between communication cost, number of samples, and estimation accuracy. We prove a lower bound on the error achievable by any estimator, highlighting the impact of dimensions, number of samples, and communication budget. Furthermore, we present an algorithm that achieves this lower bound up to a logarithmic factor, demonstrating its near-optimality in practical settings. Copyright 2024 by the author(s)

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

A coherent approach-based fine-tuning of segment anything model plus watershed algorithm for instance segmentation of mitochondria in electron microscopy images

引用

IEEE Access 2025年 13卷 98088-98105页

作者： Faska, Zahra Khrissi, Lahbib Mountasser, Imadeddine Haddouch, Khalid Akkad, Nabil El Alshathri, Samah El-Shafai, Walid Sidi Mohamed Ben Abdellah University Laboratory of Engineering Systems and Applications ENSA Fez Morocco Princess Nourah Bint Abdulrahman University College of Computer and Information Sciences Department of Information Technology P.O. Box 84428 Riyadh11671 Saudi Arabia Computer Science Department Riyadh11586 Saudi Arabia Menoufia University Faculty of Electronic Engineering Department of Electronics and Electrical Communications Engineering Menouf32952 Egypt

Increasingly available ultrastructural data from a continuously growing diversity of experimental conditions are driving new opportunities for fruitful neuroscientific hypotheses tested in intracellular compartments such as the nanoscale roles of, e.g., the mitochondria. Reliable morphological statistics are based on achieving highly accurate semantic segmentations of EM images. The state-of-the-art deep CNNs can be somewhat brittle;they tend to provide coarse and high-frequency-oscillatory solutions with discontinuities and false positives even for simple mitochondria segmentation. Historically, the current state-of-the-art in medical image segmentation would involve some variant of the encoder-decoder architecture, such as the U-Net architecture. The SAM does not perform as well, since it has not been explicitly trained for the task and does not demonstrate user-interactive, over one billion annotations mostly for natural images. However, the SAM may be applied to segment anything, including medical image segmentation challenging new datasets. This work is aimed at the difficult task of implementing domain adaptation in mitochondria segmentation within EM images obtained from various tissues and species, using deep learning. We do a systematic study to assess SAM's ability to perform segmentation in medical images, measure its performance on volumetric EM datasets, and show that it is powerful at segmenting instances even under challenging imaging conditions. We provide a fine-tuning SAM which can be naturally trained by SAM at an exemplary scale, benefiting from a diverse and large dataset over one million image masks in 11 modalities. This model would be able to perform precise segmentation for a wide range of targets under various imaging conditions, at the level of performance of specialized U-Net models, or even better. A visual comparison is shown between our fine-tuning SAM model and U-Net, along with an examination of different watershed post-processing st

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Effect of Carbon Density at Grain Boundary on Delayed Fracture Properties of Martensitic Steels

引用

Zairyo/Journal of the Society of Materials Science, Japan 2024年第2期73卷 109-114页

作者： Ichiro, Fujimoto Tatsuya, Okayama Ryosuke, Matsumoto Honda R&D Co. Ltd Haga-machi Haga-gun Tochigi 321-3393 Japan Department of Mechanical and Electrical Systems Engineering Faculty of Engineering Kyoto University of Advanced Science Yamanouchi Gotanda-cho Ukyoku Kyoto615-8577 Japan

It is well known that carbon addition enhances the strength of steel, but it also increases the sensitivity to delayed fracture. The origin of increased sensitivity to delayed fracture at a higher carbon content is not clarified yet. In this report, high-strength steels with different carbon contents were fabricated, and their delayed fracture properties were firstly evaluated. As the amount of carbon in the material increased, the amount of carbon concentration at the grain boundaries and the dislocation density also increased, and the material became more sensitive to delayed fracture. Then, a grain boundary (GB) model was created based on the samples used in the experiments, and the hydrogen effect on the cohesive energy of GB was evaluated using first principles calculations. The cohesive energy without carbon atoms was 3.47 J/m2 in the presence of hydrogen, while it with one additional carbon atom was 3.70 J/m2. This result was inconsistent to the experiment. Therefore, based on the results of dislocation density measurements, we assumed that more vacancies are generated in materials with a higher carbon content. By adding vacancy at GB, the cohesive energy decreased to 1.79 J/m2, and showed the same tendency as in the experiment. This suggests that not only hydrogen and carbon, but also vacancies, are responsible for the decrease in delayed fracture resistance. ©2024 The Society of Materials Science, Japan.

关键词： Grain boundaries

来源：评论

学校读者我要写书评

暂无评论

Distributed Learning by Local Training ADMM 63

Distributed Learning by Local Training ADMM

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Ren, Xiaoxing Bastianello, Nicola Johansson, Karl H. Parisini, Thomas Kth Royal Institute of Technology 2School of Electrical Engineering and Computer Science and Digital Futures Stockholm Sweden Imperial College London Department of Electrical and Electronic Engineering London United Kingdom Aalborg University Department of Electronic Systems Denmark University of Trieste Department of Engineering and Architecture Trieste Italy

ISBN: (纸本)9798350316339

In this paper, we focus on distributed learning over peer-to-peer networks. In particular, we address the challenge of expensive communications (which arise when e.g. training neural networks), by proposing a novel local training algorithm, LTADMM. We extend the distributed ADMM enabling the agents to perform multiple local gradient steps per communication round (local training). We present a preliminary convergence analysis of the algorithm under a graph regularity assumption, and show how the use of local training does not compromise the accuracy of the learned model. We compare the algorithm with the state of the art for a classification task, and in different set-ups. The results are very promising showing a great performance of LT-ADMM, and paving the way for future important theoretical developments. © 2024 IEEE.

关键词： Peer to peer networks

来源：评论

学校读者我要写书评

暂无评论

Enhanced Reactive Power Transfer Capability and ZVS Range Analysis for a Single-Stage DAB based Electronic Transformer Using Bidirectional Switches

Enhanced Reactive Power Transfer Capability and ZVS Range An...

引用

2024 IEEE Energy Conversion Congress and Exposition, ECCE 2024

作者： Rawat, Shubham Narwal, Ramandeep Bhattacharya, Subhashish Baliga, B. Jayant Hopkins, Douglas C. North Carolina State University Freedm Systems Center Department of Electrical and Computer Engineering RaleighNC27695 United States

ISBN: (纸本)9798350376067

A single-stage single-phase dual active bridge (DAB) based solid-state transformer (SST) offers various advantages over its multi-stage counterparts, including higher efficiency and reliability due to fewer components and the absence of bulky electrolytic capacitors. However, the lack of a DC link limits its reactive power transfer capability from the supply to the load, a capability even conventional transformers possess. To address this, external compensation elements are required across the load terminals to meet the desired reactive power, diminishing its primary advantage. This paper introduces a technique for a single phase AC-AC DAB-based SST to enhance the transformer's reactive power transfer capacity. It also presents a detailed analysis of the zero voltage switching range of the converter bridges under various operating conditions while supplying reactive power. The proposed schemes and analysis are further validated by experimental results on a 120/164 Vrms and 450 VA hardware prototype, demonstrating a correlation with the experimental results and highlighting the practical benefits of the proposed scheme. © 2024 IEEE.

关键词： Zero voltage switching

来源：评论

学校读者我要写书评

暂无评论

Coordinated EMS for Stability Enhancement of NMGs During Disturbance and Fault Conditions 50

Coordinated EMS for Stability Enhancement of NMGs During Dis...

引用

50th Annual Conference of the IEEE Industrial Electronics Society, IECON 2024

作者： Hussein, Hossam M. Abdelrahman, Mahmoud S. Kharchouf, Ibtissam Rafin, S.M. Sajjad Hossain Mohammed, Osama A. Energy Systems Research Laboratory Department of Electrical and Computer Engineering Florida International University MiamiFL33174 United States

ISBN: (纸本)9781665464543

Power systems are evolving from centralized power grid structures to networks of intelligent microgrids (MGs) that can share power more independently. The interconnection between these MGs, forming the networked MGs (NMGs), will increase the power system’s stability and expand its capabilities. However, a critical concern that necessitates sophisticated management strategies for voltage stabilization across the microgrids is the optimal and effective power sharing between renewable resources and energy storage devices. Effective power sharing between AC and DC sides is critical, necessitating robust control mechanisms for interlink converters (ILC). This paper presents a coordinated energy management strategy for hybrid networked MGs (NMGs) to enhance stability during contingencies and fault instances. The proposed Energy Management System (EMS) operates in two distinct modes: grid-connected and islanded. The system takes specific actions to maintain stability depending on the current mode. In grid-connected mode, the grid supplies the load demand while one of the microgrids (MGs) serves as a backup to ensure system stability. Several scenarios were created using MATLAB/Simulink to test and validate the EMS. These scenarios included varying load demands, pulsed power loads, uncertainties in photovoltaic (PV) system generation, disconnection from the AC side, and fault conditions. The proposed EMS has proven its efficiency while maintaining the system stability within the standard limits and fulfilling the load demands. © 2024 IEEE.

关键词： Microgrids

来源：评论

学校读者我要写书评

暂无评论

Strengthening Active Learning with a Reinforcement Approach in engineering Education 65

Strengthening Active Learning with a Reinforcement Approach ...

引用

65th IEEE Annual International Scientific Conference on Power and electrical engineering of Riga Technical University, RTUCON 2024

作者： Vodovozov, Valery Raud, Zoja Petlenkov, Eduard Tallinn University of Technology Department of Electrical Power Engineering and Mechatronics Tallinn Estonia Tallinn University of Technology Department of Computer Systems Tallinn Estonia

ISBN: (纸本)9798350365771

Nowadays, the best methods of training specialists who are able to identify new challenges, make original decisions, and explore complex issues are associated with active learning. However, it is appears that the development of new values, proclaimed as the purpose of engineering education, is not so much the goal of the learners themselves as of the educators responsible for developing curricula and the academic environment. As for students, they perceive active learning as a variety of ways to achieve their own, narrower and more specific goals, namely the successful completion of the studied disciplines. In this context, the target of the current research is to propose and substantiate a reinforcement system aimed at attracting and supporting the interest of university students in active learning based on a set of updated methodological tools. The paper demonstrates how active learning is being transformed into reinforcement learning, and supports such an observation with examples from various educational activities, including lectures, quizzes, exercises, presentations, and laboratory works. It is expected that the proposed reinforcement approach will be in need of learners, faculty and industry in the near future ahead of the big challenges facing the global educational system. © 2024 IEEE.

关键词： Federated learning

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：