检索结果-内蒙古大学图书馆

2nd International Conference on Power, electrical, Electronics and Industrial Applications, PEEIACON 2024

作者： Kibria, Hafsa Binte Hossain, Md. Ali Rajshahi University of Engineering & Technology Department of Electrical & Computer Engineering Rajshahi6204 Bangladesh Rajshahi University of Engineering & Technology Department of Computer Science Engineering Rajshahi6204 Bangladesh

ISBN: (纸本)9798331517984

The emergence of COVID-19 has underscored the urgency of accurate medical diagnosis, particularly in the context of chest X-ray image classification for various lung conditions, including COVID-19, normal cases, viral pneumonia, and lung opacity. In light of the pandemic's impact, there is a pressing need to develop resource-efficient solutions for automated classification, specifically tailored for resource-constrained devices. This article addresses this need by proposing a Lightweight Parallel CNN (Convolutional Neural Network) architecture capable of effectively categorizing the aforementioned multi-class cases. Leveraging a comprehensive dataset of 21165 images, our model achieves a decent accuracy of 93.21% for four-class classification. Notably, the proposed architecture maintains efficiency with fewer than 783k parameters, demonstrating its potential for deployment on devices with limited computational resources. This research contributes to the advancement of accessible and accurate medical diagnostics, catering to the demand for streamlined and reliable solutions amidst challenging circumstances. © 2024 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Direct Edge-To-Edge Local-Learning-Assisted Model-Based Transfer Learning

引用

IEEE Internet of Things Journal 2024年第11期11卷 20223-20235页

作者： Huang, Zih-Syuan Lu, Ching-Hu Hwang, I-Shyan Hsinchu308 Taiwan National Taiwan University of Science and Technology Department of Electrical Engineering Taipei106 Taiwan Yuan-Ze University Department of Computer Science and Engineering Taoyuan320 Taiwan

With the gradual advancement of technology in the production of consumer goods, the Internet of Things (IoT) systems have experienced rapid development, resulting in a massive amount of data that can be processed using deep neural networks. However, annotating the data and training the models require significant manpower, time, and computational resources. Transfer learning can address this problem. Traditional systems rely on centralized servers for transfer learning. Although several studies have proposed distributed systems for direct edge-To-edge (e2e) instance-based and feature-based transfer learning, they neglect model-based transfer learning (MTL) within the same domain. This leads to lower learning efficiency, lower privacy protection, and higher transmission costs. Therefore, our study proposes direct e2e local-learning-Assisted MTL for a direct e2e many-To-many MTL scenario. The method can transfer model structures and weights between distributed devices without relying on powerful centralized servers. The effectiveness of the proposed approach is demonstrated by applying it to various scenarios. © 2014 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Light-Material Interactions Using Laser and Flash Sources for Energy Conversion and Storage Applications

引用

Nano-Micro Letters 2024年第12期16卷 468-514页

作者： Jung Hwan Park Srinivas Pattipaka Geon-Tae Hwang Minok Park Yu Mi Woo Young Bin Kim Han Eol Lee Chang Kyu Jeong Tiandong Zhang Yuho Min Kwi-Il Park Keon Jae Lee Jungho Ryu Department of Mechanical Engineering(Department of Aeronautics Mechanical and Electronic Convergence Engineering)Kumoh National Institute of Technology61Daehak-RoGumiGyeongbuk 39177Republic of Korea Department of Materials Science and Engineering Pukyong National University45Yongso-RoNam-GuBusan 48513Republic of Korea Energy Technologies Area Lawrence Berkeley National LaboratoryBerkeleyCA 94720USA Department of Materials Science and Engineering Korea Advanced Institute of Science and Technology(KAIST)291 Daehak-RoYuseong-GuDaejeon 34141Republic of Korea Division of Advanced Materials Engineering Jeonbuk National UniversityJeonju 54896JeonbukRepublic of Korea School of Electrical and Electronic Engineering Harbin University of Science and TechnologyHarbin 150080People’s Republic of China Key Laboratory of Engineering Dielectrics and Its Application Ministry of EducationHarbin University of Science and TechnologyHarbin 150080People’s Republic of China Department of Materials Science and Metallurgical Engineering Kyungpook National University80 Daehak-RoBuk-GuDaegu 41566Republic of Korea School of Materials Science and Engineering Yeungnam UniversityDaehak-RoGyeongsan-Si 38541Gyeongsangbuk-doRepublic of Korea

This review provides a comprehensive overview of the progress in light-material interactions(LMIs),focusing on lasers and flash lights for energy conversion and storage *** discuss intricate LMI parameters such as light sources,interaction time,and fluence to elucidate their importance in material *** addition,this study covers various light-induced photothermal and photochemical processes ranging from melting,crystallization,and ablation to doping and synthesis,which are essential for developing energy materials and ***,we present extensive energy conversion and storage applications demonstrated by LMI technologies,including energy harvesters,sensors,capacitors,and *** the several challenges associated with LMIs,such as complex mechanisms,and high-degrees of freedom,we believe that substantial contributions and potential for the commercialization of future energy systems can be achieved by advancing optical technologies through comprehensive academic research and multidisciplinary collaborations.

关键词： Light Light-material interaction Nanomaterials Energy conversion and storage devices

来源：评论

学校读者我要写书评

暂无评论

Backup subscription scheme for differential protection using IEC61850-9-2 sampled values

引用

Energy Informatics 2024年第1期7卷 1-19页

作者： Katoulaei, Mohammad Khalili Rahmani, Aamir Høidalen, Hans Kristian Oleinikova, Irina Mork, Bruce Department of energy systems Norwegian University of Science and Technology Trondheim Norway Department of electrical power system Michigan Technical University Michigan United States Department of Electrical Power Engineering Norwegian University of Science and Technology Trondheim Norway Department of Electrical and Computer Engineering Michigan Technological University HoughtonMI49931 United States

In IEC-61850-based digital substations, the protection IED’s performance is dependent on merging unit’s vendor implementation, communication networks, and measurement circuit’s health conditions. As the process bus Sampled Value(SV) enables the availability of all sensor data on a communication network, this paper proposes a Backup Subscription scheme (BSS) for a transformer differential protection (87T, PDIF) function. BSS utilizes sensor data in digital substations to achieve a flexible protection scheme using a dynamic subscription feature. Thus, in case of failure of one sensor, differential protection would be maintained. The paper presents the implementation and verification of a prototyped scheme using a Hardware-in-the-loop simulation test bed. The main result is that BSS integration into differential protection ensures its dependability and security. Moreover, delay compensation and seamless switching feature increases the availability of differential protection. © The Author(s) 2024.

关键词： Hardware-in-the-loop simulation

来源：评论

学校读者我要写书评

暂无评论

A Practical Zinc Metal Anode Coating Strategy Utilizing Bulk h-BN and Improved Hydrogen Redox Kinetics

引用

Energy & Environmental materials 2025年第2期8卷 59-67页

作者： Dong Il Kim Hee Bin Jeong Jungmoon Lim Hyeong Seop Jeong Min Kyeong Kim Sangyeon Pak Sanghyo Lee Geon-Hyoung An Sang-Soo Chee Jin Pyo Hong Seung Nam Cha John Hong Department of Physics Research Institute for Natural ScienceHanyang UniversitySeoul 04763South Korea School of Materials Science and Engineering Kookmin UniversitySeoul 02707South Korea Department of Physics Sungkyunkwan University(SKKU)SuwonGyeonggi-do 16419South Korea School of Electronic and Electrical Engineering Hongik UniversitySeoul 04066South Korea Materials Science and Engineering Kumoh National Institute of TechnologyGumiGyeongsangbuk-do 39177South Korea Department of Energy Engineering Gyeongsang National UniversityJinjuGyeongnam-do 52725Korea Nano Convergence Materials Center Korea Institute of Ceramic Engineering and Technology(KICET)Jinju 52851Korea Division of Nano-Scale Semiconductor Engineering Hanyang UniversitySeoul 04763South Korea

Achieving high-performance aqueous zinc-ion batteries requires addressing the challenges associated with the stability of zinc metal anodes,particularly the formation of inhomogeneous zinc dendrites during cycling and unstable surface *** study introduces a practical method for scattering untreated bulk hexagonal boron nitride(h-BN)particles onto the zinc anode *** cycling,stabilized zinc fills the interstices of scattered h-BN,resulting in a more favorable(002)***,zinc dendrite formation is effectively suppressed,leading to improved electrochemical *** zinc with scattered h-BN in a symmetric cell configuration maintains stability 10 times longer than the bare zinc symmetric cell,lasting 500 ***,in a full cell configuration withα-MnO_(2) cathode,increased H^(+)ion activity can effectively alter the major redox kinetics of cycling due to the presence of scattered h-BN on the zinc *** shift in H^(+)ion activity lowers the overall redox potential,resulting in a discharge capacity retention of 96.1%for 300 cycles at a charge/discharge rate of 0.5 Ag^(-1).This study highlights the crucial role of surface modification,and the innovative use of bulk h-BN provides a practical and effective solution for improving the performance and stability.

关键词： aqueous zincionbatteries H^(+)ion insertion hexagonalboronnitride scattering Znmetalanode

来源：评论

学校读者我要写书评

暂无评论

Multiplex Immunoassays Enabled by Pixelated High-Quality Factor Metasurfaces and Acoustic Bioprinting

Multiplex Immunoassays Enabled by Pixelated High-Quality Fac...

引用

CLEO: Fundamental science, CLEO:FS 2024 - Part of Conference on Lasers and Electro-Optics, CLEO 2024

作者： Abdollahramezani, Sajjad Safir, Fareeha Moradifar, Parivash Dagli, Sahil Dolia, Varun Hu, Jack Delgado, Hamish Carr Chang, Kai Khuri-Yakub, Butrus T. Dionne, Jennifer Department of Materials Science and Engineering Stanford University United States Department of Electrical Engineering Stanford University United States

ISBN: (纸本)9781957171395

We demonstrate a compact multiplex immunoassay platform by leveraging ultra-densely-pixelated high-quality factor metasurfaces, acoustic bioprinting of surface chemistry, and hyperspectral imaging for the rapid detection of multiple proteins with high sensitivity and specificity. © 2024 The Author(s) © Optica Publishing Group 2024.

关键词： Hyperspectral imaging

来源：评论

学校读者我要写书评

暂无评论

Exploratory Analysis of Zero-Shot Lunar Crater Detection using SAM for Chandrayaan-2 Images 3

Exploratory Analysis of Zero-Shot Lunar Crater Detection usi...

引用

3rd International Conference on Communication, Control, and Intelligent Systems, CCIS 2024

作者： Koranglekar, Kaustubh Prateek, K. Kumar, Shankar Biswas, Dheeraj Kumar Khanna, Nitin Department of Mechatronics Bhilai India Department of Electrical Engineering Bhilai India Department of Computer Science and Engineering Bhilai India

ISBN: (纸本)9798331528201

This paper explores the application of a zero-shot lunar crater detection method based on the Segment Anything Model (SAM) for high-resolution Digital Terrain Model (DTM) images from ISRO's Chandrayaan-II mission. A pre-trained transformer-based instance segmentation model, SAM, is used to segment and identify lunar craters without requiring training data. The proposed method is capable of detecting craters in varying crater sizes and shapes, highlighting its potential for generalizable planetary feature detection. This work investigates the applicability of general-purpose deep learning models in planetary exploration and offers insights for efficient lunar surface analysis. © 2024 IEEE.

关键词： Lunar surface analysis

来源：评论

学校读者我要写书评

暂无评论

An Efficient Federated Learning Framework for IoT Intrusion Detection 100

An Efficient Federated Learning Framework for IoT Intrusion ...

引用

100th IEEE Vehicular Technology Conference, VTC 2024-Fall

作者： Chen, Yushen Fang, Fang Wang, Boyu Zhang, Lan Western University Department of Computer Science London Canada Western University Department of Electrical and Computer Engineering London Canada Clemson University Department of Electrical and Computer Engineering Clemson United States

ISBN: (纸本)9798331517786

The exponential growth of the Internet of Things (IoT) ecosystems has raised significant cybersecurity concerns. Deep learning (DL)-based methods have shown promising performance in detecting potential cyber threats in IoT networks. However, as these methods often involve data centralization, they can pose serious data privacy issues for IoT users and increase the communication burden of local networks. Federated learning (FL), as a distributed learning paradigm, enables privacy-preserving training of IoT intrusion detection models by requiring only model updates from IoT devices. However, the resource-constrained nature of IoT devices can significantly decrease FL training efficiencies, such as increased training latency and delayed convergence speed. Moreover, the data heterogeneous issues of IoT devices can also impact the accuracy and robustness of the trained model. To address these challenges, we propose an efficient FL framework, FedKD-Prox, based on federated proximal (FedProx) and knowledge distillation (KD). To improve the prediction accuracy within a limited time budget, the proposed framework aims to efficiently exploit the computation capability of the IoT trainers, reduce the communication overhead of FL, and alleviate the impact of heterogeneous data issues. The simulation results show that FedKD-Prox achieves higher accuracy and improves the robustness of the trained intrusion detection model. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Advancing Sustainable IoT Appliance Load Monitoring Through Edge-Enabled Federated Transfer Learning

Advancing Sustainable IoT Appliance Load Monitoring Through ...

引用

2024 International Conference on Green Energy, Computing and Sustainable Technology, GECOST 2024

作者： Natarajan, Yuvaraj Wadhwa, Gitanjali Sri Preethaa, K.R. Sundaram, Karthic Rama Abirami, K. Kpr Institute of Engineering and Technology Computer Science and Engineering Coimbatore641407 India Dresden01062 Germany Curtin University Faculty of Engineering and Science Department of Electrical and Computer Engineering Malaysia

ISBN: (纸本)9798350357905

Non-intrusive Appliance Load Monitoring (NALM) is essential for efficient electricity consumption tracking in households, promoting eco-friendly practices, and cost reduction. Privacy concerns in real-world NALM implementations can be addressed using federated learning. However, challenges persist, such as limited training data, edge model customization, and resource constraints. We introduce a practical federated learning framework for NALM, leveraging cloud-based model compression, collaborative data collection, and personalized edge and multi-task learning models through unsupervised transfer learning. Our advanced load monitoring model offers precise energy disaggregation through real-world experimentation, making it a leading solution for non-intrusive appliance load monitoring on edge devices. It maintains excellent learning performance and user privacy. Future research should aim to enhance federated learning efficiency and tackle remaining challenges in practical NALM implementations © 2024 IEEE.

关键词： Cost reduction

来源：评论

学校读者我要写书评

暂无评论

Improved Monitoring of the Water-Cooled Upper Shell of an Electric Arc Furnace Using Fiber-Optic Sensors

Improved Monitoring of the Water-Cooled Upper Shell of an El...

引用

AISTech 2024 Iron and Steel Technology Conference

作者： Mekala, Yeshwanth Reddy Saha, Rony Kumer Inalegwu, Ogbole C. Roman, Muhammad Mumtaz, Farhan Gerald, Rex E. Smith, Jeffrey D. Huang, Jie O’Malley, Ronald J. Department of Materials Science and Engineering Missouri University of Science and Technology RollaMO65409 United States Department of Electrical and Computer Engineering Missouri University of Science and Technology RollaMO65409 United States

ISBN: (纸本)9780930767259

Modern Electric Arc Furnaces (EAF) employ ultra-high-power electrical input to minimize the scrap melting time. Increasing the operating voltage increases arc length and enhances the active power, but radiation energy losses also increase if the arc is exposed to the furnace, resulting in a drop in thermal efficiency and causing hot spots in the furnace. The present work introduces a novel approach using fiber optic sensors to create a real-time, spatially distributed thermal map of the EAF's water-cooled upper shell, which can be helpful in detecting operational anomalies and improving EAF energy efficiency. Lab-scale testing using fiber-optic sensors on a spray-cooled steel plate achieved a remarkable spatial resolution of 2.3mm and a 1Hz data acquisition rate, paving the way for industrial-scale implementation. These sensors, providing reliable spatial temperature measurements, offer early detection of sidewall hot spots and precise adjustments to voltage and burner positioning based on granular data from the scrap melting stages. This study strongly advocates the use of fiber optic sensors in EAFs, would enhance efficiency and safety in steelmaking. © 2024 by the Association for Iron & Steel Technology.

关键词： Fiber optic sensors

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：