检索结果-内蒙古大学图书馆

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yuxin Shi Zelei Liu Zhuan Shi Han Yu School of Computer Science and Engineering Nanyang Technological University (NTU) Singapore Alibaba-NTU Singapore Joint Research Institute NTU Singapore Alibaba Group Hangzhou China School of Computer Science and Technology University of Science and Technology of China China

Federated learning (FL) has enabled multiple data owners (a.k.a. FL clients) to train machine learning models collaboratively without revealing private data. Since the FL server can only engage a limited number of clients in each training round, FL client selection has become an important research problem. Existing approaches generally focus on either enhancing FL model performance or enhancing the fair treatment of FL clients. The problem of balancing performance and fairness considerations when selecting FL clients remains open. To address this problem, we propose the Fairness-aware Federated Client Selection (FairFedCS) approach. Based on Lyapunov optimization, it dynamically adjusts FL clients’ selection probabilities by jointly considering their reputations, times of participation in FL tasks and contributions to the resulting model performance. By not using threshold-based reputation filtering, it provides FL clients with opportunities to redeem their reputations after a perceived poor performance, thereby further enhancing fair client treatment. Extensive experiments based on real-world multimedia datasets show that FairFedCS achieves 19.6% higher fairness and 0.73% higher test accuracy on average than the best-performing state-of-the-art approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Novel Simulation Of Ultrasonic Attenuation In Fourier Transform Analog Computing

Novel Simulation Of Ultrasonic Attenuation In Fourier Transf...

引用

IEEE Symposium (IUS) Ultrasonics

作者： Xing Haw Marvin Tan Daniel Ssu-Han Chen Viet Phuong Bui Zaifeng Yang Zibo Juan Amit Lal Ching Eng Png Kevin Tshun Chuan Chai Institute of High Performance Computing (IHPC) Agency for Science Technology and Research (A*STAR) Singapore Institute of Microelectronics (IME) Agency for Science Technology and Research (A*STAR) Singapore School of Electrical and Computer Engineering Cornell University Ithaca New York USA

Ultrasonic Fourier Transform analog computing uses acoustic waves propagating across fused silica and an acoustic lens to compute the Fourier Transform. We demonstrate a method to incorporate not only the attenuation of ultrasonic waves in the fused silica medium, but also the transmittance of the acoustic meta-lens into our 3D hybrid simulation integrating both finite element analysis and Fresnel diffraction. Our realistic simulation predicts the effect of acoustic attenuation on the voltage at the receiver pixel array, which guides electrical specifications for the low-noise amplifier at the RX CMOS circuit, to maximize the readout signal-to-noise ratio.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-Class Classification of Alzheimer’s Disease Using Frontal Cortex Non-invasive fNIRS 8th

Multi-Class Classification of Alzheimer’s Disease Using Fro...

引用

8th International Conference on the Development of Biomedical engineering, BME8 2020

作者： Ho, Thi Kieu Khanh Kim, Minhee Garg, Harish Kim, Byeong C. Lee, Jang Jae Choi, Kyu Yeong Kim, Jae Gwan Lee, Kun Ho Song, Jong-In Gwak, Jeonghwan School of Electrical Engineering and Computer Science Gwangju Institute of Science and Technology Gwangju61005 Korea Republic of Department of Biomedical Science and Engineering Institute of Science and Technology Gwangju61005 Korea Republic of School of Mathematics Thapar Institute of Engineering and Technology Deemed University Patiala Punjab147004 India Department of Neurology Chonnam National University Medical School Gwangju61469 Korea Republic of Cohort Research Center Chosun University Gwangju61452 Korea Republic of Department of Biomedical Science Chosun University Gwangju61452 Korea Republic of Aging Neuroscience Research Group Korea Brain Research Institute Daegu41062 Korea Republic of Department of Software Korea National University of Transportation Chungju27469 Korea Republic of

ISBN: (纸本)9783030755058

Early and accurate diagnosis of Alzheimer’s disease (AD) is especially important for neurodegenerative disorders allowing patients, who exhibit different patterns of severity and progression risks, to take prevention and treatments before brain damages are shaped. Functional Near-Infrared Spectroscopy (fNIRS), as a clinical test, can be employed in an ecological setting to support AD diagnosis at early stages. In this study, we aimed to comprehensively study the hemodynamic response patterns among four subject groups from 140 participants by visualizing the 4-class distributions based on t-SNE visualization techniques and showing the fNIRS topographic mapping to have a pictorial representation on the surface of the prefrontal cortex region. We demonstrated that the changes in hemodynamic concentrations of oxygenated hemoglobin (HbO) and deoxygenated hemoglobin (Hb) from healthy controls to three stages of AD did exist during four stages of our experimental protocols. Results also revealed that various machine learning techniques were capable of both analyzing AD patterns and its related features and classifying multiple pathophysiologic mechanisms with the highest accuracies of 74.39 ± 4.7% and 84.91 ± 4.01% corresponding to raw and SMOTE-based features, respectively. These findings demonstrate the feasibility of fNIRS-based approaches to investigate the stages of AD progression. © 2022, Springer Nature Switzerland AG.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Study on ESS maximum capacity calculation and operation algorithm based on load pattern of substations in urban railway

引用

Transactions of the Korean institute of Electrical Engineers 2021年第9期70卷 1405-1412页

作者： Yun, Chi-Myeong Cho, Gyu-Jung Kim, Hyungchul Kim, Chul-Hwan Jung, Hosung Smart Electrical & Signaling Division Korea Railroad Research Institute Korea Republic of Dept. of Transportation Engineering Korea University of Science and Technology Korea Republic of Dept. of Electrical and Computer Engineering Sungkyunkwan University Korea Republic of

In this paper, we introduce the method of reducing only the morning peak of the ESS and the method of calculating the maximum ESS capacity according to the method of reducing the entire day by using the characteristic that the load of the urban railway substation shows a different load pattern depending on weekdays, weekends, and holidays. Furthermore, an operation method suitable for urban railroad is introduced using the operation algorithm for each of the five points of time of the ESS according to the load pattern. To verify the introduced maximum capacity calculation method and ESS operation algorithm, power analysis program, PSCAD/EMTDC was used. Copyright © The Korean institute of Electrical Engineers.

关键词： Cost reduction

来源：评论

学校读者我要写书评

暂无评论

Identity-Based Authentication Technique for IoT Devices

Identity-Based Authentication Technique for IoT Devices

引用

2022 IEEE International Conference on Consumer Electronics, ICCE 2022

作者： Gupta, Brij B. Gaurav, Akshat Chui, Kwok Tai Hsu, Ching-Hsien National Institute of Technology Haryana Kurukshetra India Ronin Institute MontclairNJ07043 United States Hong Kong Hong Kong Asia University Department of Computer Science and Information Engineering Taiwan Department of Computer Science and Information Engineering National Chung Cheng University Taiwan Department of Medical Research China Medical University Hospital China Medical University Taiwan

ISBN: (纸本)9781665441544

The Internet of Things (IoT) is a broad term used to describe many types of linked equipment that are both intelligent and interconnected through a network. These Internet of Things devices have become an essential part of our everyday lives. These devices, however, are still in the development stage. Because of their low computing capacity, they are susceptible to various cyberattacks like distributed denial of service (DDoS) attacks and denial of service (DoS) attacks. They disrupt the normal functioning of IoT devices and expose sensitive data;therefore, identifying and mitigating cyber-attacks on IoT devices is a critical area of study. In this regard, we proposed an IoT device-specific unique identity-based authentication method in this pa-per. Our proposed approach employs lightweight authentication procedures that use the unique IDs of IoT devices to provide identity - based encryption. © 2022 IEEE.

关键词： Denial-of-service attack

来源：评论

学校读者我要写书评

暂无评论

Counting on AR: EEG responses to incongruent information with real-world context

引用

computers in Biology and Medicine 2025年 185卷 109483-109483页

作者： Wimmer, Michael Pepicelli, Alex Volmer, Ben ElSayed, Neven Cunningham, Andrew Thomas, Bruce H. Müller-Putz, Gernot R. Veas, Eduardo E. Know Center Research GmbH Graz Austria Institute of Neural Engineering Graz University of Technology Graz Austria Wearable Computer Lab University of South Australia AdelaideSA Australia BioTechMed Graz Austria Institute of Interactive Systems and Data Science Graz University of Technology Graz Austria

Augmented Reality (AR) technologies enhance the real world by integrating contextual digital information about physical entities. However, inconsistencies between physical reality and digital augmentations, which may arise from errors in the visualized information or the user's mental context, can considerably impact user experience. This work characterizes the brain dynamics associated with processing incongruent information within an AR environment. To study these effects, we designed an interactive paradigm featuring the manipulation of a Rubik's cube serving as a physical referent. Congruent and incongruent information regarding the cube's current status was presented via symbolic (digits) and non-symbolic (graphs) stimuli, thus examining the impact of different means of data representation. The analysis of electroencephalographic signals from 19 participants revealed the presence of centro-parietal N400 and P600 components following the processing of incongruent information, with significantly increased latencies for non-symbolic stimuli. Additionally, we explored the feasibility of exploiting incongruency effects for brain-computer interfaces. Hence, we implemented decoders using linear discriminant analysis, support vector machines, and EEGNet, achieving comparable performances with all methods. Therefore, this work contributes to the design of adaptive AR systems by demonstrating that above-chance detection of incongruent information based on physiological signals is feasible. The successful decoding of incongruency-induced modulations can inform systems about the current mental state of users without making it explicit, aiming for more coherent and contextually appropriate AR interactions. © 2024

关键词： Interfaces (computer)

来源：评论

学校读者我要写书评

暂无评论

Development of Business Intelligence Framework for Open Government Data Portal Usage Analysis: A Case Study of Thailand 13

Development of Business Intelligence Framework for Open Gove...

引用

13th International Conference Knowledge and Systems engineering, KSE 2021

作者： Sripramong, Sahaporn Anutariya, Chutiporn Buranarach, Marut Tumsangthong, Patipat Wutthitasarn, Theerawat School of Engineering and Technology Asian Institute of Technology Ict Department Thailand National Electronics and Computer Technology Center Data Science and Analytics Research Group Thailand

ISBN: (纸本)9781665499750

The usage of Open Government Data (OGD) can enable the government transparency for better governance, increase citizen collaboration, and promote innovation through public service improvement. OGD initiatives involve different stakeholders and complex publishing guidelines. In general, governments initiate OGD in their countries and provide the government-run portals to support the provision and consumption process of OGD. Insufficient usage of OGD and limited provision by the government is a great challenge to OGD development. Monitoring the operation and constantly analyzing the usage can be beneficial for OGD policymakers to gain insight into usage, to plan, and to enact the law to support the OGD initiative. This study proposes a Business Intelligence (BI) framework to analyze OGD portal datasets and its usage. The data from Thailand's OGD (ThOGD) portal was derived to validate our framework. The work focuses on designing and implementing the BI framework. We demonstrated the features of the prototyped BI system in supporting the analysis through various data visualization. © 2021 IEEE.

关键词： Open Data

来源：评论

学校读者我要写书评

暂无评论

Two-photon polymerization lithography for imaging optics

引用

International Journal of Extreme Manufacturing 2024年第4期6卷 21-60页

作者： Hao Wang Cheng-Feng Pan Chi Li Kishan S Menghrajani Markus A Schmidt Aoling Li Fu Fan Yu Zhou Wang Zhang Hongtao Wang Parvathi Nair Suseela Nair John You En Chan Tomohiro Mori Yueqiang Hu Guangwei Hu Stefan A Maier Haoran Ren Huigao Duan Joel K W Yang College of Mechanical and Vehicle Engineering Hunan UniversityChangsha 410082People's Republic of China Engineering Product Development Singapore University of Technology and DesignSingapore 487372Singapore Greater Bay Area Institute for Innovation Hunan UniversityGuangzhou 511300People's Republic of China Department of Electrical and Computer Engineering National University of Singapore4 Engineering Drive 3Singapore 117576Singapore School of Physics and Astronomy Faculty of ScienceMonash UniversityMelbourneVictoria 3800Australia Leibniz Institute of Photonic Technology 07745 JenaGermany Abbe Center of Photonics and Faculty of Physics FSU Jena07745 JenaGermany Otto Schott Institute of Material Research FSU Jena07745 JenaGermany Institute of Materials Research and Engineering A*STAR(Agency for Science Technology and Research)Singapore 138634Singapore Industrial Technology Center of Wakayama Prefecture Wakayama 6496261Japan School of Electrical and Electronic Engineering Nanyang Technological UniversitySingapore639798Singapore Department of Physics Imperial College LondonLondon SW72AZUnited Kingdom

Optical imaging systems have greatly extended human visual capabilities,enabling the observation and understanding of diverse *** technologies span a broad spectrum of wavelengths from x-ray to radio frequencies and impact research activities and our daily *** glass lenses are fabricated through a series of complex processes,while polymers offer versatility and ease of ***,modern applications often require complex lens assemblies,driving the need for miniaturization and advanced designs with micro-and nanoscale features to surpass the capabilities of traditional fabrication ***-dimensional(3D)printing,or additive manufacturing,presents a solution to these challenges with benefits of rapid prototyping,customized geometries,and efficient production,particularly suited for miniaturized optical imaging *** 3D printing methods have demonstrated advantages over traditional counterparts,yet challenges remain in achieving nanoscale ***-photon polymerization lithography(TPL),a nanoscale 3D printing technique,enables the fabrication of intricate structures beyond the optical diffraction limit via the nonlinear process of two-photon absorption within liquid *** offers unprecedented abilities,***-free fabrication,micro-and nanoscale capabilities,and rapid prototyping of almost arbitrary complex 3D *** this review,we emphasize the importance of the criteria for optical performance evaluation of imaging devices,discuss material properties relevant to TPL,fabrication techniques,and highlight the application of TPL in optical *** the first panoramic review on this topic,it will equip researchers with foundational knowledge and recent advancements of TPL for imaging optics,promoting a deeper understanding of the *** leveraging on its high-resolution capability,extensive material range,and true 3D processing,alongside advances in materials,fabrication,and design,we en

关键词： two-photon polymerization lithography 3D printing additive manufacturing imaging optics and nanophotonics

来源：评论

学校读者我要写书评

暂无评论

The Intersection of computer engineering and Intellectual Property Law

The Intersection of Computer Engineering and Intellectual Pr...

引用

International Conference on Computing and Networking technology (ICCNT)

作者： Shweta Bansal Sachin Sharma Sipra Sagar Shamim Ahmad Rahul Mishra Arvind Kumar Pandey Department of Computer Science & Engineering School of Engineering & Technology K. R. Mangalam University Gurugram Haryana INDIA School of Engineering and Computer Dev Bhoomi Uttarakhand University Uttarakhand Department of Applied Sciences Invertis University Bareilly Uttar Pradesh Centre for Interdisciplinary Research in Business and Technology Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Department of Computer Science and Information Technology ARKA JAIN University Jamshedpur Jharkahnd India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

laptop engineering and intellectual belongings regulation are beautiful fields, however their intersection has grow to be increasingly more extensive in current years. With technology advancing speedy, computer engineering has end up important in all industries, even as highbrow assets law has turn out to be critical in protecting the rights of creators and innovators. computer engineering involves the layout, improvement, and implementation of pc hardware and software program application systems. The era maintains to conform, computer engineers are constantly growing new merchandise and generation that push the bounds of innovation. however, with the ones improvements come demanding situations related to highbrow assets rights. As such, laptop engineers must have complete understanding of intellectual belongings regulation to shield their creations and navigate criminal problems, patent infringement, and alternate mystery robbery. however, highbrow assets regulation encompasses a set of criminal policies and rules that guard ideas, creations, and improvements from unauthorized use or duplication.

关键词： Technological innovation Patents Portable computers Law Navigation Intellectual property Regulation Software computer security Protection

来源：评论

学校读者我要写书评

暂无评论

A Survey on Deep Active Learning: Recent Advances and New Frontiers

arXiv

引用

arXiv 2024年

作者： Li, Dongyuan Wang, Zhen Chen, Yankai Jiang, Renhe Ding, Weiping Okumura, Manabu The Institute of Innovative Research School of Information and Communication Engineering Tokyo Institute of Technology Tokyo152-8550 Japan The School of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong The Center for Spatial Information Science The University of Tokyo Tokyo Japan The School of Information Science and Technology Nantong University Nantong226019 China

Active learning seeks to achieve strong performance with fewer training samples. It does this by iteratively asking an oracle to label new selected samples in a human-in-the-loop manner. This technique has gained increasing popularity due to its broad applicability, yet its survey papers, especially for deep learning-based active learning (DAL), remain scarce. Therefore, we conduct an advanced and comprehensive survey on DAL. We first introduce reviewed paper collection and filtering. Second, we formally define the DAL task and summarize the most influential baselines and widely used datasets. Third, we systematically provide a taxonomy of DAL methods from five perspectives, including annotation types, query strategies, deep model architectures, learning paradigms, and training processes, and objectively analyze their strengths and weaknesses. Then, we comprehensively summarize main applications of DAL in Natural Language Processing (NLP), computer Vision (CV), and Data Mining (DM), etc. Finally, we discuss challenges and perspectives after a detailed analysis of current studies. This work aims to serve as a useful and quick guide for researchers in overcoming difficulties in DAL. We hope that this survey will spur further progress in this burgeoning field. Copyright © 2024, The Authors. All rights reserved.

关键词： Active 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：