检索结果-内蒙古大学图书馆

Editorial:Special Topic on Federated Learning for IoT and Edge Computing

ZTE Communications 2022年第3期20卷 1-2页

作者： PAN Yi CUI Laizhong CAI Zhipeng LI Wei Faculty of Computer Science and Control Engineering at Shenzhen Institute of Advanced Technology Chinese Academy of SciencesChina the Academy of the United Nations Sciences and Technology Organization Ukrainian Academy of Engineering Sciences American Institute for Medical and Biological Engineering Institute of Engineering Technology the College of Computer Science and Software Engineering at Shenzhen University China Department of Computer Science and the College of Business at Georgia State University USA the Center for Distributed and High Performance Computing School of Computer ScienceThe University of Sydney the Australia-China Joint Research Center on Energy Informatics and Demand Response Technologies

Recent years have witnessed the proliferation of Internet of Things(IoT),in which billions of devices are connected to the Internet,generating an overwhelming amount of *** is challenging and infeasible to transfer an... 详细信息

关键词： cloud generating data.

来源：评论

学校读者我要写书评

暂无评论

Classifying Functional Data from Orthogonal Projections – Model, Properties and Fast Implementation 21st

Classifying Functional Data from Orthogonal Projections – M...

引用

21st International Conference on Computational Science, ICCS 2021

作者： Skubalska-Rafajlowicz, Ewa Rafajlowicz, Ewaryst Department of Engineering Informatics Wroclaw University of Science and Technology Wyb. Wyspianskiego 27 Wroclaw50 370 Poland Department of Control Systems and Mechatronics Wroclaw University of Science and Technology Wyb. Wyspianskiego 27 Wroclaw50 370 Poland

ISBN: (纸本)9783030779665

We consider the problem of functional, random data classification from equidistant samples. Such data are frequently not easy for classification when one has a large number of observations that bear low information for classification. We consider this problem using tools from the functional analysis. Therefore, a mathematical model of such data is proposed and its correctness is verified. Then, it is shown that any finite number of descriptors, obtained by orthogonal projections on any differentiable basis of L2(0,T), can be consistently estimated within this model. Computational aspects of estimating descriptors, based on the fast implementation of the discrete cosine transform (DCT), are also investigated in conjunction with learning a classifier and using it on-line. Finally, the algorithm of learning descriptors and classifiers were tested on real-life random signals, namely, on accelerations, coming from large bucket-wheel excavators, that are transmitted to an operator’s cabin. The aim of these tests was also to select a classifier that is well suited for working with DCT-based descriptors. © 2021, Springer Nature Switzerland AG.

关键词： Discrete cosine transforms

来源：评论

学校读者我要写书评

暂无评论

A Numerical Study of Multiphase Flow Boiling Heat Transfer of Nanofluids in the Horizontal Metal Foam Tubes

SSRN

引用

SSRN 2023年

作者： Azizifar, Shahram Song, Mengjie Chao, Christopher Yu Hang Hosseini, Seyyed Hossein Pekař, Libor Faculty of Mechanical and Energy Engineering Shahid Beheshti University Tehran Iran Department of Energy and Power Engineering Beijing Institute of Technology Beijing China Department of Building Environment and Energy Engineering Department of Mechanical Engineering The Hong Kong Polytechnic University Hong Kong999077 Hong Kong Department of Chemical Engineering Ilam University Ilam69315-516 Iran Department of Automation and Control Engineering Faculty of Applied Informatics Tomas Bata University in Zlín Nad Stráněmi 4511 Zlín76005 Czech Republic

The study aims to numerically investigate the flow boiling of Al2O3/H2O and CuO/H2O nanofluids and water in pipes filled with copper metal foams. Four different values of porosity and three values of pore density have been used. To perform numerical simulation, the mixture model has been developed. Also, with the help of user-defined functions, the effects of nanoparticle deposition on the wettability of heating surfaces were considered. The thermal performance of metal foam pipes has been compared with each other by comparing the increase in heat transfer and pressure drop. Besides, the effect of metal foams with different porosities on the onset of nucleate boiling was evaluated. As a result, by reducing the porosity from 0.95 to 0.80, the heat transfer coefficient was increased by 59%, while the pressure drop increased by 28%. Finally, by comparing the increase in heat transfer and pressure drop, results show that the metal foam pipe with 80% porosity and 5 PPI has the best thermal performance. The results of this study are expected to be used for the optimization of advanced phase change cooling technologies. © 2023, The Authors. All rights reserved.

关键词： Pressure drop

来源：评论

学校读者我要写书评

暂无评论

IT Managers’ Perspective on Technical Debt Management

SSRN

引用

SSRN 2023年

作者： Wiese, Marion Borowa, Klara Universität Hamburg Department of Informatics Vogt-Kölln-Str. 30 Hamburg22527 Germany Warsaw University of Technology Institute of Control and Computation Engineering ul. Nowowiejska 15/19 Warsaw00-665 Poland

Context. Technical Debt (TD) is a term for software solutions that are beneficial in the short-term but impede future ***. Previous research on TD indicates various management-related causes. We analyze the perspective of IT managers on TD since they usually have a major influence on deadlines, the project’s budget, and setting up a TD management (TDM) ***. To determine the IT managers’ perspective, we obtained and analyzed data from 16 semi-structured interviews and a three-person focus group discussion. Results. We found that all IT managers understood the TD concept. They consider TDM to be an essential topic, though nearly none of them had set up a TDM process so far. We identified three major concerns the IT managers had regarding TDM: communicating about TD, establishing a TDM process, and dealing with vintage systems, i.e., old legacy systems We developed a model specifying causes and consequences visible to business stakeholders, causal chains, and vicious cycles. Conclusions. Our research identifies new research gaps and demonstrates to practitioners that investing in a TDM process may be beneficial. It provides the V4CTD model of Visibility, Cycles & Chains of Causes & Consequences of TD, extending the TD conceptual model and facilitating communication on TD with business stakeholders. © 2023, The Authors. All rights reserved.

关键词： Legacy systems

来源：评论

学校读者我要写书评

暂无评论

Neural network developed for obstacle avoidance of the four wheeled electric vehicle

Neural network developed for obstacle avoidance of the four ...

引用

IEEE International Conference on Electronics, Circuits and Systems (ICECS)

作者： Grazia Lo Sciuto Paweł Kowol Paweł Nowak Wacław Banás Salvo Coco Giacomo Capizzi Department of Mechatronics Silesian University of Technology Gliwice Poland Department of Electrical Electronics and Informatics Engineering University of Catania Catania Italy Department of Automatic Control and Robotic Silesian University of Technology Gliwice Poland Department of Mathematics Applications and Methods for Artificial Intelligence Faculty of Applied Mathematics Silesian University of Technology Gliwice Poland

Several solutions have been proposed for vehicle navigation in unknown environments to ensure safer driving by avoiding obstacles and collisions. In this work, an electric vehicle equipped with Mecanum 4 omnidirectional holonomic wheels, analog joystick to control driving movement, LiDAR sensors and Wi-Fi able to detect obstacles is investigated based on neural network approach. By experimental tests conducted to avoid collisions by detecting the presence of obstacles, the relation between the resistance distance and speed is described by the artificial neural network.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dual-View Selective Instance Segmentation Network for Unstained Live Adherent Cells in Differential Interference Contrast Images

arXiv

引用

arXiv 2023年

作者： Pan, Fei Wu, Yutong Cui, Kangning Chen, Shuxun Li, Yanfang Liu, Yaofang Shakoor, Adnan Zhao, Han Lu, Beijia Zhi, Shaohua Chan, Raymond Sun, Dong Hong Kong Centre for Cerebro-Cardiovascular Health Engineering Hong Kong Department of Mathematics City University of Hong Kong Hong Kong Department of Biomedical Engineering City University of Hong Kong Hong Kong Control and Instrumentation Department King Fahd University of Petroleum and Minerals Dhahran Saudi Arabia Department of Health Technology and Informatics the Hong Kong Polytechnic University Hong Kong

Despite recent advances in data-independent and deep-learning algorithms, unstained live adherent cell instance segmentation remains a long-standing challenge in cell image processing. Adherent cells’ inherent visual characteristics, such as low-contrast structures, fading edges, and irregular morphology, have made it difficult to distinguish from one another, even by human experts, let alone computational methods. In this study, we developed a novel deep-learning algorithm called dual-view selective instance segmentation network (DVSISN) for segmenting unstained adherent cells in differential interference contrast (DIC) images. First, we used a dual-view segmentation (DVS) method with pairs of original and rotated images to predict the bounding box and its corresponding mask for each cell instance. Second, we used a mask selection (MS) method to filter the cell instances predicted by the DVS to keep masks closest to the ground truth only. The developed algorithm was trained and validated on our dataset containing 520 images and 12198 cells. Experimental results demonstrate that our algorithm achieves an APsegm of 0.555, which remarkably overtakes a benchmark by a margin of 23.6%. This study’s success opens up a new possibility of using rotated images as input for better prediction in cell images. © 2023, CC BY.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

HEART: Achieving Timely Multi-Model Training for Vehicle-Edge-Cloud-Integrated Hierarchical Federated Learning

arXiv

引用

arXiv 2025年

作者： Yang, Xiaohong Liwang, Minghui Wang, Xianbin Cheng, Zhipeng Hosseinalipour, Seyyedali Dai, Huaiyu Jiao, Zhenzhen School of Informatics Xiamen University Fujian China Department of Control Science and Engineering The National Key Laboratory of Autonomous Intelligent Unmanned Systems Japan Frontiers Science Center for Intelligent Autonomous Systems Ministry of Education Tongji University Shanghai China Department of Electrical and Computer Engineering Western University ON Canada School of Future Science and Engineering Soochow University Suzhou China Department of Electrical Engineering University at Buffalo-SUNY BuffaloNY United States Department of Electrical and Computer Engineering NC State University RaleighNC United States iF-Labs Beijing Teleinfo Technology Company Ltd. CAICT Beijing China

The rapid growth of AI-enabled Internet of Vehicles (IoV) calls for efficient machine learning (ML) solutions that can handle high vehicular mobility and decentralized data. This has motivated the emergence of Hierarchical Federated Learning over vehicle-edge-cloud architectures (VEC-HFL). Nevertheless, one aspect which is underexplored in the literature on VEC-HFL is that vehicles often need to execute multiple ML tasks simultaneously, where this multi-model training environment introduces crucial challenges. First, improper aggregation rules can lead to model obsolescence and prolonged training times. Second, vehicular mobility may result in inefficient data utilization by preventing the vehicles from returning their models to the network edge. Third, achieving a balanced resource allocation across diverse tasks becomes of paramount importance as it majorly affects the effectiveness of collaborative training. We take one of the first steps towards addressing these challenges via proposing a framework for multi-model training in dynamic VEC-HFL with the goal of minimizing global training latency while ensuring balanced training across various tasks—a problem that turns out to be NP-hard. To facilitate timely model training, we introduce a hybrid synchronous-asynchronous aggregation rule. Building on this, we present a novel method called Hybrid Evolutionary And gReedy allocaTion (HEART). The framework operates in two stages: first, it achieves balanced task scheduling through a hybrid heuristic approach that combines improved Particle Swarm Optimization (PSO) and Genetic Algorithms (GA);second, it employs a low-complexity greedy algorithm to determine the training priority of assigned tasks on vehicles. Experiments on real-world datasets demonstrate the superiority of HEART over existing methods. © 2025, CC BY-NC-ND.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Routing on the Shortest Pairs of Disjoint Paths

Routing on the Shortest Pairs of Disjoint Paths

引用

IFIP Networking Conference

作者： Pé ter Babarczi Gá bor Ré tvá ri Lajos Ró nyai Janos Tapolcai Department of Telecommunications and Media Informatics Faculty of Electrical Engineering and Informatics Budapest University of Technology and Economics Budapest Hungary Department of Algebra Institute for Computer Science and Control Institute of Mathematics Budapest University of Technology and Economics E&#x00F6 tv&#x00F6 s Lorand Research Network Budapest Hungary

Recent trends point towards communication networks will be multi-path in nature to increase failure resilience, support load-balancing and provide alternate paths for congestion avoidance. We argue that the transition from single-path to multi-path routing should be as seamless as possible in order to lower the deployability barrier for network operators. Therefore, in this paper we are focusing on the problem of routing along the shortest pairs of disjoint paths between each source-destination pair over the currently deployed link-state routing architecture. We show that the union of disjoint path-pairs towards a given destination has a special structure, and we propose an efficient tag encoding scheme which requires only one extra forwarding table entry per router per destination. Our numerical evaluations demonstrate that in real-world topologies usually only 4 bit tags are sufficient in the packet headers to route on the disjoint path-pairs. Finally, we show that our tags automatically encode additional paths beyond the shortest pair of disjoint paths, including the shortest paths themselves, which enables incremental deployment of the proposed method.

关键词： Focusing Tagging Routing Data structures Market research Load management Encoding

来源：评论

学校读者我要写书评

暂无评论

Case Studies of Games by Self-Interested Agents with Totally Positive Externalities

引用

IFAC-PapersOnLine 2021年第9期54卷 131-136页

作者： Adrianto Ravi Ibrahim Tomohisa Hayakawa National Institute of Informatics 100-0003 Tokyo Japan Department of Systems and Control Engineering Tokyo Institute of Technology 152-8552 Tokyo Japan

Case studies of games by self-interested agents with totally positive externalities are provided. To that end, theoretical results on the class of games by self-interested agents with totally positive externalities are stated. Then, by focusing on four types of games, various properties of the class of games by self-interested agents with totally positive externalities are illustrated.

关键词： Multi-agent systems game theory linear systems self-interested agents positive externalities

来源：评论

学校读者我要写书评

暂无评论

Cooperative Secure Communication in UAV Assisted Networks with Dynamic Role Switching

Cooperative Secure Communication in UAV Assisted Networks wi...

引用

IEEE Globecom Workshops

作者： Qinyu Wang Ang Gao Yansu Hu Jiankang Zhang School of Electronics and Information Northwestern Polytechnical University Xi'an China Yangtze River Delta Research Institute of Northwest Polytechnic University Taicang China School of Electronic and Control Engineering Chang'an University China Department of Computing and Informatics Bournemouth University UK

This paper proposes a novel role switching scheme (RSS) to optimize the secure communication by the cooperation of multiple unmanned aerial vehicles (UAVs). Each UAV is enabled to switch its role during the flight, i.e., could be an aerial relay to serve ground users (GUs) or a friendly jammer to generate artificial noise (AN) to deteriorate the wiretapping of potential eavesdropper users (EUs). It's worthy to be noticed that the joint optimization for UAVs' trajectory and legitimate GUs' transmission power control with RSS is a non-convex mixed integer fractional programming problem. A multi-agent deep reinforcement learning (MADRL) combined successive convex approximate (SCA) algorithm is further designed to maximize the achievable secrecy energy efficiency (ASEE). Numerical results illustrate that compared with the role fixed scheme (RFS) and relaxation based SCA approaches, the proposed DRL-SCA algorithm endows UAVs the capacity to fly close enough to target users (both GUs and EUs) which brings a better achievable secrecy rate (ASR), less energy consumption and higher ASEE.

关键词：

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：