检索结果-内蒙古大学图书馆

Dynamic Distributed Model Compression for Efficient Decentralized Federated Learning and Incentive Provisioning in Edge computing Networks

引用

IEEE Transactions on Mobile computing 2025年第7期24卷 6293-6314页

作者： Asheralieva, Alia Niyato, Dusit Wei, Xuetao Southern University of Science and Technology Department of Computer Science and Engineering 1088 Xueyuan Avenue Shenzhen China Nanyang Technological University College of Computing and Data Science 50 Nanyang Avenue Singapore639798 Singapore

We study decentralized federated learning (DFL) in edge computing networks where edge nodes (ENs) collaboratively train their artificial intelligence (AI) models in a serverless manner without sharing local data. We consider the following critical DFL challenges: i) scarce bandwidth resources of ENs;ii) dynamic, heterogeneous edge environment;iii) incentive provisioning and complex tradeoffs between the DFL performance and training costs. To resolve these challenges, we develop a new model compression method where ENs utilize dynamic, non-identical compression rates to improve the communication efficiency of DFL under time-varying, heterogeneous resource constraints. We show that our method can be formulated as a graphical Markov potential game where ENs act as players deciding on their compression factors and the number of data samples used for model updates. Each EN is incentivized to participate in DFL through rewards based on the EN's contribution to training. We prove that our game has a dominant pure-strategy Nash equilibrium (NE) maximizing its potential function and propose a dynamic distributed compression algorithm in which each EN can find its dominant strategy independently. We show that this algorithm converges to the Pareto-optimal NE, representing the most efficient solution of our game enhancing the DFL performance with minimal costs. © 2002-2012 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

An Innovation of Energy Harvesting for Small Scale Robotics in Automation Industry 2

An Innovation of Energy Harvesting for Small Scale Robotics ...

引用

2nd IEEE International Conference on Distributed computing and Electrical Circuits and Electronics, ICDCECE 2023

作者： Mehrotra, Tushar Shetty, Sahana Teerthanker Mahaveer University College of Computing Science & It Department of Computing Science & It Moradabad India Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350347456

Robotics is a rapidly emerging technology in the automation industry, and small-scale robotics is becoming increasingly prevalent in automation applications. Small-scale robotics can be used to automate a variety of manufacturing processes, such as assembly, welding, and painting. Small-scale robotics can be used to improve efficiency and reduce labor costs, allowing companies to produce products faster and more reliably with fewer resources. Small-scale robots are typically designed with a smaller size and weight than traditional industrial robots, making them suitable for applications with limited space and weight requirements. Small-scale robots are capable of performing a wide range of tasks, including pick-and- place operations, vision-guided navigation, logistics, and even complex manipulation tasks. Small-scale robots can provide a number of benefits to automation operations. For example, they can reduce labor costs by automating manual tasks. Small-scale robots are also capable of performing highly accurate and repeatable tasks, which can improve the quality of products. Additionally, small-scale robots can be used to increase throughput and reduce cycle times, enabling companies to produce more products in less time. © 2023 IEEE.

关键词： Wages

来源：评论

学校读者我要写书评

暂无评论

Secure Channel Estimation Using Norm Estimation Model for 5G Next Generation Wireless Networks

引用

Computers, Materials & Continua 2025年第1期82卷 1151-1169页

作者： Khalil Ullah Song Jian Muhammad Naeem Ul Hassan Suliman Khan Mohammad Babar Arshad Ahmad Shafiq Ahmad Faculty of Information Engineering and Automation Kunming University of Science and TechnologyKunming650500China Department of Computer Science Abbottabad University of Science and TechnologyHavelianAbbottabad22500Pakistan Department of Computing and Electronics Engineering Middle East CollegeMuscat124Oman Department of CS&IT Pak-Austria Fachhochschule Institute of Applied Sciences and Technology MangHaripur22621Pakistan Industrial Engineering Department College of EngineeringKing Saud UniversityRiyadh11421Saudi Arabia

The emergence of next generation networks(NextG),including 5G and beyond,is reshaping the technological landscape of cellular and mobile *** networks are sufficiently scaled to interconnect billions of users and *** in academia and industry are focusing on technological advancements to achieve highspeed transmission,cell planning,and latency reduction to facilitate emerging applications such as virtual reality,the metaverse,smart cities,smart health,and autonomous *** continuously improves its network functionality to support these *** input multiple output(MIMO)technology offers spectral efficiency,dependability,and overall performance in *** article proposes a secure channel estimation technique in MIMO topology using a norm-estimation model to provide comprehensive insights into protecting NextG network components against adversarial *** technique aims to create long-lasting and secure NextG networks using this extended *** viability of MIMO applications and modern AI-driven methodologies to combat cybersecurity threats are explored in this ***,the proposed model demonstrates high performance in terms of reliability and accuracy,with a 20%reduction in the MalOut-RealOut-Diff metric compared to existing state-of-the-art techniques.

关键词： Next generation networks massive mimo communication network artificial intelligence 5G adversarial attacks channel estimation information security

来源：评论

学校读者我要写书评

暂无评论

Enhanced Energy Optimization of Structured Random Matrix Model in Industrial Automation 2

Enhanced Energy Optimization of Structured Random Matrix Mod...

引用

2nd IEEE International Conference on Distributed computing and Electrical Circuits and Electronics, ICDCECE 2023

作者： Bishnoi, Amit Kumar Vivek, V. Teerthanker Mahaveer University College of Computing Science & It Department of Computing Science & It Moradabad India Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350347456

The Structured Random Matrix (SRM) model is an increasingly popular approach to industrial automation. This model is based on the idea that the control systems of industrial machines are "structured"in a certain way, with certain properties that can be predicted and used to model the behavior of the system. SRM incorporates the principles of random matrix theory in order to provide an efficient, reliable, and realistic model for industrial automation. The SRM model works by taking a large set of variables, such as the type of machine, the speed of the machine, the number of required parts, and the number of different components to be used in the system. These variables are then used to generate a random matrix, which can then be analyzed to identify patterns and correlations between the different variables. This allows engineers to develop more accurate models of the system, as well as to identify potential problems and solutions. In addition to providing a more accurate model, the SRM model also allows engineers to simplify the design process by reducing the number of variables used in the system. This simplification means that fewer parts are needed in the system, which reduces the cost and complexity of the system. Furthermore, by reducing the complexity of the system, engineers can reduce the amount of time spent on maintenance and repairs, which saves money and increases efficiency. © 2023 IEEE.

关键词： Automation

来源：评论

学校读者我要写书评

暂无评论

YOLOCSP-PEST for Crops Pest Localization and Classification

引用

Computers, Materials & Continua 2025年第2期82卷 2373-2388页

作者： Farooq Ali Huma Qayyum Kashif Saleem Iftikhar Ahmad Muhammad Javed Iqbal Department of Software Engineering University of Engineering and TechnologyTaxila47050Pakistan Department of Computer Science&Engineering College of Applied Studies&Community ServiceKing Saud UniversityRiyadh11362Saudi Arabia Department of Information Technology Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Computer Science University of Engineering and TechnologyTaxila47050Pakistan

Preservation of the crops depends on early and accurate detection of pests on crops as they cause several diseases decreasing crop production and quality. Several deep-learning techniques have been applied to overcome the issue of pest detection on crops. We have developed the YOLOCSP-PEST model for Pest localization and classification. With the Cross Stage Partial Network (CSPNET) backbone, the proposed model is a modified version of You Only Look Once Version 7 (YOLOv7) that is intended primarily for pest localization and classification. Our proposed model gives exceptionally good results under conditions that are very challenging for any other comparable models especially conditions where we have issues with the luminance and the orientation of the images. It helps farmers working out on their crops in distant areas to determine any infestation quickly and accurately on their crops which helps in the quality and quantity of the production yield. The model has been trained and tested on 2 datasets namely the IP102 data set and a local crop data set on both of which it has shown exceptional results. It gave us a mean average precision (mAP) of 88.40% along with a precision of 85.55% and a recall of 84.25% on the IP102 dataset meanwhile giving a mAP of 97.18% on the local data set along with a recall of 94.88% and a precision of 97.50%. These findings demonstrate that the proposed model is very effective in detecting real-life scenarios and can help in the production of crops improving the yield quality and quantity at the same time.

关键词： Deep learning classification of pests YOLOCSP-PEST pest detection

来源：评论

学校读者我要写书评

暂无评论

An Smart Analysis of Energy Efficiency Issues in Industrial Automation 2

An Smart Analysis of Energy Efficiency Issues in Industrial ...

引用

2nd IEEE International Conference on Distributed computing and Electrical Circuits and Electronics, ICDCECE 2023

作者： Singhal, Priyank Mahesh, T.R. Teerthanker Mahaveer University College of Computing Science & It Department of Computing Science & It Moradabad India Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350347456

Industrial automation has become increasingly important in recent years. It has allowed for increased efficiency, productivity and safety in the workplace, as well as improved quality control of products. However, with the increased use of automation, comes the need to be mindful of energy efficiency issues. Energy use in industrial automation is primarily driven by the use of electric motors, pumps and other devices. These devices consume a large amount of electricity, especially when they are running continuously or at high speeds. This can result in significant energy losses and increased costs. Additionally, when the motors are operating at different speeds, they can draw more power than they need and this can also cause energy losses. To reduce energy losses, it is important to ensure that the motors and pumps are properly sized for the application and that they are running at the correct speed. Additionally, it is important to take into account the efficiency of the motors and pumps. For example, variable speed drives can introduce energy savings in certain applications. Additionally, energy-efficient motors and pumps can reduce energy losses significantly. © 2023 IEEE.

关键词： Automation

来源：评论

学校读者我要写书评

暂无评论

The Smart Application Development in Real Time Parallel Applications with Industrial Automation 2

The Smart Application Development in Real Time Parallel Appl...

引用

2nd IEEE International Conference on Distributed computing and Electrical Circuits and Electronics, ICDCECE 2023

作者： Khan, Gulista Zabeeulla, Zabeeulla Teerthanker Mahaveer University College of Computing Science & It Department of Computing Science & It Moradabad India Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350347456

Real-time parallel applications with industrial automation are applications that are designed to run in parallel, in order to accomplish a task in a shorter amount of time. These applications are used in industrial environments to control machines and other processes in order to maximize efficiency and minimize waste. Real-time parallel applications allow machines and processes to be managed simultaneously. This means that instead of needing to wait for one process to finish before starting the next, multiple processes can be run at the same time. This increases the speed at which tasks can be completed, allowing for greater efficiency and productivity. Real-time parallel applications can be used to automate processes and machines. This means that instead of needing to manually manage and monitor a machine, the software can handle all of the work. This can help to reduce errors and improve the overall quality of the product being produced. © 2023 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Cognition2Vocation: meta-learning via ConvNets and continuous transformers

引用

Neural computing and Applications 2024年第21期36卷 12935-12950页

作者： Kamran, Sara Hosseini, Saeid Esmailzadeh, Sayna Kangavari, Mohammad Reza Hua, Wen School of Computer Engineering Iran University of Science and Technology Tehran Iran Faculty of Computing and Information Technology Sohar University Sohar Oman Department of Computing The Hong Kong Polytechnic University Hong Kong

Estimating the suitability of individuals for a vocation via leveraging the knowledge within cognitive factors comes with numerous applications: employment resourcing, occupation counseling, and workload management. Accordingly, the enterprises aim to hire the most suitable person from a massive array of similar applicants, maximizing performance and minimizing the gap between strategic indicators and predefined targets. While cognitive factors signify the best-suited person from similarly skilled workers, inferring pertinent latent cues from noisy and growing social network contents is time-intensive. To tackle the challenges involved, we propose a framework that, on the one hand, extends influential features based on the correlations between cognitive cues and, on the other hand, leverages a novel continuous transformer to mitigate the overlapping and approximation issues in discrete modeling. Rather than relying on discrete patterns that may evolve frequently, we use continuous elements that include not only numerous aggregating components but also sense minor irregular fluctuations. In a hybrid manner, we fuse multiple base models to transfer a higher representation to the meta-learning unit, agglomerating outputs from gradient boosters and the ConvNets. The experimental results show that our proposed framework can outperform trending vocation estimation methods by 1.36% in F1-Score and approximately 1% in accuracy. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Knowledge management

来源：评论

学校读者我要写书评

暂无评论

Unsupervised machine learning approach for tailoring educational content to individual student weaknesses

引用

High-Confidence computing 2024年第4期4卷 91-104页

作者： Shabab Intishar Rahman Shadman Ahmed Tasnim Akter Fariha Ammar Mohammad Muhammad Nayeem Mubasshirul Haque Sriram Chellappan Jannatun Noor Department of Computer Science and Engineering BRAC UniversityDhaka 1212Bangladesh Department of Computer Science and Engineering University of South FloridaFL 33620USA Computing for Sustainability and Social Good(C2SG)Research Group Department of Computer Science and EngineeringSchool of Data and SciencesBRAC UniversityDhaka 1212Bangladesh

By analyzing data gathered through Online Learning(OL)systems,data mining can be used to unearth hidden relationships between topics and trends in student ***,in this paper,we show how data mining techniques such as clustering and association rule algorithms can be used on historical data to develop a unique recommendation system *** our implementation,we utilize historical data to generate association rules specifically for student test marks below a threshold of 60%.By focusing on marks below this threshold,we aim to identify and establish associations based on the patterns of weakness observed in the past ***,we leverage K-means clustering to provide instructors with visual representations of the generated *** strategy aids instructors in better comprehending the information and associations produced by the *** clustering helps visualize and organize the data in a way that makes it easier for instructors to analyze and gain insights,enabling them to support the verification of the relationship between *** can be a useful tool to deliver better feedback to students as well as provide better insights to instructors when developing their *** paper further shows a prototype implementation of the above-mentioned concepts to gain opinions and insights about the usability and viability of the proposed system.

关键词： Recommendation system Clustering F-P growth Apriori Associative pattern E-learning sphere Online learning

来源：评论

学校读者我要写书评

暂无评论

Accurate threat hunting in industrial internet of things edge devices

引用

Digital Communications and Networks 2023年第5期9卷 1123-1130页

作者： Abbas Yazdinejad Behrouz Zolfaghari Ali Dehghantanha Hadis Karimipour Gautam Srivastava Reza M.Parizi Cyber Science Lab School of Computer ScienceUniversity of GuelphOntarioCanada Department of Electrical and Software Engineering University of CalgaryAlbertaCanada Department of Mathematics and Computer Science Brandon UniversityBrandonCanada College of Computing and Software Engineering Kennesaw State UniversityGAUSA Research Center for Interneural Computing China Medical UniversityTaichungTaiwanChina Department of Computer Science and Mathematics Lebanese American UniversityBeirut1102Lebanon

Industrial Internet of Things(IIoT)systems depend on a growing number of edge devices such as sensors,controllers,and robots for data collection,transmission,storage,and *** kind of malicious or abnormal function by each of these devices can jeopardize the security of the entire ***,they can allow malicious software installed on end nodes to penetrate the *** paper presents a parallel ensemble model for threat hunting based on anomalies in the behavior of IIoT edge *** proposed model is flexible enough to use several state-of-the-art classifiers as the basic learner and efficiently classifies multi-class anomalies using the Multi-class AdaBoost and majority *** evaluations using a dataset consisting of multi-source normal records and multi-class anomalies demonstrate that our model outperforms existing approaches in terms of accuracy,F1 score,recall,and precision.

关键词： IIoT Threat hunting Edge devices Multi-class anomalies Ensemble methods

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：