检索结果-内蒙古大学图书馆

Intelligent Digital Twin Communication Framework for Addressing Accuracy and Timeliness Tradeoff in Resource-Constrained Networks

引用

IEEE Transactions on Cognitive Communications and Networking 2025年第3期11卷 1954-1965页

作者： Cakir, Lal Verda Thomson, Craig J. Özdem, Mehmet Canberk, Berk Nguyen, Van-Linh Duong, Trung Q. Edinburgh Napier University School of Computing Engineering and Built Environment EdinburghEH10 5DT United Kingdom BTS Group Istanbul34400 Turkey Turk Telekom Ankara06090 Turkey National Chung Cheng University Department of Computer Science and Information Engineering Minxiong621301 Taiwan Memorial University of Newfoundland Faculty of Engineering and Applied Science St. John’sNLA1C 5S7 Canada Queen’s University Belfast School of Electronics Electrical Engineering and Computer Science BelfastBT7 1NN United Kingdom

The accuracy and timeliness tradeoff prevents Digital Twins (DTs) from realizing their full potential. High accuracy is crucial for decision-making, and timeliness is equally essential for responsiveness. Therefore, this tradeoff in DT communication must be addressed to achieve DT synchronization. Previous studies identified the issue but considered the problem as maximizing data transfer, which is infeasible due to resource constraints. To facilitate this, we quantify accuracy and timeliness as E and and define the problem as joint minimisation. We then introduce the Intelligent DT Communication (IDTC) Framework to solve the problem, which includes machine learning-based Predictive Synchronization (PS) and DT synchronization management (DTSYNC) protocol. Here, PS uses imputation and forecasting to generate future values, which are utilized to update DT at the projected time points. This mechanism of PS enables lowering E and of the communication. Subsequently, we utilize the DTSYNC to control synchronization and optimise the twining frequency ft. We evaluate the proposed framework using a public dataset and compare its performance with several state-of-the-art studies in a real-world scenario. Evaluation results indicate that IDTC outperforms the existing methods by 80% for E and 84% for while enabling ft adjustment, resulting in 3.8 times goodput improvement. © 2015 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

VANET-Sec: A Framework to Secure Vehicular Ad-Hoc Networks Using a Permissioned Blockchain

VANET-Sec: A Framework to Secure Vehicular Ad-Hoc Networks U...

引用

2023 International Symposium on Networks, computers and Communications, ISNCC 2023

作者： Kacem, Thabet School of Engineering and Applied Sciences Department of Computer Science and Information Technology University of the District of Columbia WashingtonDC20008 United States

ISBN: (纸本)9798350335590

In recent years, Vehicular Ad-hoc Networks (VANET) has revolutionized the intelligent vehicle systems thanks to the services that it offers such as traffic information, road transportation emergency services and road traffic warnings, which has the potential of increasing the safety and improving the driving experience. VANET operates by sharing information from vehicle-to-vehicle (V2V), vehicle-to-infrastructure (V2I) and vehicle-to-everything (V2X) using communication standards such as Dedicated Short Range Communication (DSRC). However, several security and privacy concerns threaten its operation as they pose serious threats to vehicles. In order to tackle this problem, classic security protocols would face serious challenges due to lack of scalability. Even emerging solutions that use blockchains face the challenge of having elaborate cryptographic key exchange scheme. In this paper, we propose a permissioned blockchain-based framework to secure VANETs by allowing only authenticated stakeholders to add or view blocks on the blockchain. Another key contribution of our approach is that we propose a key exchange in which key stakeholders interact by the means of a smart contract. We also discuss the resilience of our approach against common VANET attacks. Finally, we validate our findings with a performance evaluation of the transaction latency of the sent location updates by the vehicles in an urban mobility scenario, which shows potential success of our solution. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Meta-Learning-Driven QoS Estimation for Self-Optimizing 6G Networks in Stochastic α-η-μ Fading Channels with Multi-Layer Selection Combining and Cross-Layer Interference Adaptation 2

Meta-Learning-Driven QoS Estimation for Self-Optimizing 6G N...

引用

2nd International Conference on IT Innovations and Knowledge Discovery, ITIKD 2024

作者： Kaushik, Keshav Gaur, Priyanka Mujahid, Barga Mohammed Khan, Mudassir Mustafa, Elfatih Elmubarak Singh, Amrita Sharda School of Computer Science & Engineering Sharda University Greater Noida India India Applied College Khamish Mushaiyt Department of Computer Science King Khalid University Saudi Arabia College of Computer Science Applied College Tanumah King Khalid University Department of Computer Science Abha Saudi Arabia College of Computer Science and Information Technology University of Bisha Department of Computer Science and Artificial Intelligence Saudi Arabia Chandigarh Engineering College Department of Computer Science and Engineering Chandigarh Group of Colleges Mohali Punjab Jhanjeri India

ISBN: (纸本)9798350355468

The authors proposed to use a meta-learningbased approach for QoS optimization in future 6G networks that are self-optimizing sections, focusing on stochastic α - η - μ fading channels. The proposed model utilizes information learned in the past so that it can rapidly adapt to these changes as they arrive, providing much better area adaptation, energy efficiency and interference mitigation than traditional learning approaches. You push the best and QoS, network throughput, latency abased simulation results are provided under high mobility in addition to severe fading conditions. The metalearning model showed accelerated convergence, adaptive resource allocation and improved interference mitigation which naturally led to QoS improvement up to 80% as well energy efficiency increased up to 65-90%, network reliability were enhanced. This step helps build green and robust communication mechanisms in the next-generation networks. © 2025 IEEE.

关键词： 6G Fading Meta-Learning Optimization QoS

来源：评论

学校读者我要写书评

暂无评论

Integration of Metaverse Recordings in Multimedia Information Retrieval 24

Integration of Metaverse Recordings in Multimedia Informatio...

引用

13th International Conference on Software and computer Applications, ICSCA 2024

作者： Steinert, Patrick Wagenpfeil, Stefan Frommholz, Ingo Hemmje, Matthias L. University Of Hagen Faculty Of Mathematics And Computer Science Hagen Germany Pfh Private University Of Applied Sciences Faculty Of Business Computing And Software Engineering Göttingen Germany University Of Wolverhampton School Of Mathematics And Computer Science Wolverhampton United Kingdom

ISBN: (纸本)9798400708329

This paper addresses the challenges in integrating Metaverse Recordings in Multimedia Information Retrieval as a new type of multimedia. Specifically, we describe the characteristics of video content and explain the key differences of a metaverse to other videos. We present a specialized process to analyze and index Metaverse Recordings. We demonstrate that existing techniques can be used for metaverse-specific retrieval, but need content-specific adaptions. Furthermore, we evaluate a prototypical implementation based on the proposed methods with respect to the impact on the retrieval process. © 2024 Owner/Author.

关键词： Multimedia systems

来源：评论

学校读者我要写书评

暂无评论

Classifying Air Quality Using Machine Learning Models 14

Classifying Air Quality Using Machine Learning Models

引用

14th IEEE Annual Ubiquitous Computing, Electronics and Mobile Communication Conference, UEMCON 2023

作者： Abdelfattah, Eman Ashkenazi, Yuval Sacred Heart University School of Computer Science & Engineering FairfieldCT United States School of Theoretical & Applied Science Ramapo College of New Jersey MahwahNJ United States

ISBN: (纸本)9798350304138

This study presents the classification of air quality levels in India based on data that has been collected prior to and during the Covid-19 pandemic. The data was collected to identify the effects of shutting down the world for several months on the quality of air. This data could later be used to define the necessary precautions that need to be taken to decrease negative effects of humans on the quality of air and the environment. The machine learning models experimented in this research are Stochastic Gradient Descent, Random Forests, k-Nearest Neighbors, Decision Trees, and Extra Trees. We concluded that the Decision Trees, Extra Trees, and Random Forests have comparable results. They produce the most accurate values with respect to different performance metrics and they outperform the other models. © 2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

A Nature-Inspired AI Framework for Accurate Glaucoma Diagnosis

引用

computer Modeling in engineering & sciences 2025年第4期143卷 539-567页

作者： Jahanzaib Latif Ahsan Wajahat Alishba Tahir Anas Bilal Mohammed Zakariah Abeer Alnuaim School of Software Northwestern Polytechnical UniversityXi’an710072China Shifa College of Medicine Shifa Tameer-e-millat UniversityIslamabad44000Pakistan College of Information Science and Technology Hainan Normal UniversityHaikou571158China Department of Computer Science and Engineering College of Applied Studies and Community ServiceKing Saud UniversityRiyadh11495Saudi Arabia

Glaucoma,a leading cause of blindness,demands early detection for effective *** AI-based diagnostic systems are gaining traction,their performance is often limited by challenges such as varying image backgrounds,pixel intensity inconsistencies,and object size *** address these limitations,we introduce an innovative,nature-inspired machine learning framework combining feature excitation-based dense segmentation networks(FEDS-Net)and an enhanced gray wolf optimization-supported support vectormachine(IGWO-SVM).This dual-stage approach begins with FEDS-Net,which utilizes a fuzzy integral(FI)technique to accurately segment the optic cup(OC)and optic disk(OD)from retinal images,even in the presence of uncertainty and *** the second stage,the IGWO-SVM model optimizes the SVM classification process,leveraging a gray wolf-inspired optimization strategy to fine-tune the kernel function for superior *** testing on three benchmark glaucoma image databases DRIONS-DB,Drishti-GS,and Rim-One-r3 demonstrates the efficacy of our method,achieving classification accuracies of 97.65%,94.88%,and 93.2%,*** results surpass existing state-of-the-art techniques,offering a promising solution for reliable and early glaucoma detection.

关键词： Glaucoma fundus images machine learning nature-inspired algorithm segmentation classification

来源：评论

学校读者我要写书评

暂无评论

JET FORMATION FOLLOWING DROPLET IMPACT ON AN INCLINED MICROHOLED HYDROPHILIC SUBSTRATE

JET FORMATION FOLLOWING DROPLET IMPACT ON AN INCLINED MICROH...

引用

ASME 2024 International Mechanical engineering Congress and Exposition, IMECE 2024

作者： Nath, Tushar Shondhi, Sakib Sadat Tan, Hua Alam, Md Nur E. School of Engineering and Computer Science Washington State University VancouverWA98686 United States Department of Mechanical Engineering College of Engineering Computing and Applied Sciences Clemson University ClemsonSC29634 United States

ISBN: (纸本)9780791888667

Given its wide-ranging applications, the dynamics of liquid droplet impact on diverse surfaces has been extensively investigated. While much of the existing research focuses on droplet impacts on horizontal hydrophobic surfaces, it's worth noting that droplets often collide with inclined or moving surfaces in practical scenarios. Hence it is important to understand the physics related to such oblique impact of the droplet. Our present study focuses on the study of the oblique impacts. A microholed hydrophilic surface has been set at different inclination angles from 0o to 30o with an interval of 5o. Almost constant size droplets have been released through a micropipette tip using a syringe pump. The height of the release of the droplet was varied for every inclination angle to vary the impact velocity of the droplet. We focused on the normal impact velocity component and normal Weber number (WeN) in the study. We have found the time for maximum spread quite independent of the inclination angle for a certain normal Weber number (WeN). It is observed that the normalized maximum spreading dia. of the droplet remains almost constant for certain normal Weber number at different inclination angles and it follows a power law as βm ~ WeN0.27. Our power law model closely aligns with theoretical models discussed in the literature. The jet velocities at different inclinations have been found to vary linearly with the normal impact velocity and it has been found to increase at higher angles which can be described by the reduction in the effective area of the substrate hole at higher angles. The correlations between pinch-off time and maximum length of the jet before breakup have also been discussed. Copyright © 2024 by ASME.

关键词： Hydrophilicity

来源：评论

学校读者我要写书评

暂无评论

ANN-Based Modeling and Control of a Pick and Place Manipulator 1

引用

8th International Congress on Information and Communication Technology, ICICT 2023

作者： Mostafa, Mohamed Essam Mostafa, Aya Essam Ammar, Hossam Hassan Shalaby, Raafat School of Engineering and Applied Science NU Giza Egypt School of Information Technology and Computer Science NU Giza Egypt SESC Center School of EAS NU Giza Egypt Faculty of Electronic Engineering Menofia University Menouf Egypt

ISBN: (数字)9789819930913

ISBN: (纸本)9789819930906

Pick-and-place robots are used in the manufacturing industry. This paper will focus on one of the most used functionalities in the industry. In addition, it will focus on this functionality and how to achieve more precision with the least cost. The robot is used for packaging, picking, placing factory jobs, and inspection. This paper is focusing on the design of the linear pick-and-place robot. The target of this paper is to tackle the design, construction, control, and analysis of the linear pick-and-place robot. The main target of this paper is to find the best design and the most cost-effective way to develop it. It will be done by comparing several delta robots designs to find which one will be the most economical. It will be done via a survey. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Cost effectiveness

来源：评论

学校读者我要写书评

暂无评论

Autonomic IoT Pet Health Monitoring System

Autonomic IoT Pet Health Monitoring System

引用

2024 International Symposium on Networks, computers and Communications, ISNCC 2024

作者： Shultz, Michael Rouff, Christopher Tekeoglu, Ali Johns Hopkins University Whiting School of Engineering Computer Science Department United States Johns Hopkins University Applied Physics Laboratory Jhu Whiting School of Engineering United States Leidos Innovations Center Johns Hopkins University Whiting School of Engineering United States

ISBN: (纸本)9798350364910

Internet of Things (IoT) devices have seen an uptick in popularity in recent years for individual health tracking, allowing for a person to monitor their health in real time. Simultaneously, pet care devices have also become popular. These devices have become increasingly connected and automated to allow for easier care of pets. This includes allowing an owner to not have to worry about forgetting to feed or overfeeding their pet, or to monitor a pet's health condition. In this paper, we propose an approach for using the principles of self-health monitoring overlaid on existing IoT connected pet care devices to provide an autonomic system that can adjust itself to the needs of a pet as it detects changes in the pet's health. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Confidence Trigger Detection: Accelerating Real-Time Tracking-by-Detection Systems 5

Confidence Trigger Detection: Accelerating Real-Time Trackin...

引用

5th International Conference on Electronic Communication and Artificial Intelligence, ICECAI 2024

作者： Ding, Zhicheng Lai, Zhixin Li, Siyang Li, Panfeng Yang, Qikai Wong, Edward Fu Foundation School of Engineering and Applied Science Columbia University New York United States Cornell University Department of Computer Science Ithaca United States Lubin School of Business Pace University New York United States University of Michigan Department of Electrical and Computer Engineering Ann Arbor United States University of Illinois Urbana-Champaign Department of Computer Science Urbana United States Tandon School of Engineering New York University Brooklyn United States

ISBN: (纸本)9798350386943

Real-time object tracking necessitates a delicate balance between speed and accuracy, a challenge exacerbated by the computational demands of deep learning methods. In this paper, we introduce Confidence-Triggered Detection (CTD), a novel approach that strategically skips object detection for frames exhibiting high similarity, leveraging tracker confidence scores. CTD not only enhances tracking speed but also preserves accuracy, surpassing existing tracking algorithms. Through extensive evaluation across various tracker confidence thresholds, we identify an optimal trade-off between tracking speed and accuracy, providing crucial insights for parameter fine-tuning and enhancing CTD's practicality in real-world scenarios. Furthermore, our experiments across diverse detection models underscore the robustness and versatility of the CTD framework, demonstrating its potential to enable real-time tracking in resource-constrained environments. © 2024 IEEE.

关键词： Object detection

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：