检索结果-内蒙古大学图书馆

2024 International Conference on Communication, computer sciences and Engineering, IC3SE 2024

作者： Murshleen, Mohd. Prabhu, A. Jain, Garima Tula's Institute Department Of Computer Science And Engineering Dehradun India Department Of Computer Science And Information Technology Bangalore India Noida Institute Of Engineering And Technology Department Of Computer Science & Business System Uttar Pradesh Greater Noida India

ISBN: (纸本)9798350366846

Web search engines are used for retrieving information but still there exists ambiguity in their retrieval process. It is so because traditional search engines laid emphasis on matching of keywords rather than maintaining semantic relations among terms lack of ability to produce precise results, presence of ambiguous keywords and verifying needs of users are few hindrances that are acting as scenario for web search engines. The paper focuses on improving search quality of users by collecting user experiences through creating hierarchical user profile it leads to collaborative search engine that helps in reaching at particular decision then the collected user's data are uploaded to recommendation server which are than displayed a search engines like Google/Yahoo. © 2024 IEEE.

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

Advancements and Challenges in Federated Learning : A Survey

Advancements and Challenges in Federated Learning : A Survey

引用

2024 International Conference on Advances in computing Research on science Engineering and technology, ACROSET 2024

作者： Prajapat, Vivek Singh Rathore, Narendra Pal Sethi, Kamal Kumar Rajput, Shiv Shankar Acropolis Institute of Technology and Research Department of Computer Science and Engineering Indore India

ISBN: (纸本)9798350388800

Machine Learning (ML) has significantly impacted daily life by automating tasks and enhancing decision-making across diverse sectors such as healthcare, finance, and transportation. However, concerns regarding data privacy, particularly in sensitive domains like healthcare and finance, have impeded its widespread adoption. Federated Learning (FL), pioneered by Google in 2016, presents a promising solution by enabling devices to collaborate on model training without sharing raw data. In FL, each device retains its data locally, and only model updates are exchanged with a central server for aggregation. This decentralized approach preserves data privacy while still improving model performance through collaborative learning. FL has garnered interest across industries, with approximately 32% of companies intending to integrate it into their systems soon. Furthermore, investment in FL is projected to rise substantially from 107 million in 2020 to 538 million by 2025, as indicated by forecasts from KPMG. This paper provides an overview of FL, its applications across various sectors, current adoption trends, and future growth prospects, highlighting its significance in addressing data privacy concerns while advancing machine learning capabilities. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

ProctorXam - Online Exam Proctoring Tool 1

ProctorXam - Online Exam Proctoring Tool

引用

1st IEEE International Conference on Electronics, computing, Communication and Control technology, ICECCC 2024

作者： Ashwini, S. Bhuvan Kumar, M.S. Chandra Sai, D. Sathya, V. Atria Institute of Technology Dept. of Computer Science & Engineering Bangalore India

ISBN: (数字)9798350371802

ISBN: (纸本)9798350371802

Robust exam monitoring solutions are now essential in light of the most notable Covid-19 outbreak and the increasing inclination towards virtual learning. The automated method for supervising online exams that is suggested in this paper is intended to lessen the difficulties associated with exam cheating. With the assistance of our system's clever face detection algorithms, instructors may efficiently identify suspicious conduct by monitoring students' web activity and camera feed in real-time. Unlike earlier systems, ours provides improved accuracy and functionality, guaranteeing the authenticity of online tests. In light of the difficulties presented by the epidemic, this research attempts to offer a workable option for academic institutions and people wishing to administer fair and secure online exams. © 2024 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Improving Traffic Sign Recognition with the YOLOv9 Algorithm 2

Improving Traffic Sign Recognition with the YOLOv9 Algorithm

引用

2nd International Conference on Computational Intelligence, Communication technology and Networking, CICTN 2025

作者： Anand, Ketan Dwivedi, Shyam Shankar Department of Computer Science and Engineering Rameshwaram Institute of Technology & Management AKTU Lucknow India

ISBN: (纸本)9798331530389

Modern intelligent transportation systems and autonomous driving technologies are quite helpful in light of the population's increasing growth, and they work particularly well when used in conjunction with traffic sign monitoring. By giving drivers accurate and exact traffic signals, such as speed limits, warnings, and directional assistance, this makes transportation much safer. Autonomous vehicles must correctly understand these indicators in order to make wise driving judgments. Accurately identifying and classifying a wide variety of traffic signs in a range of environmental circumstances is a difficulty. A cutting-edge deep learning model created specifically for object recognition tasks is called YOLOv9 (You Only Look Once version 9).In addition to offering respectable speed and accuracy, YOLOv9 expands on the advantages of its predecessors by implementing cutting-edge strategies such as PGI and *** of these improvements, YOLOv9 is especially ideal for real-time applications like recognition of traffic signs, where more accuracy and quick and accurate object identification are essential. With an increased accuracy the results demonstrate the model's stability and dependability and show that it is appropriate for real-world uses in autonomous driving and traffic control. Subsequent investigations will concentrate on improving resilience in various situations, utilizing semi-supervised learning, creating more resource-efficient models, broadening the range of datasets, and combining traffic sign recognition with additional autonomous driving tasks. The development of dependable and effective traffic sign detection systems is furthered by this work. © 2025 IEEE.

关键词： Traffic signs

来源：评论

学校读者我要写书评

暂无评论

A Comparative Evaluation of Lightweight Cryptographic Algorithms for Secure Data Transmission in IoT Network 3

A Comparative Evaluation of Lightweight Cryptographic Algori...

引用

3rd International Conference on Artificial Intelligence For Internet of Things, AIIoT 2024

作者： Verma, Abhay Thokchom, Surmila National Institute of Technology Department of Computer Science and Engineering Meghalaya Shillong India

ISBN: (纸本)9798350372120

Internet of Things (IoT), in a blend with advanced computer vision techniques, models new challenges for end users in securing images and videos. Securing images becomes one of the crucial aspects in the enormous and growing domain of digital transfer. One of the well-known methods for preserving the privacy of photos on an unconstrained public medium is image encryption. IoT devices generally have constrained resources due to low computational potential, bounded memory, and limited power supply. This exhibits the demand for lightweight security schemes instead of traditional cryptographic algorithms to facilitate image security in an intelligent environment. This paper implemented three well-known lightweight encryption algorithms on the actual IoT, such as the Raspberry Pi 3 device, to capture and encrypt images and transmit the encrypted binary over the network. PRESENT, SIMON & XTEA lightweight algorithms are implemented on the Raspberry device. A comparison is made among those to find efficiency in terms of encryption time, PSNR, MSE, and SSIM over the live environment. On comparison over the number of factors, the SIMON algorithm was found to be the most efficient of the other two. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Trusted Traceable NFT for Certificates 5th

Trusted Traceable NFT for Certificates

引用

5th International Conference on Trends in Computational and Cognitive Engineering, TCCE 2023

作者： Dixit, Harsh Chaurasia, Brijesh Kumar Dixit, Manas Bhatia, Naman Department of Computer Science and Engineering Pranveer Singh Institute of Technology Kanpur India

ISBN: (纸本)9789819719228

This paper introduces a blockchain-based non-fungible token (NFT) for any type of certificate, such as patents, international and national conferences, poems, contents of social media, etc. These documents may be altered or modified, so by creating a NFT’s certificate, we can simply keep a record of the digital form. Blockchain and NFT certificates can be trusted and securely traceable without any alteration or modification. In this work, we analyzed the potential for using NFTs using both types of public and private blockchain. We also present the proposed framework and implementation details for secure, traceable certificates. The results show the NFT is a feasible solution for any kind of digital certificate. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

An EDGE based end-2-end system architecture for retail stores

引用

International Journal of Information technology (Singapore) 2024年 1-29页

作者： Sundaresan, Vijay Anand Chandrapragasam, Tharini Rajaganesh, Thivish Naran Vimal, Pranhav Vadivelu, Manjula B.S.A Crescent Institute of Science and Technology Vandalur India School of Electrical and Communication Sciences B.S.A Crescent Institute of Science and Technology Vandalur India New York University NY United States Vellore Institute of Technology Vellore India School of Computer Science and Engineering Vellore Institute of Technology Vellore India

Retailers need real-time insights to know customer behavior and preferences to enhance operations efficiency and administrative cost reduction. There is a need to interconnect various legacy devices within the retail store that work on different technologies/standards like MATTER, Thread, WiFi, and Zigbee. This paper focuses on EDGE-based system design as a private retail network encompassing EDGE sensor nodes, EDGE gateway, and EDGE cloud. The proposed EDGE-based approach provides a detailed software architecture outlining the design and implementation methodology, enabling retailers to deliver a superior shopping experience. The performance evaluation clearly highlights the essential role of EDGE-based designs in retail shops for leveraging the full potential of battery-powered sensor nodes in diverse applications. © The Author(s), under exclusive licence to Bharati Vidyapeeth's institute of computer Applications and Management 2024.

关键词： Connectivity EDGE cloud EDGE gateway EDGE sensor node Energy management Smart retail

来源：评论

学校读者我要写书评

暂无评论

Role of Artificial Intelligence for Noninvasive Height Measurement Applications: A Survey 7

Role of Artificial Intelligence for Noninvasive Height Measu...

引用

7th IEEE Pune Section International Conference, PuneCon 2024

作者： Ruchitha, Inaganti Dhavale, Sunita Defence Institute of Advanced Technology Department of Computer Science and Engineering Pune India

ISBN: (纸本)9798331527822

Height measurement is crucial across various domains including healthcare, ergonomics, security, and forensic analysis. Traditional methods, such as stadiometers, often require cooperation from the subject and can be intrusive, posing significant challenges especially with children, the elderly, or individuals with disabilities. This survey paper addresses the growing need for artificial intelligence (AI) based noninvasive, automated height measurement techniques that can effectively estimate height without physical interaction. In this paper, we examined different state of the art methodologies for height measurement application area, including AI, computer vision (CV), deep learning (DL), depth imaging, and 3D laser scanning. While 3D scanning and depth imaging methodologies provide precise measurements, but they require specialized equipments which leads to additional costs for implementation. Recently, DL and advanced CV models have shown great accuracy in height estimation. Promising solutions for uncooperative subjects can be found by utilizing facial recognition and anatomical traits, and incorporating biometric parameters which can improve prediction accuracy. Despite these advancements, challenges remain with methods requiring multiple images or additional equipment, underscoring the need for more practical and user-friendly solutions. This survey highlights the necessity for tailored approaches to address specific measurement challenges and proposes guidelines for future studies to improve efficiency of noninvasive height estimation technologies. © 2024 IEEE.

关键词： Laser applications

来源：评论

学校读者我要写书评

暂无评论

Nucleus Segmentation with Modified Attention Gate UNET using Sobel Edge detection 3

Nucleus Segmentation with Modified Attention Gate UNET using...

引用

3rd International Conference for Advancement in technology, ICONAT 2024

作者： Sravanthi, Jakkula Bhukya, Raju National Institute of Technology Computer Science and Engineering Telangana Warangal506004 India

ISBN: (纸本)9798350354171

Automated segmentation of nuclei in hematoxylin and eosin (H&E) stained histopathology images is crucial for precise cancer diagnosis and prognosis. These methods enable comprehensive analysis of numerous nuclei within H&E stained histopathology images, offering both qualitative and quantitative insights. However, accurately segmenting nuclei with variable sizes and ambiguous boundaries presents a significant challenge, impacting the reliability of the segmentation process. To tackle this challenge, our research introduces a novel approach integrating edge information extracted from input data into the UNET model, a widely used architecture for image segmentation tasks. By modifying the attention gate mechanism within the UNET model, we aim to prioritize edge features during segmentation. This enhancement is essential for improving the delineation of nuclei boundaries, especially in cases with unclear boundaries, thereby reducing segmentation errors and enhancing overall accuracy. In summary, our study presents an innovative methodology to enhance nuclei segmentation in H&E stained histopathology images. By leveraging edge information and refining the attention mechanism within the UNET model, we aim to address challenges associated with variable-sized nuclei and unclear boundaries, ultimately improving the accuracy of cancer diagnosis and prognosis. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Coalition-Based Web Server Load Balancing in Software Defined Network 6

Coalition-Based Web Server Load Balancing in Software Define...

引用

6th International Conference on Computational Intelligence and Networks, CINE 2024

作者： Budania, Vijay Tehariya, Sanjay Sharma, Suhana Singh, Atinder Pal Mina, Aman Ahmed, Mushtaq Malaviya National Institute of Technology Department of Computer Science and Engineering Jaipur India

ISBN: (纸本)9798331516796

Software Defined Network(SDN) is a paradigm, which defines new architecture for network management. In traditional networking, the network is managed by dedicated net neg working devices. These devices have tightly coupled control plane and data plane. And generally proprietary in nature. For load balancing, traditional networks use an expensive hardware device. But in the case of SDN, only a new load balancing application is needed to install at the controller. This application uses APIs provided by the controller to build logic for load balancing. Here this paper proposes a game theory-based load-balancing application. It uses concepts of the coalition from cooperative game theory to build the logic of load balancing. The coalition build is based on the hosts connected to a particular OpenFlow switch, i.e. close proximity. The performance of the proposed algorithm is evaluated and compared to a round-robin load balancing scheme under a Mininet emulated environment. Experimental evaluations in a Mininet-emulated environment demonstrate that the proposed method improves throughput by up to 19% compared to the round-robin method under peak loads. Additionally, the proposed method reduces average response time by up to 6%, while also minimizing network congestion and traffic, outperforming the round-robin scheme in overall performance. © 2024 IEEE.

关键词： Traffic congestion

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：