检索结果-内蒙古大学图书馆

11th International Conference on Reliability, Infocom Technologies and Optimization, ICRITO 2024

作者： Kumar, Aman Singh, Soumyendra Mohan G, Bharathi Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering India Amrita School of Engineering Amrita Vishwa Vidyapeetham Department of Mathematics India

ISBN: (纸本)9798350350357

The research work explores advanced techniques in object detection frameworks, specifically focusing on Faster R-CNN and YOLOv8, to enhance the accuracy of military aircraft detection. Leveraging the multi-stage Faster R-CNN architecture, we investigate the impact of adjusting anchor ratios, systematically evaluating their influence on the model's ability to detect objects with diverse shapes. Departing from the conventional anchor-based approach, YOLOv8 introduces anchor-free detection, eliminating predefined anchors and increasing robustness to object scale variations. Our experimentation includes anchor ratio configurations and explores the innovative components of YOLOv8, such as the CSPDarknet53 backbone and the C2f module. It aims to contribute insights into optimizing military aircraft detection accuracy, catering to the dynamic and critical nature of aerial threats. By providing a comparative analysis of Faster R-CNN and YOLOv8, we shed light on their strengths and weaknesses, offering valuable considerations for deployment in military contexts. The paper's findings contribute to the continual advancement of computer vision applications in national security, emphasizing the importance of automated detection for efficient and timely threat identification. © 2024 IEEE.

关键词： National security

来源：评论

学校读者我要写书评

暂无评论

HoloStream: a GPU-powered high-speed user interface for holographic microscopy imaging

引用

Optics Express 2025年第7期33卷 15648-15660页

作者： Morales, Johan Obando-Vásquez, Sofia Doblas, Ana Trujillo, Carlos Applied Optics Group School of Applied Science and Engineering EAFIT University Medellin Colombia Optical Imaging Research Lab Electrical and Computer Engineering Department University of Massachusetts Dartmouth DartmouthMA United States

This paper presents HoloStream, a GPU-powered high-speed user interface designed for holographic microscopy imaging. The platform reconstructs quantitative phase images rapidly for off-axis digital holographic microscopy (DHM) systems operating in the telecentric regime. By optimizing critical computational procedures, the HoloStream app reconstructs phase maps of 1280 × 960 pixels up to 11 frames per second (FPS) in live visualization and 90 fps for pre-recorded holographic videos. This real-time phase compensation is performed by upgrading the semi-heuristic phase compensation (SHPC) algorithm through GPU acceleration via PyCUDA. The interface also offers a user-friendly experience with flexible control over acquisition modes, visualization formats, and 3D tracking functionalities. Experimental validation demonstrates the platform’s capability to achieve fast and accurate phase imaging for live microscopy applications. The HoloStream app advances DHM technology by combining high-speed processing with ease of use, making it suitable for a wide range of DHM imaging applications. © 2025 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement.

关键词： computer graphics equipment

来源：评论

学校读者我要写书评

暂无评论

A Multi-Modal Framework for Fake News Analysis for Detection to Deconstruction 2

A Multi-Modal Framework for Fake News Analysis for Detection...

引用

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Vadakkethil Somanathan Pillai, Sanjaikanth E Parveen, H. Summia School of Electrical Engineering and Computer Science University of North Dakota Grand Forks United States Sri Eshwar College of Engineering Department of Computer Science Engineering Coimbatore India

ISBN: (纸本)9798350371055

The research discusses a multimodal framework for analyzing and detecting fake news and understanding its impact on society. This framework employs diverse strategies, including linguistic analysis, social network monitoring, and visual assessment, to capture various aspects of fabricated information and its dissemination. The first component of the framework focuses on linguistic analysis, examining the language and textual content used in fake news articles to identify misleading information, biased language, and sensationalized headlines. The second component analyzes the role of social networks in spreading fake news, tracking its propagation through platforms like social media and identifying key actors and influencers involved in its dissemination. The third component involves visual assessment, examining the images and videos used in fake news to manipulate public perceptions and emotions, including the detection of doctored images and misleading illustrations. © 2024 IEEE.

关键词： Fake News Detection Machine Learning NLP

来源：评论

学校读者我要写书评

暂无评论

Enhancing Healthcare Record Privacy Through the Integration of Visual Cryptography and Diverse Image Encryption Techniques 9

Enhancing Healthcare Record Privacy Through the Integration ...

引用

9th International Conference on Communication and Electronics Systems, ICCES 2024

作者： Chinnasamy, P. Deepalakshmi, P. Sandeep, Dayina Ganesh, Addala Siva Krishna, Angalakurthi Jaya Priya, D. Divya School of Computing Kalasalingam Academy of Research and Education Department of Computer Science and Engineering Tamilnadu India Kalasalingam Academy of Research and Education Department of Computer Science and Engineering Krishnankoil Virudhunagar India Mlr Institute of Technology Department of Computer Science and Engineering Hyderabad India

ISBN: (纸本)9798350377972

The methodology of this research focuses on analyzing real-world breaches, such as the Star Health Insurance leak, and demonstrating how multi-layered encryption techniques could have mitigated the impact. By splitting sensitive healthcare information into multiple shares using visual cryptography, unauthorized access is prevented unless all shares are combined, adding an additional layer of security. Furthermore, image-based encryption adds another line of defense, ensuring that even if hackers gain access to data, it remains unusable without the correct decryption methods. Through the implementation of these techniques, we demonstrate a significant enhancement in the security of healthcare records. By combining diverse encryption methods, our approach not only strengthens the protection of personal health information but also prevents unauthorized data dissemination, as seen in the Star Health breach. The results indicate that our model is resilient to various cyber-attacks, reducing the likelihood of large-scale data leaks and improving the integrity of healthcare systems. © 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

Nuclei Pathology Classification using YoloV9

Nuclei Pathology Classification using YoloV9

引用

2024 International Conference on Artificial Intelligence and Emerging Technology, Global AI Summit 2024

作者： Singh, Deependra K. Anitha, G. Pattanaik, Balachandra Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Tamil Nadu Chennai601103 India School of Electrical and Computer Engineering Wollaga University P.O.BOX:395 Nekemte Ethiopia

ISBN: (纸本)9798350379716

Nuclei pathology is important for diagnosing various diseases and cancer. It is responsible for examining cellular structures found in tissue samples. Laboratories have the challenge of accurate nuclei classification in order to identify illnesses and support treatment. Here, we introduce a new strategy to identify four types of nuclei (,Other', 'Inflammatory', 'Epithelial' and 'Spindle-Shaped'), using YOLOv9 deep learning. The present approach provides an overall accuracy of 98.9% in classifying nuclei, with other metrics also ranked strongly. A high rate of consistency is guaranteed by the use of this model, meaning that the associated expertise is capable of increasing the diagnosis aid in pathology. Brought by the increase in precision, diagnosis in all other fields is also able to be increased more quickly. The utilization of YOLOv9 opens up a better approach to faster pipelines of better quality for the diagnosis of patients, where reliability and speed are the key to help guide proper funding to lived improvement outcomes. © 2024 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Distributed Page Table: Harnessing Physical Memory as an Unbounded Hashed Page Table 57

Distributed Page Table: Harnessing Physical Memory as an Unb...

引用

57th Annual IEEE/ACM International Symposium on Microarchitecture, MICRO 2024

作者： Kwon, Osang Lee, Yongho Park, Junhyeok Jang, Sungbin Tak, Byungchul Hong, Seokin Sungkyunkwan University Department of Electrical and Computer Engineering Korea Republic of School of Computer Science and Engineering Kyungpook National University Korea Republic of

ISBN: (纸本)9798350350579

Virtual memory systems rely on the page table, a crucial component that maps virtual addresses to physical addresses (i.e., address translation). While the Radix Page Table (RPT) has traditionally been used for this task, its limitations have become more apparent with the rise of memory-intensive applications. Recently, Hashed Page Tables (HPTs) have been explored as an alternative page table structure to offer faster address translation. However, the HPT introduces its own set of challenges particularly in resizing the page table and allocating contiguous physical memory space for storing the table. To tackle the fundamental problem of the existing HPT designs, this paper introduces Distributed Page Table (DPT), a novel approach that utilizes the physical memory as a huge hashed page table. DPT distributes Page Table Entries (PTEs) across the entire physical memory space, significantly reducing the hash collisions while avoiding the table resizing overheads. When distributing the PTEs across the physical memory, they can be mapped to memory locations already allocated to data pages. This new type of collision, referred to as address collision, may reduce the effectiveness of the DPT. This paper showcases that the DPT can effectively resolve the address collision with three simple yet efficient techniques: Strided Open Addressing (SOA), Collision-Aware Virtual Address Allocation (CVA) and Collided Page Displacement (CPD). Our experimental results demonstrate that DPT achieves average performance improvements of 12.6%, 11.6%, and 8.7% compared to traditional RPT, the latest large-coverage TLB design, and state-of-the-art HPTs, respectively. © 2024 IEEE.

关键词： Virtual addresses

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Cloud computing and the Gig Economy Pricing Strategies

Comparative Analysis of Cloud Computing and the Gig Economy ...

引用

2024 International Conference on Innovative computing, Intelligent Communication and Smart electrical Systems, ICSES 2024

作者： Jothish Kumar, M. Reddy, Gajulapalli Venkata Karthik Kumar Iyapparaja Nowritha, S. School of Computer Science Engineering and Information Systems Vit Vellore Department of Smart Computing Tamil Nadu Vellore India School of Computer Science Engineering and Information Systems Vit Vellore Tamil Nadu Vellore India School of Computer Science Engineering and Information Systems Vit University Department of Smart Computing Tamil Nadu Vellore India

ISBN: (纸本)9798331543617

Cloud computing services and gig economy platforms vary in flexibility, efficiency, and scalability due to their pricing schemes. Cloud computing services provide flexibility and cost control via pay-as-you-go, subscription, and freemium models. Like gig economy platforms, workers and customers pay for task completion, time-based contracts, and premium services. Assessing how successfully different pricing techniques fulfil varied demands, from short-term initiatives to long-term commitments, requires identifying their strengths and weaknesses. The goal is to evaluate these models' capacity to meet shifting demand, save money, and scale. The methodology also assesses cost predictability and company and consumer advantages of each pricing structure. The comparison seeks to improve resource allocation and financial planning by revealing how various pricing systems function in different circumstances. The research helps decision-makers use cloud services or gig economy platforms for different operational purposes by emphasizing their economic consequences. From datasets, simulated pricing model data was examined. The first example includes settings such as Hours Used (5-25), Pay-as-You-Go (10-50 USD), and Subscription-Based (30 USD). The second instance has Job Size (Resources) from 5 to 25, Freemium Model (USD) from 10 to 30, and Usage-Based Pricing (USD) from 10 to 50. © 2024 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

SACNN-IDS: A self-attention convolutional neural network for intrusion detection in industrial internet of things

引用

CAAI Transactions on Intelligence Technology 2024年第6期9卷 1398-1411页

作者： Mimonah Al Qathrady Safi Ullah Mohammed S.Alshehri Jawad Ahmad Sultan Almakdi Samar M.Alqhtani Muazzam A.Khan Baraq Ghaleb Department of Information Systems College of Computer Science and Information SystemsNajran UniversityNajranSaudi Arabia Department of Computer Science Quaid-i-Azam UniversityIslamabadPakistan Department of Computer Science College of Computer Science and Information SystemsNajran UniversityNajranSaudi Arabia School of Computing Engineering and the Built EnvironmentEdinburgh Napier UniversityEdinburghUK ICESCO Chair Big Data Analytics and Edge Computing Quaid-i-Azam UniversityIslamabadPakistan

Industrial Internet of Things(IIoT)is a pervasive network of interlinked smart devices that provide a variety of intelligent computing services in industrial *** IIoT nodes operate confidential data(such as medical,transportation,military,etc.)which are reachable targets for hostile intruders due to their openness and varied *** Detection Systems(IDS)based on Machine Learning(ML)and Deep Learning(DL)techniques have got significant ***,existing ML and DL-based IDS still face a number of obstacles that must be *** instance,the existing DL approaches necessitate a substantial quantity of data for effective performance,which is not feasible to run on low-power and low-memory *** and fewer data potentially lead to low performance on existing *** paper proposes a self-attention convolutional neural network(SACNN)architecture for the detection of malicious activity in IIoT networks and an appropriate feature extraction method to extract the most significant *** proposed architecture has a self-attention layer to calculate the input attention and convolutional neural network(CNN)layers to process the assigned attention features for *** performance evaluation of the proposed SACNN architecture has been done with the Edge-IIoTset and X-IIoTID *** datasets encompassed the behaviours of contemporary IIoT communication protocols,the operations of state-of-the-art devices,various attack types,and diverse attack scenarios.

关键词： convolutional neural network deep learning industrial internet of things intrusion detection self-attention

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Algorithms in Mobile Edge with Real-Time Abnormal Event Detection for 5G-IoT Devices

International Journal of Interactive Mobile Technologies

引用

International Journal of Interactive Mobile Technologies 2023年第17期17卷 59-71页

作者： Praveenchandar, J. Kumar, S. Vinoth Paul, A. Christopher Mukunthan, M.A. Maharajan, K. Department of Computer Science and Engineering Karunya Institute of Technology and Sciences Tamil Nadu Coimbatore India Department of Computer Science and Engineering School of Computing Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Tamil Nadu Avadi India Department of Information Technology Karpagam Institute of Technology Tamil Nadu Coimbatore India Department of Computer Science and Engineering School of Computing Kalasalingam Academy of Research and Education Tamil Nadu Krishnankoil India

IoT is becoming increasingly popular due to its quick expansion and variety of applications. In addition, 5G technology helps with communication and network connectivity. This work integrates C-RAN with IoT networks to provide an experimental 5G testbed. In a 5G IoT environment, this experience is utilized to enhance both perpendicular and flat localization (3D localization). DRCaG, an acronym for the proposed model, stands for a deep, complicated network with a gated layer on top. The performance of the proposed model has been demonstrated through extensive simulations in terms of learning reduction, accuracy, and matrix disorientation, with a variable signal-to-noise ratio (SNR) spanning from 20 dB to + 20 dB, which illustrates the superiority of DRCaG compared to others. An online, end-to-end solution based on deep learning techniques is presented in this study for the fast, precise, reliable, and automatic detection of diverse petty crime types. By detecting tiny crimes like hostility, bag snatching, and vandalism, the suggested system may not only identify unusual passenger behavior like vandalism and accidents but also improve passenger security. The solution performs admirably in a variety of use cases and environmental settings. © 2023 by the authors of this article. Published under CC-BY.

关键词： Crime

来源：评论

学校读者我要写书评

暂无评论

Reset-Free Reinforcement Learning via Multi-State Recovery and Failure Prevention for Autonomous Robots

引用

Tsinghua science and Technology 2024年第5期29卷 1481-1494页

作者： Xu Zhou Benlian Xu Zhengqiang Jiang Jun Li Brett Nener School of Mechanical Engineering Changshu Institute of TechnologyChangshu 215500China School of Automation Nanjing University of Science and TechnologyNanjing 210094China School of Electronic and Information Engineering Suzhou University of Science and TechnologySuzhou 215009China Faculty of Medicine and Health The University of SydneySydney 2006Australia Department of Electrical Electronic and Computer EngineeringThe University of Western AustraliaPerth 6009Australia

Reinforcement learning holds promise in enabling robotic tasks as it can learn optimal policies via trial and ***,the practical deployment of reinforcement learning usually requires human intervention to provide episodic resets when a failure *** manual resets are generally unavailable in autonomous robots,we propose a reset-free reinforcement learning algorithm based on multi-state recovery and failure prevention to avoid failure-induced *** multi-state recovery provides robots with the capability of recovering from failures by self-correcting its behavior in the problematic state and,more importantly,deciding which previous state is the best to return to for efficient *** failure prevention reduces potential failures by predicting and excluding possible unsafe actions in specific *** simulations and real-world experiments are used to validate our algorithm with the results showing a significant reduction in the number of resets and failures during the learning.

关键词： reinforcement learning manual reset multi-state recovery failure prediction

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：