检索结果-内蒙古大学图书馆

IEEE Conference on Wireless Communications and networking

作者： Wei Jiang Hans D. Schotten Intelligent Networking Research Group German Research Center for Artificial Intelligence (DFKI) Germany Department of Electrical and Computer Engineering Technische Universität (TU) Kaiserslautern Germany

Intelligent reflecting surface (IRS) is envisioned to become a key technology for the upcoming six-generation (6G) wireless system due to its potential of reaping high performance in a power-efficient and cost-efficient way. With its disruptive capability and hardware constraint, the integration of IRS imposes some fundamental particularities on the coordination of multi-user signal transmission. Consequently, the conventional orthogonal and non-orthogonal multiple-access schemes are hard to directly apply because of the joint optimization of active beamforming at the base station and passive reflection at the IRS. Relying on an alternating optimization method, we develop novel schemes for efficient multiple access in IRS-aided multi-user multi-antenna systems in this paper. Achievable performance in terms of the sum spectral efficiency is theoretically analyzed. A comprehensive comparison of different schemes and configurations is conducted through Monte-Carlo simulations to clarify which scheme is favorable for this emerging 6G paradigm.

关键词： 6G mobile communication Wireless communication NOMA Time division multiple access Monte Carlo methods Array signal processing Spectral efficiency

来源：评论

学校读者我要写书评

暂无评论

A Privacy-Preserving Symptoms Retrieval System with the Aid of Homomorphic Encryption and Private Set Intersection Schemes

引用

Algorithms 2023年第5期16卷

作者： Wang, Yi-Wei Wu, Ja-Ling Department of Computer Science and Information Engineering National Taiwan University Taipei106216 Taiwan Graduate Institute of Networking and Multimedia National Taiwan University Taipei106216 Taiwan

This work presents an efficient and effective system allowing hospitals to share patients’ private information while ensuring that each hospital database’s medical records will not be leaked;moreover, the privacy of patients who access the data will also be protected. We assume that the thread model of the hospital’s security is semi-honest (i.e., curious but honest), and each hospital hired a trusted medical records department administrator to manage patients’ private information from other hospitals. With the help of Homomorphic Encryption- and Private Set Intersection -related algorithms, our proposed system protects patient privacy, allows physicians to obtain patient information across hospitals, and prevents threats such as troublesome insider attacks and man-in-the-middle attacks. © 2023 by the authors.

关键词： Hospitals

来源：评论

学校读者我要写书评

暂无评论

Approximation Algorithms and Simulated Annealing Heuristics for Row-and-Column Pruning of Deep Neural Networks

Approximation Algorithms and Simulated Annealing Heuristics ...

引用

International Symposium on Parallel and Distributed Processing with Applications, ISPA

作者： Ping-Han Tu Yu-Che Cheng Ding-Yong Hong Pangfeng Liu Jan-Jan Wu The Graduate Institute of Networking and Multimedia National Taiwan University Taipei Taiwan Department of Computer Science and Information Engineering National Taiwan University Taipei Taiwan Institute of Information Science Academia Sinica Taipei Taiwan

ISBN: (数字)9798331509712

ISBN: (纸本)9798331509729

Convolutional neural networks (CNNs) have achieved immense success in computer vision and other field of science. Despite the achievements, state-of-the-art CNN models have grown to gigantic sizes that demand a lot of computing power and memory resources. As a model compression technique, parameter pruning can lower the computation and memory a CNN model needs. Previous work has proposed a parameter pruning method, which compresses the neural networks by eliminating the rows and columns of the weight matrices. Removing rows and columns preserves the dense structure of the weight matrix, rather than the sparse structure produced by unstructured pruning. Although row-and-column pruning effectively reduces the model size, making the model as compact as possible without sacrificing accuracy remains a challenge. We prove that the row-and-column pruning problem is an NP-complete problem, and we propose two approximation algorithms that provide solutions within twice the cost of the optimal solution. We also show that the approximation ratio cannot be improved for these two algorithms. Finally, we propose two schemes based on simulated annealing to solve the row-and-column pruning problem. The two proposed schemes improve accuracy by 2.7% and 1.6%, respectively, on the ResNet-18 model with 93% sparsity using the Food-101 dataset.

关键词： Distributed processing Accuracy Costs Computational modeling Heuristic algorithms Simulated annealing Approximation algorithms Convolutional neural networks Sparse matrices NP-complete problem

来源：评论

学校读者我要写书评

暂无评论

Analysis of Various Image Segmentation Techniques on Retinal OCT Images

Analysis of Various Image Segmentation Techniques on Retinal...

引用

Artificial Intelligence and Smart Systems (ICAIS), International Conference on

作者： T. M. Sheeba S. Albert Antony Raj M. Anand Department of Computer Applications College of Science and Humanities SRM Institute of Science and Technology Chennai India Department of Networking and Communications College of Engineering and Technology SRM Institute of Science and Technology Chennai India

Image segmentation is one of the most important processes involved in image processing. Segmenting an image is breaking it up into smaller pieces, or segments. These are the areas where it is most helpful because processing the complete image would be inefficient for tasks like object recognition or image compression. Image segmentation is the process of dividing an image's elements for further processing. This article looked at a number of image segmentation techniques, including the threshold approach, edge-based method, and clustering-based method. The segmentation method that is most effective for separating images in OCT images is clustering-based segmentation. To reduce the speckle noise during preprocessing, the wiener filter approach is used. With regards to the threshold, edge-based (Sobel, Canny, Robert's), and clustering-based segmentation techniques, calculate MSE (mean square error) and PSNR (peak signal to noise ratio) values for the segmented image quality.

关键词： Image segmentation PSNR Wiener filters Image edge detection Clustering methods Mean square error methods Speckle

来源：评论

学校读者我要写书评

暂无评论

Multiple plant leaf disease detection using efficient Machine learning classification techniques

Multiple plant leaf disease detection using efficient Machin...

引用

Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication engineering (RMKMATE), International Conference on

作者： K. Kalaiselvi K. Deepa Thilak K. Lalitha Devi K. Kumaresan Department of Networking and Communications Faculty of Engineering and Technology SRM Institute of Science and Technology Chennai India Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India Department of CSE K.S.R College of Engineering Tiruchengode Namakkal India

accurate diagnosis of plant diseases is essential for reversing declines in crop output. To study plant illnesses, one must examine the outward symptoms produced by the plant in question. It is also essential for long-term husbandry that plant health be monitored and complaints about diseases made. Disease auditing in plants is tedious work that requires special equipment. It takes a huge commitment of time, courage when dealing with plant illnesses, and fortitude to endure the devilishly long processing time. As a result, landing the photos of the leaves and comparing it with the data sets is how image processing is employed for the detection of plant conditions. To learn to distinguish between photos of unhealthy and healthy leaves, a group of computers is trained on datasets of both types. In conclusion, we now have a straightforward method to descry the complaint existent in crops at a massive scale by employing machine learning to train on the vast data sets available privately. To aid greenhouse growers, this report has been written.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Demand-Aware Beam Hopping and Power Allocation for Load Balancing in Digital Twin empowered LEO Satellite Networks

引用

IEEE Transactions on Wireless Communications 2025年第6期24卷 5084-5098页

作者： Zhao, Ruili Cai, Jun Luo, Jiangtao Gao, Junpeng Ran, Yongyi Chongqing University of Posts and Telecommunications School of Communication and Information Engineering Chongqing400065 China Department of Electrical and Computer Engineering MontrealQCH3G 1M8 Canada Chongqing University of Posts and Telecommunications Electronic Information and Networking Research Institute Chongqing400065 China

Low-Earth orbit (LEO) satellites utilizing beam hopping (BH) technology offer extensive coverage, low latency, high bandwidth, and significant flexibility. However, the uneven geographical distribution and temporal variability of ground traffic demands, combined with the high mobility of LEO satellites, present significant challenges for efficient beam resource utilization. Traditional BH methods based on GEO satellites fail to address issues such as satellite interference, overlapping coverage, and mobility. This paper explores a Digital Twin (DT)-based collaborative resource allocation network for multiple LEO satellites with overlapping coverage areas. A two-tier optimization problem, focusing on load balancing and cell service fairness, is proposed to maximize throughput and minimize inter-cell service delay. The DT layer optimizes the allocation of overlapping coverage cells by designing BH patterns for each satellite, while the LEO layer optimizes power allocation for each selected service cell. At the DT layer, an Actor-Critic network is deployed on each agent, with a global critic network in the cloud center. The A3C algorithm is employed to optimize the DT layer. Concurrently, the LEO layer optimization is performed using a Multi-Agent Reinforcement Learning algorithm, where each beam functions as an independent agent. The simulation results show that this method reduces satellite load disparity by about 72.5% and decreases the average delay to 12ms. Additionally, our approach outperforms other benchmarks in terms of throughput, ensuring a better alignment between offered and requested data. © 2025 IEEE. All rights reserved.

关键词： Satellite communication systems

来源：评论

学校读者我要写书评

暂无评论

Survey on Security Based Approach to Prevent Attacks in SDN Using IoT Framework

Survey on Security Based Approach to Prevent Attacks in SDN ...

引用

International Conference on Edge Computing and Applications (ICECAA)

作者： V. Prabhu P. Balamurugan Department of Computer Science and Engineering School of Computing College of Engineering and Technology SRM Institute of Science and Technology Chengalpattu Tamilnadu India Department of Networking and Communications School of Computing College of Engineering and Technology SRM Institute of Science and Technology Chengalpattu Tamilnadu India

Network evolution trendincludes Internet of Things (IoT) and Software-Defined networking (SDN). By separating the data plane from the control plane, the software defined networking architectural framework is used and it will makes the network admins works more easily. SDN mainly focuses on network management and controls at the higher levels to monitoring and sharing the connection between the devices with the help of network connectivity in real time using the Internet of Things concepts. Almost in all the fields, IoT devices used so have to improve the security of IoT devices. The SDN has the centralized control logic, if the number of network traffic increases then centralized controller may not be handle all the network traffic requests at the same time, because the SDN controller is a single point of failure, its failure can bring the entire network down. The Software Defined Network (SDN) is easily exposed to various attacks mostly to DDoS attacks. Majority of the existing research is concentrated only on sensing of HR-DDoS attacks occurring over the control layer and not focusing on LR-DDoS attack occurring over the data layer because the accuracy of attacks on the LR-DDoS attacks are very low. This study mainly focusing on how to design the multi controller SDN architecture to improve the scalability, how to increase the detection accuracy of low-rate DDoS attacks on the SDN data layer and how to detect the attacks using machine learning algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimizing Real-Time Image Processing in Augmented Reality with Low-Latency Edge AI

Optimizing Real-Time Image Processing in Augmented Reality w...

引用

International Conference on Signal Processing, Communication, Power and Embedded System (SCOPES)

作者： Gokila Deepa G Gomathi S Aadhitya S Sujitha R Sundarrajan M Mani Deepak Choudhry Department of Artificial Intelligence & Data Science PPG Institute of Technology Coimbatore India Department of Computer Science and Engineering Dr. N.G.P. Institute of Technology Coimbatore India Department of Computer Science and Engineering PSNA College of Engineering and Technology Dindigul India Department of Information Technology Christ The King Engineering College Coimbatore India Department of Networking and Communications SRM Institute of Science and Technology Chennai India Department of Computing Technologies SRM Institute of Science and Technology Chennai India

ISBN: (数字)9798331506452

ISBN: (纸本)9798331506469

This work addresses the issue of seamless real-time Augmented Reality (AR) integration in gaming, healthcare, education, and industrial maintenance using resource-constrained edge devices, such as smartphones and AR glasses. The existing models include YOLO, SSD, and Faster R-CNN, which fail to reach an acceptable balance between accuracy and latency, degrading AR interactions. For these purposes, a low-latency Edge-AI model using lightweight CNNs such as MobileNet and EfficientNet for efficient performance is introduced. Task-specific heads allow real-time object detection, classification, and segmentation, while improved training techniques, such as adaptive learning rate scheduling and data augmentation, enhance performance in more complex scenarios. Experimental results show that the method achieves a latency reduction of 30% and accuracy improvement of 10% over challenging AR scenarios while keeping frames per second high enough for smooth usability. This model sets the basis for further optimizations, integrating and deploying real-time data streams on edge platforms, enhancing the prospects of AR applications in different industries through faster response times and higher accuracy.

关键词： Real-time systems Accuracy Computational modeling Image edge detection Image processing Feature extraction Low latency communication Training YOLO Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Coordination of Autonomous Vehicles for Smart Logistics in Industrial Environments

Multi-Agent Coordination of Autonomous Vehicles for Smart Lo...

引用

International Conference on System Modeling & Advancement in Research Trends (SMART)

作者： Kirubhakaran D. Karthikeswaran M. Arun R. Arun Chakravarthy J. Akshya M. Sundarrajan Mani Deepak Choudhry Department of Computer Science and Engineering Surya Engineering College Erode Department of Artificial Intelligence and Data Science Nehru Institute of Engineering and Technology Coimbatore Department of Electronics and Communication Engineering KGiSL Institute of Technology Coimbatore Department of Computational Intelligence SRM Institute of Science and Technology Chennai Department of Networking and Communications SRM Institute of Science and Technology Chennai Department of Computing Technologies SRM Institute of Science and Technology Chennai

ISBN: (数字)9798350380583

ISBN: (纸本)9798350380590

Dynamic effects in industrial logistics demand more creative solutions towards the pursuit of efficiency and agility in evolving environments. Though static path-planning and taskallocation algorithms have provided the basis for how autonomous vehicles are guided within structured environments, those approaches usually fail to contend with indeterminacy outside of their modelled world, where there is dynamic obstacle appearance and changing task requirements, thus raising inefficiencies and costs of operations. To address these issues, the paper introduces a new multi-agent coordination system that uses a hybrid A* algorithm, integrating path planning with sophisticated detection methods for dynamic obstacles and improving superior task allocation. The system is supposed to provide improvements in real-time coordination in industries of autonomous vehicles to achieve efficient management of tasks and paths in changing environments. We integrate the latest in machine learning techniques for improved and real-time updates within the changes of the vehicle routing process based on both immediate sensory input and environmental interactions. Simulations show that our system performs the task much faster than classic systems: up to 30% improvement in completing tasks compared with classic models, and an average improvement of 25% in allround energy efficiency. It intelligently integrates machine learning techniques with real-time data processing. With the ability to scale up or down, or to adapt itself, this system addresses the chief challenges existing methods face and could revolutionize logistics operations within any industry.

关键词： Industries Adaptation models Heuristic algorithms Real-time systems Path planning Vehicle dynamics Collision avoidance Autonomous vehicles Optimization Logistics

来源：评论

学校读者我要写书评

暂无评论

Enhancing Approximate Message Passing via Diffusion Models Towards On-Device Intelligence

Enhancing Approximate Message Passing via Diffusion Models T...

引用

IEEE International Conference on Communications Workshops, ICC

作者： Philip Dai Kai Yue Richeng Jin Tianfu Matt Wu Kaiqi Xiong Enloe High School Raleigh NC USA Department of Electrical and Computer Engineering NC State University Raleigh NC USA College of Information Science and Electronic Engineering Zhejiang University Hangzhou China Intelligent Computer and Networking Security Lab and Cyber Florida University of South Florida Tampa FL USA

ISBN: (数字)9798350304053

ISBN: (纸本)9798350304060

In this paper, we introduce a novel denoising-based approximate message passing framework augmented by a noise estimation module realized through a reverse diffusion process. This approach offers significant improvements in training simplicity, recovery quality, and inference efficiency, particularly suitable for deployment at mobile terminals in dynamic environments to facilitate edge computing. Extensive experiments verify the superiority of the proposed method over the state of the art, and demonstrate its potential towards sustainable edge computing and on-device intelligence at scale.

关键词： Training Message passing Conferences Computational modeling Noise Estimation Diffusion processes

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：