检索结果-内蒙古大学图书馆

A Comparison Study of FC-RDVM and RIWM Router Placement Methods for WMNs: Performance Evaluation Results by WMN-PSOHC Simulation system Considering Chi-Square Distribution and Different Instances 1

引用

37th International Conference on Advanced Information Networking and Applications, AINA 2023

作者： Sakamoto, Shinji Barolli, Admir Liu, Yi Kulla, Elis Barolli, Leonard Takizawa, Makoto Department of Information and Computer Science Kanazawa Institute of Technology 7-1 Ohgigaoka Ishikawa Nonoichi921-8501 Japan Department of Information Technology Aleksander Moisiu University of Durres L.1 Rruga e Currilave Durres Albania Department of Computer Science National Institute of Technology Oita College 1666 Maki Oita870-0152 Japan Department of System Management Fukuoka Institute of Technology 3-30-1 Wajiro-Higashi Higashi-Ku Fukuoka811-0295 Japan Department of Information and Communication Engineering Fukuoka Institute of Technology 3-30-1 Wajiro-Higashi Higashi-Ku Fukuoka811-0295 Japan Department of Advanced Sciences Faculty of Science and Engineering Hosei University Tokyo Kajino-Machi Koganei-Shi184-8584 Japan

ISBN: (数字)9783031290565

ISBN: (纸本)9783031290558

In this work, we deal with the node placement problem in Wireless Mesh Networks (WMNs). We present a hybrid intelligent simulation system called WMN-PSOHC, which combines Particle Swarm Optimization (PSO) and Hill Climbing (HC). We implement in WMN-PSOHC system the Fast Convergence Rational Decrement of Vmax Method (FC-RDVM) and Random Inertia Weight Method (RIWM) router replacement methods. By using WMN-PSOHC system, we carry out simulations the access the performance of these two methods considering Chi-Square distribution of mesh clients and two different instances. The simulation results show that FC-RDVM performs better then RIWM in the considered scenario. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Optimal Resource Allocation for U-Shaped Parallel Split Learning

arXiv

引用

arXiv 2023年

作者： Lyu, Song Lin, Zheng Qu, Guanqiao Chen, Xianhao Huang, Xiaoxia Li, Pan The Department of Electrical and Electronic Engineering The University of Hong Kong Pok Fu Lam Hong Kong School of Electronics and Communication Engineering Sun Yat-sen University Shenzhen510275 China The Department of Electrical Computer and System Engineering Case Western Reserve University ClevelandOH44106 United States

Split learning (SL) has emerged as a promising approach for model training without revealing the raw data samples from the data owners. However, traditional SL inevitably leaks label privacy as the tail model (with the last layers) should be placed on the server. To overcome this limitation, one promising solution is to utilize U-shaped architecture to leave both early layers and last layers on the user side. In this paper, we develop a novel parallel U-shaped split learning and devise the optimal resource optimization scheme to improve the performance of edge networks. In the proposed framework, multiple users communicate with an edge server for SL. We analyze the end-to-end delay of each client during the training process and design an efficient resource allocation algorithm, called LSCRA, which finds the optimal computing resource allocation and split layers. Our experimental results show the effectiveness of LSCRA and that U-shaped parallel split learning can achieve a similar performance with other SL baselines while preserving label privacy. Copyright © 2023, The Authors. All rights reserved.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

A Way of Making Smart Health Through Collaborating Machine Learning with the Bibliometrics

A Way of Making Smart Health Through Collaborating Machine L...

引用

Advance Computing and Innovative Technologies in engineering (ICACITE), International Conference on

作者： T Vignesh P. S Sruthi T. Mohanraj Gaurav Kumar Akshay Varkale M.Sahaya Sheela Department of Computer Science and Engineering Prince Shri Venkateshwara Padmavathy Engineering College TN Department of Computer Science and Business System Nehru Institute of Technology T.M. Palayam Tamil Nadu India Department of Computer Science Engineering Karpagam Academy of Higher Education Chitkara Centre for Research and Development Chitkara University Himachal Pradesh India Department of Computer Science & Engineering (CS and E) IES Institute of Technology and Management IES University Bhopal M.P India Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India

ISBN: (数字)9798350360165

ISBN: (纸本)9798350360172

It datasets are widely utilized, shared, and repurposed without providing enough context for understanding the decision-making processes that led to their creation. It is necessary to modify system creation and use procedures to handle the concrete effects of how knowledge for model building is envisioned and used in real-world applications as AI systems assume more and more important roles. Documents are created at every phase of the data generation lifecycle to improve communication, aid in decision-making, and highlight the need of careful data work. By putting out this paradigm, we want to shed light on the choices and duties that are often disregarded while creating datasets, which is a crucial first step in bridging the duty of care gap in AI. This framework provides an essential and important resource for guaranteeing ethical AI activities, and it is in line with current developments in auditing procedures.

关键词： Ethics Decision making Smart healthcare Production Planning Maintenance Stakeholders

来源：评论

学校读者我要写书评

暂无评论

Encoder Decoder-Based Virtual Physically Unclonable Function for Internet of Things Device Authentication Using Split-Learning

SSRN

引用

SSRN 2024年

作者： Saleh, Hani Khan, Raviha Muhaidat, Sami Alhussein, Omar Eldeeb, Hossien B. Mefgouda, Brahim Computer and Communication Engineering Department Khalifa University Abu Dhabi United Arab Emirates Computer Science Department Khalifa University Abu Dhabi United Arab Emirates KU-6G Research Center Khalifa University Abu Dhabi United Arab Emirates System on Chip Research Center Khalifa University Abu Dhabi United Arab Emirates

Internet of Things (IoT) networks have been deployed widely because of contemporary methods in which devices communicate. Device authentication in IoT networks is a crucial requirement that poses challenges related to security vulnerabilities, power consumption, and maintenance overheads. While cryptographic techniques secure device communication;storing keys in Non-Volatile Memory (NVM) poses challenges for edge devices. Physically Unclonable Functions (PUFs) offer robust hardware-based authentication but introduce complexities such as hardware production and conservation expenses and susceptibility to aging effects. This paper proposes a novel scheme based on split learning, utilizing an encoder-decoder architecture at the device and server nodes to create a Virtual PUF (VPUF). The proposed VPUF reduces maintenance and power demands compared to the hardware PUF while enhancing security by transmitting latent space representations of responses between nodes. The obtained results demonstrate the effectiveness of the proposed VPUF scheme in modeling the behavior of the hardware-based PUF with added Gaussian noise. Furthermore, the authentication accuracy of the proposed scheme is 100%, as measured by the validation rate. This highlights the superior performance of the proposed scheme in emulating the capabilities of a hardware-based PUF while providing secure and efficient authentication in IoT networks. © 2024, The Authors. All rights reserved.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

A Surveillance system Utilizing mmWave-FMCW Radar for Restricted Control Area

A Surveillance System Utilizing mmWave-FMCW Radar for Restri...

引用

International Conference on Electrical engineering/Electronics, computer, Telecommunications and Information Technology, ECTI-CON

作者： Nattakarn Shutimarrungson Seksan Eiadkaew Akkarat Boonpoonga Krit Athikulwongse Suramate Chalermwisutkul Department of Business Computer Mahasarakham Business School Mahasarakham University Maha Sarakham Thailand Department of Electrical and Computer Engineering Faculty of Engineering King Mongkut's University of Technology North Bangkok Bangkok Thailand Department of Electrical and Computer Engineering Faculty of Engineering Research Center of Innovation Digital and Electromagnetic Technology (iDEMT) King Mongkut's University of Technology North Bangkok Bangkok Thailand National Electronics and Computer Technology Center National Science and Technology Development Agency Pathumthani Thailand Communication and Smart System Engineering The Sirindhorn International Thai- German Graduate School of Engineering King Mongkut's University of Technology North Bangkok Bangkok Thailand

ISBN: (数字)9798350381559

ISBN: (纸本)9798350381566

In this paper, we introduce a surveillance system utilizing mmWave-FMCW radar designed for restricted control areas. The experiment, conducted in our laboratory, defines the restricted control area parameters. Employing the TI-IWR6843AOPEVM model, operating at 60–64 GHz, and providing point cloud and Doppler information, we assumed walking paths for testing, partitioning scenarios into four distinct cases to simulate real-world scenarios. system performance evaluation, assessed through confusion matrices, demonstrates an achieved accuracy of up to 76.9%. Notably, errors are mainly caused by multipath effects due to static objects within the testing environment.

关键词： Point cloud compression Measurement Accuracy Surveillance system performance Radar tracking Doppler radar

来源：评论

学校读者我要写书评

暂无评论

FMCW Radar-Based Enhancing Moving Target Positioning Accuracy in Spectrogram Mapping

FMCW Radar-Based Enhancing Moving Target Positioning Accurac...

引用

International Conference on Electrical engineering/Electronics, computer, Telecommunications and Information Technology, ECTI-CON

ISBN: (数字)9798350381559

ISBN: (纸本)9798350381566

In this paper, we propose a methodology aimed to enhancing the accuracy of moving target positioning using FMCW radar within spectrogram mapping. Utilizing a 10 GHz operating frequency, the FMCW radar effectively detects moving targets. However, the interpretation of intermediate frequency (IF) signals posed challenges due to multiple reflections and resulting ambiguous distances between objects. For solving this problem, we propose two steps of solution: employing an enveloping method and normalization of the IF signal. This process can extract maximum amplitude peaks specific to the target. Experimental validation involved detecting a drone moving away from the radar. Comparative analysis pre and post signal processing in spectrogram terms demonstrate the efficacy of our technique. Furthermore, verification of the detection range of radar was conducted using the GSM-015 GNSS speed meter. Results confirm the accuracy of the positioning capabilities of radar, emphasizing the effectiveness of the proposed approach.

关键词： Visualization Accuracy Refining Radar detection Radar Radar antennas Reflection

来源：评论

学校读者我要写书评

暂无评论

Smart Class on Android: A Handy Classroom Scheduling Solution

Smart Class on Android: A Handy Classroom Scheduling Solutio...

引用

Next Generation communication & Information Processing (INCIP), International Conference on

作者： Vishnuraja Palanisamy M. Thiyagarajan R. Bhavani Arun Anthonisamy K. Manivannan S. Vaishnavi Department of Artificial Intelligence and Data Science Builders Engineering College Kangeyam Tamil Nadu India Department of Computer Science and Engineering School of Computing Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi Chennai Tamil Nadu India Department of Electronics and Communication Engineering K. Ramakrishnan College of Technology Trichy Tamil Nadu India Department of Computer Science and Business System Panimalar Engineering College Chennai Tamil Nadu India Department of Information Science and Engineering School of Computer Science & Engineering JAIN (Deemed-to-be) University Bengaluru Karnataka India Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education (MAHE) Manipal India

ISBN: (数字)9798331528140

ISBN: (纸本)9798331528157

Classroom scheduling is vital but difficult for educational institutions, especially those with large student populations and diverse needs. Traditional methods using outdated software or manual processes often cause inefficiencies, disagreements, and administrative workload. In low-resource regions without access to cutting-edge technology and infrastructure, these issues are severe. This paper introduces Android-based SmartClass Mobile to transform classroom scheduling. The program's SOA-based functionality offers flexibility, adaptability, and integration with institution-specific procedures. The Heuristic algorithm and Solution Space Navigation (SSN) tackle scheduling problems such as room availability, multimedia needs, and seating capacities. SSN dynamically resolves conflicts by exploring alternate configurations, while the Heuristic Algorithm assigns time slots and classrooms depending on availability and priority. SmartClass Mobile analysis indicates benefits. The solution reduces conflicts, increases user satisfaction, and decreases scheduling time by 50% compared to manual methods with 85% test user approval. Due to its mobile-first approach, the initiative is open to urban and rural institutions. Dependence on internet access for some functions is a downside, especially in resource-constrained contexts. The findings suggest that SmartClass Mobile provides a scalable, effective, and simple classroom scheduling solution. Mobile technology, advanced algorithms, and SOA concepts make it valuable for school administrators. Additions like AI and machine learning will boost its potential.

关键词： Navigation Heuristic algorithms Software algorithms Manuals Transforms Scheduling Software Real-time systems Mobile applications Reliability

来源：评论

学校读者我要写书评

暂无评论

Traffic Light Control Using Reinforcement Learning

Traffic Light Control Using Reinforcement Learning

引用

Integrated Circuits and communication systems (ICICACS), IEEE International Conference on

作者： S M Masfequier Rahman Swapno SM Nuruzzaman Nobel Ramachandra A C Md Babul Islam Rezaul Haque Mohammad Mominur Rahman Dept of CSE Bangladesh University of Business and Technology Dhaka Bangladesh Department of Electronics and Communication Engineering Nitte Meenakshi Institute of Technology Bengaluru Dept. of Computer Modeling Electronic and System Engineering UNICAL Rende Italy Dept of CSE East West University Dhaka Bangladesh College of Science and Engineering Hamad Bin Khalifa University Qatar

Nowadays, one of the biggest issues in urban areas is traffic. This problem wastes important time and contributes to air and sound pollution. This affects people’s general quality of life in addition to posing health dangers. Our study attempts to mitigate these problems, effectively cutting down on wait times and delays. Our Reinforcement Learning method creates intelligent agents that can adjust traffic lights at crossings instantly. Our objective is to minimize delays, reduce congestion, reduce travel times, improve safety, and improve traffic flow. We implemented the Deep Q Learning algorithm which activities yield the greatest benefits under various traffic scenarios. Our model can the sequence time since the Green signal (GS) lasts 10 seconds and the Red signal (RS) lasts 5 seconds. The waiting period is shortened by 50% as a result. This study suggests reinforcement learning may improve traffic signal controller synchronization and urban traffic congestion. This novel method may improve transport efficiency and sustainability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Intelligent Caching Strategies for 5G Edge Networks using Machine Learning

Intelligent Caching Strategies for 5G Edge Networks using Ma...

引用

Smart Electronics and communication (ICOSEC), International Conference on

作者： Naga Venkata Ramakrishna Guduri S. Sethu R. Shalinirajan R. Reena Karthikeyan M G.S. Uthayakumar Electrical and Electronics Section Engineering Department University of Technology and Applied Sciences-Al Musannah Sultanate of Oman Department of Computer Science and Engineering Vels Institute of Science Technology & Advanced Studies (VISTAS) Chennai Tamilnadu India Department of Computer Science and Business System Panimalar Engineering College Chennai Tamilnadu India Department of Computer Science and Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai Tamilnadu India Department of Computer Science and Engineering (Cyber Security) R.M.K. College of Engineering and Technology Chennai Tamilnadu India Department of Electronics and Communication Engineering St. Joseph's Institute of Technology Chennai Tamilnadu India

To reduce latency and improve the user experience, content caching solutions at the network periphery will become increasingly important as 5G networks and data-intensive applications. In this proposed work, the deployment of a caching architecture for 5G periphery networks using machine learning is done. Utilizing information on user behavior, network conditions, and content prominence enables more accurate forecasts and cache management decisions. This trains the prediction models using a wide range of machine-learning techniques to accommodate the ever-changing needs of both networks and content. To evaluate the efficiency of the proposed architecture by measuring its ability to increase cache hit rates and decrease latency. These techniques significantly outperform the standard caching methods. With the intelligent caching architecture of 5G periphery networks, throughput is increased, latency is reduced, and congestion is alleviated. The findings of this study contribute to the growing corpus of literature on AI-driven optimization in 5G networks and shed light on how such solutions could be enhanced for future networks. Neural Networks achieved 96% accuracy than SVM which is 93%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Tracing the Motion in High-Speed Video Frames Using Deep Learning

Tracing the Motion in High-Speed Video Frames Using Deep Lea...

引用

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

作者： R. Gayathri Harsha B K D. Sharmiladevi Sajitha. L. P Vuda Sreenivasa Rao G. Nirmala Department of ECE Rajalakshmi Engineering College Chennai Tamilnadu India Department of ECE CMR Institute of Technology Bengaluru Karnataka India Department of Electronics and Communication Engineering Sona College of Technology Salem Tamilnadu India Department of Computer Science and Business System R. M. K Engineering College Kavaraipettai Tamilnadu India Department of CSE Koneru Lakshmaiah Education Foundation Vaddeswaram AP India Department of Computer Science and Engineering R.M.D Engineering College Chennai India

One of the most important jobs of a self-driving vehicle's visual system is to identify and categorize obstacles along the route. Cars need to be detected, categorized, localized, and linked across frames if they are to be tracked. With the low cost and high utility of visual information, vision-based technologies have gained popularity for this purpose. In this paper, we develop a deep learning-based motion tracking from high-speed video frames. The model is developed using deep convolutional neural network that makes it to be applicable for classification of objects in the video frames. The deep convolutional neural network classifies the obstacles present in the pathway and offers a better classification pattern than the conventional models.

关键词：

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：