检索结果-内蒙古大学图书馆

13th International Conference on Information and Communication Technology Convergence, ICTC 2022

作者： Min, Junhong Oh, MyoungJin Kim, Woongsoo Seo, Hyewon Paek, Jeongyeup Chung-Ang University Department of Computer Science & Engineering Seoul Korea Republic of

ISBN: (数字)9781665499392

ISBN: (纸本)9781665499392

Time Sensitive Networking (TSN) is an emerging technology for providing deterministic ultra low-latency network based on Ethernet. It is designed for application domains such as industrial automation where guaranteed latency is required to meet the hard deadlines of flows. TSN achieves this by carefully scheduling the transmissions of frames through the IEEE 802.1Qbv standard, also known as time-aware shaper (TAS). However, TAS scheduling problem is classified as NP-hard. To overcome this challenge, we explore various metaheuristic approaches using MEALPY, a state-of-the-art meta-heuristic algorithm module of Python. We evaluate the meta-heuristic algorithms for TAS scheduling optimization problem through TSN simulations and provide observations for future directions. © 2022 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

A Review on Research Trends of Optimization for Client Selection in Federated Learning 38

A Review on Research Trends of Optimization for Client Selec...

引用

38th International Conference on Information Networking, ICOIN 2024

作者： Kim, Jaemin Song, Chihyun Paek, Jeongyeup Kwon, Jung-Hyok Cho, Sungrae Chung-Ang University School of Computer Science and Engineering Seoul06974 Korea Republic of Hallym University Smart Computing Laboratory Hallym University Chuncheon24252 Korea Republic of

ISBN: (纸本)9798350330946

Federated Learning (FL) presents a paradigm shift in data-driven model training, allowing for the collaborative learning of a shared model while keeping all the training data on the client side, hence avoiding central data accumulation. Within this framework, the selection of clients becomes a pivotal element impacting learning efficiency, model performance, and communication overhead. Engaging all clients simultaneously in the learning process can lead to inefficiencies, particularly when considering resource constraints and diverse data distributions. Consequently, there has been a burgeoning interest in research dedicated to developing optimization techniques tailored for strategic client selection to address these challenges. This paper delves into the various optimization strategies proposed in the realm of FL for user selection, scrutinizing their objectives, methodologies, and outcomes. [1] Our review indicates that these techniques not only contribute to alleviating bandwidth constraints and reducing computational loads but also enhance model performance by intelligently choosing clients that provide the most informative updates. Furthermore, we discuss the trade-offs involved in such optimization processes, like the balance between model accuracy and training time, and highlight potential paths for future research that may pave the way for more sophisticated and efficient federated systems. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Intelligent Beamforming Design in mmWave mMIMO: A Reinforcement Learning Approach 13

Intelligent Beamforming Design in mmWave mMIMO: A Reinforcem...

引用

13th International Conference on Information and Communication Technology Convergence, ICTC 2022

作者： Hien Pham, Thi Thu Nguyen, The Vi Cho, Sungrae School of Computer Science and Engineering Chung-Ang University Seoul Korea Republic of

ISBN: (数字)9781665499392

ISBN: (纸本)9781665499392

Bandwidth nowadays becomes increasingly limited due to a huge amount of devices and applications joining the network. Fortunately, along with the development of technology, now we are able to exploit the abundant spectrum available at the millimeter-wave (mmWave) frequency band. This new technique comes with many prospective benefits and one of them is increasing data rates. Nonetheless, one of the major challenge in this is identifying the optimal beamforming (BF) vector in a large antenna array system which is often prohibitively expensive when using an exhaustive search. In this paper, we investigate an intelligent beamforming design in a typical mmWave mMIMO system to overcome the aforementioned problem. Specifically, we propose a solution leveraging the deep q-learning model (DQL) to learn a BF pattern that maximizes the BF rate received at the user equipment. © 2022 IEEE.

关键词： Beamforming

来源：评论

学校读者我要写书评

暂无评论

Analyzing image-based political propaganda in referendum campaigns: from elements to strategies

引用

EPJ Data science 2023年第1期12卷 1-20页

作者： Wang, Ming-Hung Chang, Wei-Yang Kuo, Kuan-Hung Tsai, Kuo-Yu Department of Computer Science and Information Engineering National Chung Cheng University Chiayi Taiwan Department of Information Engineering and Computer Science Feng Chia University Taichung Taiwan Taipei Taiwan

Due to the increasing prominence of social network services, political communication has experienced a paradigm shift. To communicate with internet users, politicians, candidates, and political organizations create fan pages. Initially, they provide text-only material on their pages;later, to increase engagement, they include photos, images, and videos. This paper investigates image-based political images in Taiwan for the first time during a nationwide referendum. Unlike an election, a referendum is a policy-based vote. We evaluate over 2000 Facebook images shared by the two most prominent political parties in order to comprehend the aspects of images and the tactics of political organizations. In addition, we examine the textual content, objects, and colors of the collected data. We find that the characteristics of propaganda materials vary between political groups. Nonetheless, the color strategies employed by both sides are equivalent, with each side utilizing its own representative colors for consolidation and the opponent’s colors for attacking. © 2023, Springer-Verlag GmbH, DE.

关键词： Color

来源：评论

学校读者我要写书评

暂无评论

A Survey on Intelligent Reflecting Surface-aided Non-Orthogonal Multiple Access Networks 13

A Survey on Intelligent Reflecting Surface-aided Non-Orthogo...

引用

13th International Conference on Information and Communication Technology Convergence, ICTC 2022

作者： Nguyen, Thi My Tuyen Nguyen, The Vi Hua, Duc Thien Tran, Nam Phuong Cho, Sungrae School of Computer Science and Engineering Chung-Ang University Seoul Korea Republic of

ISBN: (数字)9781665499392

ISBN: (纸本)9781665499392

Recently, intelligent reflecting surface (IRS) and non-orthogonal multiple access (NOMA) are recognized as the key enablers for B5G and 6G networks, in which IRS can intelligently reconfigure the wireless propagation environment, while NOMA can effectively support massive connectivity and improve user fairness. Therefore, integrating both technologies is a promising approach to compensate for their advantages. In this paper, we provide a small survey of recent studies on IRS, NOMA, and IRS-NOMA integration. Particularly, the basics of IRS and NOMA are first presented, and then, the IRS-NOMA fundamentals are discussed focusing on resource allocation, which is one of the key elements in an efficient IRS-aided NOMA system design. Lastly, we present some future directions for the IRS-NOMA systems. © 2022 IEEE.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Full-body Avatar Generation for Increased Embodiment

Full-body Avatar Generation for Increased Embodiment

引用

Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), IEEE Conference on

作者： Dohyung Kim Jun Koo Jewoong Hwang Minjae Seo Inhyung Jung Kyoungju Park School of Computer Science and Engineering Chung-Ang University

ISBN: (数字)9798350374490

ISBN: (纸本)9798350374506

Having a virtual full-body increases the embodiment of users in virtual reality(VR) applications. As consumer-grade virtual reality systems provide the head and two hand-held sensors, full-body motion generation is a vastly under-determined problem. Consequently, most current VR applications show the upper-body only using an inverse kinematics method from three given sensors or wearing the additional sensors on the lower body. Recent studies have focused on neural network methods to generate a full-body avatar from three sparse sensors. Although neural network methods produce notable results with low error metrics in motion capture datasets, it is challenging to apply to online VR systems. Technical issues include that VR sensors fluctuate and lose connection, hand-held controllers orient differently depending on the user's grabbing style, the coordinate system of VR platforms differs from that of motion capture datasets, and the global position and orientation of the users vary in a virtual world. We address these technical issues and present a solution to generate a full-body avatar in VR systems. We compare our method with other full-body generation methods on online VR systems. Then, we show how our method works in two kinds of online VR tasks, a single-user obstacle task and a multi-user catch ball task, and conduct a user study for embodiment and preferences.

关键词： Measurement Three-dimensional displays Avatars Conferences Neural networks User interfaces Sensor systems

来源：评论

学校读者我要写书评

暂无评论

Luxating Patella and Obesity Prevention Device Model of Dogs Based on Vision Transformers 13

Luxating Patella and Obesity Prevention Device Model of Dogs...

引用

13th International Conference on Information and Communication Technology Convergence, ICTC 2022

作者： Yu, Hyeonwuk Kim, Junho Kim, Mucheol Chung-Ang University Department of Computer Science and Engineering Seoul Korea Republic of

ISBN: (数字)9781665499392

ISBN: (纸本)9781665499392

The number of households raising pets is increasing. Accordingly, the health problems of companion animals, which are regarded as family members, are also becoming an issue. Luxating patella and obesity are common in dogs, which account for about two-thirds of companion animals. However, the disease permanently disrupts the dog's behavior and poses a threat to the dog's overall health. Therefore, We proposes a leash-type smart device model that can improve the dog's living environment and establish a proper eating habit. This model provides dog behavior information and exercise amount information through deep learning so that users can provide a suitable parenting environment for the dog. © 2022 IEEE.

关键词： Animals

来源：评论

学校读者我要写书评

暂无评论

Application of Recommendation System for Personalized Smart Home Care 13

Application of Recommendation System for Personalized Smart ...

引用

13th International Conference on Information and Communication Technology Convergence, ICTC 2022

作者： Cho, Yongmun Kang, HyonJun Kim, Mucheol Chung-Ang University Department of Computer Science and Engineering Seoul Korea Republic of

ISBN: (数字)9781665499392

ISBN: (纸本)9781665499392

Smart home care refers to a technology used to provide optimal life care services through information on the state of users in the living space and surrounding environment. With the recent rapid development of online platforms, many companies have begun to focus on e-commerce, making the development of recommendation systems. We intend to propose personalized smart home healthcare and smart home beauty care to users by applying a personalized recommendation system to smart home care. © 2022 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

A Measurement Study of Adalm-PLUTO Software Defined Radio with IEEE 802.15.4 13

A Measurement Study of Adalm-PLUTO Software Defined Radio wi...

引用

13th International Conference on Information and Communication Technology Convergence, ICTC 2022

作者： Kwon, Yonghan Park, Mingyu Paek, Jeongyeup Chung-Ang University Department of Computer Science & Engineering Seoul Korea Republic of

ISBN: (数字)9781665499392

ISBN: (纸本)9781665499392

Software Defined Radio (SDR) enables a general purpose computer to generate, manipulate, and process various kinds of radio signals using software. It is receiving great interest from scientists and engineers to design novel communication and networking technologies without manufacturing dedicated radio chips. While USRP being the most popular one, Adalm-PLUTO is one of the most affordable SDR among those produced by several different companies. However, Adalm-PLUTO has hardly been used in research work to the best of our knowledge. In this paper, we measure the performance of Adalm-PLUTO SDR as an IEEE 802.15.4 radio, with and against a commercial off-the-shelf device, to verify that Adalm-PLUTO is capable of running IEEE 802.15.4 technology at 250 kbps datarate, at least on the radio side. Evaluation results show that Adalm-PLUTO can achieve over 95 % reliability without CSMA nor retransmissions. © 2022 IEEE.

关键词： Radio

来源：评论

学校读者我要写书评

暂无评论

Analysis of Base Station Location Impact on Performance of LEACH Protocol in Wireless Sensor Networks 13

Analysis of Base Station Location Impact on Performance of L...

引用

13th International Conference on Information and Communication Technology Convergence, ICTC 2022

作者： Woraphonbenjakul, Geeranuch Lee, Yunseong Lee, chunghyun Masood, Arooj Tuyen, Nguyen Thi My Nguyen, The Vi Tran, Anh-Tien Cho, Sungrae School of Computer Science and Engineering Chung-Ang University Seoul Korea Republic of

ISBN: (数字)9781665499392

ISBN: (纸本)9781665499392

Wireless Sensor Networks (WSNs) are widely used in our daily applications. WSNs consist of many small devices called sensor nodes and are used for physical or environmental events monitoring. WSNs are typically used to monitor events from remote or hazardous locations. Therefore, battery replacement is a difficult task. Low Energy Adaptive Clustering Hierarchy (LEACH) protocol is one of the energy-efficient protocols. This protocol minimizes energy dissipation in sensor networks. In this paper, we aim to analyze the impact of base station location on LEACH protocol performance. The results show that the best location for the base station should be in the middle of the network to prolong the network lifetime for last long. © 2022 IEEE.

关键词： Location

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：