检索结果-内蒙古大学图书馆

An Extended SDN Architecture for Video-on-Demand Caching

Mobile Networks and Applications 2024年第6期29卷 2004-2021页

作者： Chiang, Wei-Kuo Li, Tsung-Ying Department of Computer Science & amp Information Engineering National Chung Cheng University Chiayi621 Taiwan

Owing to the variety of ways to view the Internet and the changes in user behavior on the Internet, network traffic has been explosively growing in recent years. Users can watch high-quality videos on the Internet;it is a critical issue to reduce network traffic and increase the user's quality of experience (QoE). Therefore, there have been in-network caching services that cache the content that had been fetched by the user in a proxy server. Meanwhile, the software-defined network (SDN) has been developed to implement the network function through the virtualization function. Programmers can implement customized network functions using the SDN architecture. In this paper, we proposed an Extended SDN Cache service architecture (ESC). The ESC decomposes the function of inspecting incoming traffic, making cache decisions, and caching content to three network entities. This design can reduce the load of a single network entity. To reduce the load of the SDN controller, we utilize an extended OpenFlow switch named the DPI (deep packet inspection) switch, which can inspect the incoming traffic. The ESC designed a mechanism that can cache the different parts of a video in distinct cache nodes. The distributed content storage mechanism can increase the cache capability and the system's flexibility. We use the M/M/1 queuing model to analyze the average queuing delay time and compare the ESC queuing delay time with the C-flow and the OpenCache. The numerical analysis results show that the ESC queuing delay is shorter than the other two. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Queueing theory

来源：评论

学校读者我要写书评

暂无评论

An Efficient Attention-Based Strategy for Anomaly Detection in Surveillance Video

引用

computer Systems science & engineering 2023年第9期46卷 3939-3958页

作者： Sareer Ul Amin Yongjun Kim Irfan Sami Sangoh Park Sanghyun Seo Department of Computer Science and Engineering Chung-Ang UniversitySeoul06974Korea Intelligent Convergence Research Lab. ETRIDaeJeon34129Korea Department of Electrical and Electronics Engineering Chung-Ang UniversitySeoul06974Korea College of Art and Technology Chung-Ang UniversityAnseong17546Korea

In the present technological world,surveillance cameras generate an immense amount of video data from various sources,making its scrutiny tough for computer vision *** is difficult to search for anomalous events manually in thesemassive video records since they happen infrequently and with a low probability in real-world monitoring ***,intelligent surveillance is a requirement of the modern day,as it enables the automatic identification of normal and aberrant behavior using artificial intelligence and computer vision *** this article,we introduce an efficient Attention-based deep-learning approach for anomaly detection in surveillance video(ADSV).At the input of the ADSV,a shots boundary detection technique is used to segment prominent ***,The Lightweight ConvolutionNeuralNetwork(LWCNN)model receives the segmented frames to extract spatial and temporal information from the intermediate *** that,spatial and temporal features are learned using Long Short-Term Memory(LSTM)cells and Attention Network from a series of frames for each anomalous activity in a *** detect motion and action,the LWCNN received chronologically sorted ***,the anomaly activity in the video is identified using the proposed trained ADSV *** experiments are conducted on complex and challenging benchmark *** addition,the experimental results have been compared to state-ofthe-artmethodologies,and a significant improvement is attained,demonstrating the efficiency of our ADSV method.

关键词： Attention-based anomaly detection video shots segmentation video surveillance computer vision deep learning smart surveillance system violence detection attention model

来源：评论

学校读者我要写书评

暂无评论

Improving Network Performance in Semantic Communications: A Survey 14

Improving Network Performance in Semantic Communications: A ...

引用

14th International Conference on Ubiquitous and Future Networks, ICUFN 2023

作者： Won, Dongwook Oh, Junsuk Lee, chunghyun Ha, Taeyun Song, Chihyun Vu, Duc-Nghia Cho, Sungrae Chung-Ang University School of Computer Science and Engineering 221 Heukseok Dongjak Seoul Korea Republic of

ISBN: (纸本)9798350335385

Semantic communication enables devices to interact in a meaningful way by transmitting and compressing data at the semantic level. This approach reduces bandwidth usage and enhances understanding, leading to improved decision-making and tailored services. Semantic communication is particularly relevant for emerging technologies like metaverses, augmented reality, virtual reality, smart factories, and autonomous vehicles, which require efficient communication systems. However, to fully benefit from semantic communication, optimal resource management and energy efficiency are crucial. This survey paper aims to provide a comprehensive overview of research in this area, identify gaps and challenges, and serve as a valuable resource for researchers and practitioners. © 2023 IEEE.

关键词： Wireless networks

来源：评论

学校读者我要写书评

暂无评论

Survey on Challenges and Solutions of C-V2X: LTE-V2X Communication Technology 14

Survey on Challenges and Solutions of C-V2X: LTE-V2X Communi...

引用

14th International Conference on Ubiquitous and Future Networks, ICUFN 2023

作者： Hur, Donghyeon Lee, Donghyun Oh, Junsuk Won, Dongwook Song, Chihyun Cho, Sungrae Chung-Ang University School of Computer Science and Engineering 221 Heukseok Dongjak Seoul Korea Republic of

ISBN: (纸本)9798350335385

In Vehicle-to-Everything (V2X) communications, various tasks have been performed to enable various applications for traffic efficiency, road safety and passenger infotainment. This paper deals with challenges and solutions of the core technology of Cellular V2X (C-V2X) communication that provides high reliability and low latency as it evolves from Long Term Evolution (LTE)-V2X to LTE-enhanced V2X (eV2X) and 5G-New Radio (NR)-V2X. And High throughput communication technologies. Finally, we will further invest gate and discuss research directions that can solve the challenges of C-V2X in the future. © 2023 IEEE.

关键词： Vehicle to Everything

来源：评论

学校读者我要写书评

暂无评论

Norm-Based Outlier Filtering and Consensus Aggregation for Robust Federated Learning

引用

IEEE Access 2025年 13卷 104926-104936页

作者： Hasung Yeo Joon-Woo Lee Department of Computer Science and Engineering Chung-Ang University Seoul Republic of Korea

Federated Learning (FL) enables collaborative training of machine learning models across distributed clients without sharing private data, making it ideal for privacy-sensitive applications. However, FL is highly vulnerable to backdoor attacks, especially those designed to persist undetected over time. One of the most advanced of these is the Irreversible Backdoor Attack (IBA), which remains effective even after malicious clients are removed by aligning its updates with benign ones. In this paper, we propose a novel defense framework called Norm-Based Outlier Filtering and Consensus-Aware Aggregation (NOFCA) to effectively defend against such attacks. NOFCA combines norm-based outlier removal of client updates with a consensus-direction-based perturbation mechanism that disrupts the insertion of aligned adversarial updates. Unlike conventional aggregation rules or heuristic-based filtering, our method actively removes anomalous updates and performs adjusted aggregation based on the consensus direction of benign clients, thereby effectively obstructing backdoor attacks. Experimental results on MNIST and CIFAR-10 datasets demonstrate that NOFCA consistently achieves the lowest backdoor accuracy across all evaluated attack scenarios while maintaining competitive main accuracy. Furthermore, under fixed-frequency attack settings, where the attacker participates in every communication round, NOFCA shows robust and stable performance, maintaining strong defense even in highly persistent threat conditions. These findings confirm the effectiveness of NOFCA as a practical and resilient defense strategy for real-world FL systems.

关键词： Federated learning Data models Robustness Filtering Computational modeling Cryptography Training Adaptation models Scalability Privacy

来源：评论

学校读者我要写书评

暂无评论

Synergistically coupling of Ni–Fe LDH arrays with hollow Co–Mo sulfide nanotriangles for highly efficient overall water splitting

引用

Rare Metals 2024年第2期43卷 522-532页

作者： Yun Jae Lee Seung-Keun Park Department of Advanced Materials Engineering Chung-Ang UniversityAnseongGyeonggi-do17546Republic of Korea Department of Intelligent Energy and Industry Chung-Ang University84 Heukseok-ro Dongjak-guSeoul06974Republic of Korea Western Seoul Center Korea Basic Science Institute150 Bugahyeon-roSeodaemun-guSeoul03759Republic of Korea

Developing bifunctional catalysts that can catalyze both oxygen evolution reaction(OER)and hydrogen evolution reaction(HER)is pivotal to commercializing large-scale water ***,a novel hollow nanotriangle composed of NiFe LDH-CoMoS_(x) heterojunction(H-CMSx@NiFe LDH)is proposed as a highly efficient bifunctional electrocatalyst for both OER and *** fabricate a heterojunction system,ultra-thin nickel–iron layered double hydroxide(NiFe LDH)nanosheets are uniformly electrodeposited onto a metal–organic framework-derived hollow CoMoS_(x) *** strong coupling of CoMoS_(x) and NiFe LDH catalysts forms the intimate heterojunction interfaces to facilitate interfacial charge transfer,which is favorable to enhance the bifunctional catalytic ***,the large void of CoMoS_(x) nanotriangles and interconnected ultra-thin NiFe LDH nanosheets result in good electrolyte penetration and gas ***,the as-prepared H-CMSx@NiFe LDH on nickel foam(NF)exhibits an impressive catalytic activity and durability for OER and HER activities,delivering a current density of 100 mA·cm^(−2) at the small overpotentials of 214 and 299 mV in OER and HER,***,H-CMSx@NiFe LDH/NF proves to be an effective electrode for an alkaline electrolyzer,as a voltage of only 1.99 V is enough to achieve a current density voltage of only 1.99 V is enough to achieve a current density of 400 mA·cm^(−2) with no degradation in performance over 50 h.

关键词： Overall water splitting Metal-organic framework Molybdenum sulfide Layered double hydroxide Heterojunction

来源：评论

学校读者我要写书评

暂无评论

RSMA for Uplink MIMO Systems: DRL-Based Achievable System Sum Rate Maximization

RSMA for Uplink MIMO Systems: DRL-Based Achievable System Su...

引用

2023 IEEE Globecom Workshops, GC Wkshps 2023

作者： Truong, Thanh Phung Tuyen Nguyen, Thi My Nguyen, The-Vi Dao, Nhu-Ngoc Cho, Sungrae School of Computer Science and Engineering Chung-Ang University Seoul06974 Korea Republic of Sejong University Department of Computer Science and Engineering Seoul05006 Korea Republic of

ISBN: (纸本)9798350370218

This research studies an uplink multiple-input multiple-output (MIMO) system with rate-splitting multiple access (RSMA) techniques. In this regard, we formulate a problem to maximize the achievable system sum rate by optimizing the precoding matrices at the users and the decoding order of all sub-messages received at the base station (BS). To solve the problem that combines continuous variables and the decoding order, we propose a deep reinforcement learning (DRL) framework that integrates a graph-based searching strategy into the deep deterministic policy gradient (DDPG) algorithm. The simulation results prove the convergence in the training of the proposed framework and its performance in various scenarios. Further-more, the results also open up an attractive research aspect when considering the sum rate maximization problem in RSMA-enhanced MIMO systems. © 2023 IEEE.

关键词： deep reinforcement learning multiple-input multiple-output Rate splitting multiple access

来源：评论

学校读者我要写书评

暂无评论

A Review on AI-Enabled Congestion Control Schemes for Content Centric Networks 14

A Review on AI-Enabled Congestion Control Schemes for Conten...

引用

14th International Conference on Information and Communication Technology Convergence, ICTC 2023

作者： Masood, Arooj Dao, Nhu-Ngoc Kim, Hyosu Son, Yongseok Lee, Hyung Tae Paek, Jeongyeup Cho, Sungrae Chung-Ang University School of Computer Science and Engineering Seoul06974 Korea Republic of Sejong University Department of Computer Science and Engineering Seoul05006 Korea Republic of

ISBN: (纸本)9798350313277

Content centric networks (CCN) offer more advantages over conventional TCP/IP networks in areas like content distribution. However, congestion control functionalities in CCN present challenges such as detecting congestion, over-reducing windows for non-congested paths, and addressing fairness issues. Most existing studies employed congestion control mechanisms similar to those in TCP. In addition, the existing mechanisms were based on conventional optimization rules to adjust the rate at which Interest packets are sent to request data from downstream nodes. However, such existing mechanisms do not consider the changes in network status and caching strategy due to multi-path and multi-source transmission. Moreover, they are based on assumptions about link bandwidth. In this paper, we study the problem of congestion control in CCN and discuss its challenges. In addition, we review the existing congestion control schemes in CCN based on machine learning. Finally, we highlight the open research issues to spur further investigations. © 2023 IEEE.

关键词： congestion control Content centric networks in-network caching

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Natural Language Processing Model and Optical Character Recognition for Detection of Online Grooming on Social Networking Services

引用

computer Modeling in engineering & sciences 2025年第5期143卷 2079-2108页

作者： Sangmin Kim Byeongcheon Lee Muazzam Maqsood Jihoon Moon Seungmin Rho Department of Security Convergence Chung-Ang UniversitySeoul06974Republic of Korea Department of Computer Science COMSATS University IslamabadAtock CampusAttock43600Pakistan Department of Data Science Duksung Women's UniversitySeoul01369Republic of Korea Department of Industrial Security Chung-Ang UniversitySeoul06974Republic of Korea

The increased accessibility of social networking services(SNSs)has facilitated communication and information sharing among ***,it has also heightened concerns about digital safety,particularly for children and adolescents who are increasingly exposed to online grooming *** and accurate identification of grooming conversations is crucial in preventing long-term harm to ***,research on grooming detection in South Korea remains limited,as existing models trained primarily on English text and fail to reflect the unique linguistic features of SNS conversations,leading to inaccurate *** address these issues,this study proposes a novel framework that integrates optical character recognition(OCR)technology with KcELECTRA,a deep learning-based natural language processing(NLP)model that shows excellent performance in processing the colloquial Korean *** the proposed framework,the KcELECTRA model is fine-tuned by an extensive dataset,including Korean social media conversations,Korean ethical verification data from AI-Hub,and Korean hate speech data from Hug-gingFace,to enable more accurate classification of text extracted from social media conversation *** results show that the proposed framework achieves an accuracy of 0.953,outperforming existing transformer-based ***,OCR technology shows high accuracy in extracting text from images,demonstrating that the proposed framework is effective for online grooming *** proposed framework is expected to contribute to the more accurate detection of grooming text and the prevention of grooming-related crimes.

关键词： Online grooming KcELECTRA natural language processing optical character recognition social networking service text classification

来源：评论

学校读者我要写书评

暂无评论

Immersive Body-Hand Gesture Interfaces for HMD- Based Virtual Environment Navigation 13

Immersive Body-Hand Gesture Interfaces for HMD- Based Virtua...

引用

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

作者： Jung, Ki Seok Sohn, Bong-Soo Chung-Ang University Department of Computer Engineering Seoul Korea Republic of School of Computer Science and Engineering Chung-Ang University Seoul Korea Republic of

ISBN: (数字)9781665499392

ISBN: (纸本)9781665499392

In order to experience Virtual Reality (VR) contents realistically, a Head-Mounted Display (HMD) user should be able to immerse themselves in a virtual environment. Gesture interfaces allow the user to immerse in the virtual environment by recognizing and using the user's movement. To maximize this effect, we propose a new gesture interface that can take the advantages of both hand and body gestures for the navigation of virtual environments. Experimental results show that the proposed gesture interface has expanded the available virtual environment, increasing the immersion. © 2022 IEEE.

关键词： Virtual reality

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：