检索结果-内蒙古大学图书馆

International Conference on Advanced Communication Technology (ICACT)

作者： Geon-Woo Kim Joo-Chang Kim Department of AI Computer Science and Engineering Kyonggi University Suwon South Korea Contents Convergence Software Research Institute Kyonggi University Suwon South Korea

ISBN: (数字)9791188428137

ISBN: (纸本)9798331507602

This paper proposes a method for expanding the metadata of three-dimensional point cloud data using Large Language Models (LLMs). Currently, point cloud data plays a crucial role in various fields such as autonomous driving and medical image reconstruction, necessitating the expansion of metadata for efficient processing. Traditionally, metadata construction has relied on manual input, which is prone to errors. In this study, we propose a method that utilizes LLMs, particularly the Llama 3.1 model, to extract the center points of each class in the point cloud data and expand the metadata by adding these center points to the annotation files. By using center points, computational costs are reduced, and the performance of segmentation and detection models based on this data is improved.

关键词： Point cloud compression Solid modeling Three-dimensional displays Computational modeling Large language models Data preprocessing Manuals Metadata Data mining Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Spatiotemporal Traffic Analysis: Deep Hybrid Approach for Resource and Cyberattacks Prediction

Spatiotemporal Traffic Analysis: Deep Hybrid Approach for Re...

引用

International Conference on Ubiquitous Information Management and Communication (IMCOM)

作者： Hyeonmin Lee Dongchan Kim Donggyu Beom Gyurin Byun Van-Vi Vo Hyunseung Choo Department of AI Systems Engineering Sungkyunkwan University Suwon Republic of Korea Department of Electrical and Computer Engineering Sungkyunkwan University Suwon Republic of Korea Convergence Research Institute Sungkyunkwan University Suwon Republic of Korea Department of Computer Science and Engineering Sungkyunkwan University Suwon Republic of Korea

ISBN: (数字)9798331507817

ISBN: (纸本)9798331507824

This study proposes a hybrid deep learning approach to address the complexity and dynamic characteristics of modern network environments. The research integrates Graph Neural networks (GNNs) and Convolutional Long and Short-Term Memory (ConvLSTM) networks to predict future network traffic and detect cyberattacks. The model was trained and evaluated on the CICIDS 2018 dataset which includes various types of normal and malicious traffic. Grid-based representations were created from the dataset. The attack type of each timestamp were visualized using distinct colors to the grid images. These images are sued as input of ConvLSTM model. Protocol and destination port are modeled as nodes in a graph, with volume of data flow represented as weighted edges. This graph-based representation is designed to capture unique traffic patterns of specific services and enhance the analysis of spatial and temporal features. Experimental results show a 13% increase in macro F1 score and a 4% increase in weighted F1 score, highlighting the effectiveness of the proposed method. This research highlights its potential to enable proactive responses through the prediction of potential cyberattack occurrences.

关键词： Solid modeling Protocols Image color analysis Image edge detection Telecommunication traffic Traffic control Graph neural networks Spatiotemporal phenomena Information management computer crime

来源：评论

学校读者我要写书评

暂无评论

Debiasing Classifiers by Amplifying Bias with Latent Diffusion and Large Language Models 25

Debiasing Classifiers by Amplifying Bias with Latent Diffusi...

引用

Proceedings of the 40th ACM/SIGAPP Symposium on Applied Computing

作者： Donggeun Ko Dongjun Lee Namjun Park Wonkyeong Shim Jaekwang Kim AiM Future Seoul Republic of Korea Maum AI Gyeonggi-do Republic of Korea Department of Computer Science and Engineering/Convergence Program for Social Innovation Sungkyunkwan University Suwon Republic of Korea Department of Computer Science and Engineering Sungkyunkwan University Suwon Republic of Korea School of Convergence / Convergence Program for Social Innovation Sungkyunkwan University Suwon Republic of Korea

ISBN: (纸本)9798400706295

Neural networks struggle with image classification when biases are learned and misleads correlations, affecting their generalization and performance. Previous methods require attribute labels (e.g. background, color) or utilizes Generative Adversarial networks (GANs) to mitigate biases. We introduce DiffuBias, a novel pipeline for text-to-image generation that generates bias-conflict samples, without any training. By utilizing pretrained diffusion and image captioning models, DiffuBias generates, bias-conflict samples using the top-K losses from a biased classifier (fB) to debias the classifier. This method not only debiases effectively but also boosts classifier generalization capabilities. Our comprehensive experimental evaluations demonstrate that DiffuBias achieves state-of-the-art performance on benchmark datasets.

关键词： debiasing

来源：评论

学校读者我要写书评

暂无评论

Joint Movement and User Association of UAV-BS for Indoor User Service: A Multi-Agent Deep Reinforcement Learning Approach

Joint Movement and User Association of UAV-BS for Indoor Use...

引用

Consumer Communications and networking Conference, CCNC IEEE

作者： Tae-Yoon Kim Yujeong Ahn Jaeyeol Lee Jae-Hyun Kim Department of Artificial Intelligence Convergence Network Ajou University Suwon South Korea Department of Space Electronics and Information Engineering Ajou University Suwon South Korea Department of Electrical and Computer Engineering Ajou University Suwon South Korea

ISBN: (数字)9798331508050

ISBN: (纸本)9798331508067

This paper investigates the joint optimization of movement and user association for multiple UAV base stations (UAV-BSs) to provide emergency services to indoor users. In this paper, we propose a multi-agent deep Q-network (MADQN) reinforcement learning algorithm to address this problem. Moreover, we apply a self-attention mechanism to achieve the objective more effectively. Simulation results demonstrate that the proposed algorithm outperforms conventional algorithms, such as random action and MADQN without a self-attention mechanism.

关键词： Base stations Simulation Interference Autonomous aerial vehicles Emergency services Deep reinforcement learning Trajectory Optimization Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Optimization Satellite Power Control in Integrated Non-Terrestrial networks Using Multi-Agent Deep Reinforcement Learning

Optimization Satellite Power Control in Integrated Non-Terre...

引用

Consumer Communications and networking Conference, CCNC IEEE

作者： Jaeyeol Lee Won-Jae Lee Tae-Yoon Kim Taehan Moon Jae-Hyun Kim Department of Space Electronics and Information Engineering Ajou University Suwon South Korea Department of Artificial Intelligence Convergence Network Ajou University Suwon South Korea Department of Electrical and Computer Engineering Ajou University Suwon South Korea

ISBN: (数字)9798331508050

ISBN: (纸本)9798331508067

High altitude platform station (HAPS) and low Earth orbit (LEO) satellites that provide services to the ground in the line of sight (LoS) environment are gaining attention as next-generation communication networks. Additionally, integrating HAPS and satellite networks is being researched to provide high-quality communication services to terrestrial environments. However, a critical issue in integrated networks is the increased interference, which leads to degraded signal quality for users and a higher outage probability when the same frequency is used. In this paper, we propose a method to reduce outage probability for users being served by the HAPS by adjusting the transmission power of the satellite using deep reinforcement learning (DRL). This paper uses a multi-agent deep Q-network (MADQN) and an attention-based A-MADQN, which combines MADQN with an attention mechanism. By employing reinforcement learning, the optimal transmission power can be determined. The simulations illustrate confirmed a reduction in user outage probability compared to the conventional satellite transmission power for each cell.

关键词： Satellites Attention mechanisms Power control Low earth orbit satellites Interference Probability Deep reinforcement learning Power system reliability Optimization Next generation networking

来源：评论

学校读者我要写书评

暂无评论

Graph-Based Multi-Task Transfer Learning for Fault Detection and Diagnosis of Few-Shot Analog Circuits

引用

IEEE Internet of Things Journal 2025年

作者： Gao, Zhongyu Yan, aibin Huang, Zhengfeng Cui, Jie Roh, Byeong-Hee Liu, Guangzhu Girard, Patrick Wen, Xiaoqing Anhui University School of Computer Science and Technology Hefei230601 China Hefei University of Technology School of Microelectronics Hefei230009 China Ajou University Department of AI Convergence Network Suwon16499 Korea Republic of University of Montpellier/CNRS LIRMM Montpellier34095 France Kyushu Institute of Technology Department of Computer Science and Networks Fukuoka820-8502 Japan

Building an interpretable fault detection and diagnostic model based on few-shot circuit samples and prior information about circuit structures is of significant importance. To fill these gaps, we propose a graph-based multi-task transfer learning method for fault detection and diagnosis of circuits under few-shot conditions. Firstly, in order to model the interconnections of nodes in a circuit, the sample data is organized into a graph-structure, and a semi-supervised graph-based structural feature fusion method is proposed. The proposed method can accept graph-structured data and process the data using feature fusion methods. Secondly, to improve the model performance under few-shot conditions, two transfer learning mechanisms are proposed for the topological structure characteristics of analog circuits as well as circuit signal characteristics. Finally, through parameter-shared strategy, we propose a task transfer-based fault diagnosis approach. Experimental results on three different circuits show that the proposed method has the best diagnostic accuracy compared to typical detection and diagnosis schemes. © 2025 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Quality of Service Improvement with Optimal Software-Defined networking Controller and Control Plane Clustering

引用

computers, Materials & Continua 2021年第4期67卷 849-875页

作者： Jehad Ali Byeong-hee Roh Department of Computer Engineering and Department of AI Convergence Network Suwon16499Korea

The controller is indispensable in software-defined networking(SDN).With several features,controllers monitor the network and respond promptly to dynamic *** performance affects the quality-of-service(QoS)in *** controller supports a set of ***,the support of the features may be more prominent in one ***,a single controller leads to performance,single-point-of-failure(SPOF),and scalability *** overcome this,a controller with an optimum feature set must be available for ***,a cluster of optimum feature set controllers will overcome an SPOF and improve the QoS in ***,leveraging an analytical network process(ANP),we rank SDN controllers regarding their supporting features and create a hierarchical control plane based cluster(HCPC)of the highly ranked controller computed using the ANP,evaluating their performance for the OS3E *** results demonstrated in Mininet reveal that a HCPC environment with an optimum controller achieves an improved ***,the experimental results validated in Mininet show that our proposed approach surpasses the existing distributed controller clustering(DCC)schemes in terms of several performance metrics i.e.,delay,jitter,throughput,load balancing,scalability and CPU(central processing unit)utilization.

关键词： Quality-of-service software-defined networking controller hierarchical control plane clustering scalability

来源：评论

学校读者我要写书评

暂无评论

Dynamic Transfer Learning Switching Approach Using Resource Benchmark in Edge Intelligence

引用

IEEE Internet of Things Journal 2025年

作者： Nkenyereye, Lionel Rajkumar, Chellakannu Lee, Boon Giin Chung, Wan-Young Pukyong National University Artificial Intelligence Convergence Education and Research Group Busan48513 Korea Republic of Pukyong National University Department of Electronic Engineering Busan48513 Korea Republic of University of Nottingham Ningbo China School of Computer Science Nottingham Ningbo China Beacons of Excellence Research and Innovation Institute Ningbo315104 China Pukyong National University Department of AI Convergence Department of Electronic Engineering Busan48513 Korea Republic of

Machine learning (ML) techniques are applied for profiling computing and processing resources data collected while running deep neural network models on edge devices. Adaptive deep neural network (DNN) model switching requires proper benchmarking for categorizing ai models based on their applications and computational resources enabled by their processing accelerators. Based on benchmark metrics, DNN models can be classified into tiny, low, small, medium, and large resources, then identify DNN models that perform well within resource constraints. Ensure efficient resource allocation, latency management, and trade-off between accuracy and resource. In this work, we propose a benchmark for edge transfer artificial intelligence learning service (TALS) that uses ML techniques. They aim at classifying DNN models by their target edge applications while running edge inferences. We used both unsupervised learning (UL) and supervised learning (SL) techniques to identify the most effective features for the TALS models and to benchmark the performance of edge devices. To achieve this, two approaches were investigated: first, determining features based on edge inference’s computing resources profiling using principal component analysis;and second, classifying the DNN models at the target application level using a regression approach based on historical resource utilization data. In addition, we propose a dynamic model transfer learning that switches between a set of pre-trained and optimized and quantized DNN models based on the cost function. ML techniques learn resource-aware prediction from new resource allocation data and ensure that the multicriteria switch cost selects the inference task models that meet the edge resource constraint requirements. The experimental results highlight a strong relationship between the supervised learning model and the clustering execution method. The dynamic switching approach on real edge devices demonstrates dynamic switching between models

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Continual Reinforcement Learning for Digital Twin Synchronization Optimization

引用

IEEE Transactions on Mobile Computing 2025年

作者： Tong, Haonan Chen, Mingzhe Zhao, Jun Hu, Ye Yang, Zhaohui Liu, Yuchen Yin, Changchuan Beijing University of Posts and Telecommunications Beijing Key Laboratory of Network System Architecture and Convergence Beijing Advanced Information Network Laboratory Beijing China College of Computing and Data Science Singapore University of Miami Department of Electrical and Computer Engineering Frost Institute for Data Science and Computing Coral Gables33146 United States University of Miami Department of Industrial and Systems Engineering Coral Gables33146 United States Zhejiang University College of Information Science and Electronic Engineering Hangzhou310027 China North Carolina State University Department of Computer Science RaleighNC27695 United States Beijing Key Laboratory of Network System Architecture and Convergence China Beijing University of Posts and Telecommunications Beijing Advanced Information Network Laboratory Beijing100876 China

This article investigates the adaptive resource allocation scheme for digital twin (DT) synchronization optimization over dynamic wireless networks. In our considered model, a base station (BS) continuously collects factory physical object state data from wireless devices to build a real-time virtual DT system for factory event analysis. Due to continuous data transmission, maintaining DT synchronization must use extensive wireless resources. To address this issue, a subset of devices is selected to transmit their sensing data, and resource block (RB) allocation is optimized. This problem is formulated as a constrained Markov process (CMDP) problem that minimizes the long-term mismatch between the physical and virtual systems. To solve this CMDP, we first transform the problem into a dual problem that refines RB constraint impacts on device scheduling strategies. We then propose a continual reinforcement learning (CRL) algorithm to solve the dual problem. The CRL algorithm learns a stable policy across historical experiences for quick adaptation to dynamics in physical states and network capacity. Simulation results show that the CRL can adapt quickly to network capacity changes and reduce normalized root mean square error (NRMSE) between physical and virtual states by up to 55.2%, using the same RB number as traditional methods. © 2025 IEEE. All rights reserved.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Admission Control Scheme for Dynamic Slice Handover Policy in 5G network Slicing

引用

computers, Materials & Continua 2023年第5期75卷 4611-4631页

作者： Ratih Hikmah Puspita Jehad Ali Byeong-hee Roh Department of AI Convergence Network Ajou UniversitySuwon16499Korea Department of Computer Engineering and Department of AI Convergence NetworkAjou UniversitySuwon16499Korea

5G use cases,for example enhanced mobile broadband(eMBB),massive machine-type communications(mMTC),and an ultra-reliable low latency communication(URLLC),need a network architecture capable of sustaining stringent latency and bandwidth requirements;thus,it should be extremely flexible and *** enables service providers to develop various network slice *** users travel from one coverage region to another area,the callmust be routed to a slice thatmeets the same or different *** research aims to develop and evaluate an algorithm to make handover decisions appearing in 5G sliced *** of thumb which indicates the accuracy regarding the training data classification schemes within machine learning should be considered for validation and selection of the appropriate machine learning ***,this study discusses the network model’s design and implementation of self-optimization Fuzzy Qlearning of the decision-making algorithm for slice *** algorithm’s performance is assessed by means of connection-level metrics considering the Quality of Service(QoS),specifically the probability of the new call to be blocked and the probability of a handoff call being ***,within the network model,the call admission control(AC)method is modeled by leveraging supervised learning algorithm as prior knowledge of additional ***,to mitigate high complexity,the integration of fuzzy logic as well as Fuzzy Q-Learning is used to discretize state and the corresponding action *** results generated from our proposal surpass the traditional methods without the use of supervised learning and fuzzy-Q learning.

关键词： 5g network slice fuzzy q-Learning slice handover

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：