检索结果-内蒙古大学图书馆

Optimal Multi-Bitrate Video Caching and Processing in Edge Computing: A Stackelberg Game Approach

IEEE Internet of Things Journal 2025年第13期12卷 25059-25076页

作者： Guo, Min Zhang, Di Xing, Weiwei Shao, Xun Liu, Zhi Zhang, Yaoxue Beijing Jiaotong University School of Software Engineering Beijing100044 China Toyohashi University of Technology Department of Electrical and Electronic Information Engineering Aichi441-8580 Japan The University of Electro-Communications Department of Computer and Network Engineering Tokyo182-8585 Japan Tsinghua University Department of Computer Science and Technology Beijing100084 China

By caching and transcoding video files on edge servers, video edge caching (VEC) can alleviate network congestion and improve user experience. To achieve this, VEC needs to address resource allocation and pricing problems and develop caching and transcoding strategies. However, existing works have not effectively coordinated and resolved these issues. Towards this end, we propose a game-theoretic multi-bitrate video caching and processing method for VEC. Specifically, to address these interdependent issues concurrently, we first incorporate multidimensional strategies into the system model and formalize the profit maximization problems of the network service provider and multiple video providers (VPs) as a constrained multi-objective optimization problem. Second, we transform the problem into a Stackelberg game and identify a Nash equilibrium as the solution. To solve the game problem, we decompose the game process into two stages focusing on resource competition and price determination, respectively. Then, we address the problems of transcoding and caching strategies development, and resource allocation in parallel across varying resource price conditions. The transcoding strategy is determined based on the constraints imposed by delay, value, and the source video. For the caching strategy development and resource allocation, we transform them into two grouped knapsack problems and apply the "dominant strategy» from game theory to identify the "feasible strategy» of VPs. Finally, we determine the resource prices in a traversal manner. Theoretical analysis shows that our proposed method achieves the optimal solution. Experimental results show that our algorithm achieve a 6.04% increase in overall profit compared to the greedy strategy algorithm. © 2025 IEEE.

关键词： Costs

来源：评论

学校读者我要写书评

暂无评论

Teacher Probability Reconstruction based knowledge distillation within intelligent network compression

International Journal of Intelligent Networks

引用

International Journal of Intelligent Networks 2025年 6卷 47-56页

作者： Chen, Han Teng, Xuyang Su, Jiajie Li, Chunhao Hu, Chang Han, Meng School of Communication Engineering Hangzhou Dianzi University Hangzhou China Department of Computer Science National University of Singapore Singapore College of Computer Science and Technology Zhejiang University Hangzhou China

In the optimization of intelligent network architecture, limited resources at each node, including edge computing devices, have posed challenges for deploying large models in performance-demanding scenarios. Knowledge distillation serves as a model compression method that extracts knowledge from a large-scale teacher model and transfers it to a more lightweight student model. Previous knowledge distillation methods mainly focus on the intermediate layers of the network. However, due to privacy protection regulations that limit data sharing and access as well as computational efficiency requirements in practical scenarios, feature-based distillation encounters challenges in practical applications. We start with logit-based distillation to address these issues, enabling students to learn more representative knowledge from the teacher's output probability distribution. Due to the structural limitations of the teacher network such as insufficient depth or width, and potential issues in the training data like noise and imbalance, the output probability distribution contains many errors. Therefore, we propose a knowledge distillation method that improves the student by correcting errors in the teacher model. Nevertheless, teacher's errors not only bring mistakes to students but also give students greater subjectivity, enabling them to break free from the limitations of the teacher. We also retain the teacher's thinking to prevent students from becoming biased on the remaining (non-target) categories while correcting teacher errors for students. Extensive experiments demonstrate that our method achieves competitive performance on multiple benchmarks without extra parameters. © 2025 The Authors

关键词： Normal distribution

来源：评论

学校读者我要写书评

暂无评论

A deep reinforcement learning framework and its implementation for UAV-aided covert communication

引用

Chinese Journal of Aeronautics 2025年第2期38卷 403-417页

作者： Shu FU Yi SU Zhi ZHANG Liuguo YIN College of Microelectronics and Communication Engineering Chongqing UniversityChongqing 400044China Department of Electronic Engineering Tsinghua UniversityBeijing 100084China Beijing National Research Center for Information Science and Technology Tsinghua UniversityBeijing 100084China

In this work,we consider an Unmanned Aerial Vehicle(UAV)-aided covert transmission network,which adopts the uplink transmission of communication Nodes(CNs)as a cover to facilitate covert transmission to a Primary communication Node(PCN).Specifically,all nodes transmit to the UAV exploiting uplink non-Orthogonal Multiple Access(NOMA),while the UAV performs covert transmission to the PCN at the same *** minimize the average age of covert information,we formulate a joint optimization problem of UAV trajectory and power allocation designing subject to multi-dimensional constraints including covertness demand,communication quality requirement,maximum flying speed,and the maximum available *** address this problem,we embed Signomial Programming(SP)into Deep Reinforcement Learning(DRL)and propose a DRL framework capable of handling the constrained Markov decision processes,named SP embedded Soft Actor-Critic(SSAC).By adopting SSAC,we achieve the joint optimization of UAV trajectory and power *** simulations show the optimized UAV trajectory and verify the superiority of SSAC compared with various existing baseline *** results of this study suggest that by maintaining appropriate distances from both the PCN and CNs,one can effectively enhance the performance of covert communication by reducing the detection probability of the CNs.

关键词： Covert communication Unmanned aerial vehicle Deep reinforcement learning Trajectory planning Power allocation communication systems

来源：评论

学校读者我要写书评

暂无评论

FLAG: frequency-based local and global network for face forgery detection

引用

Multimedia Tools and Applications 2025年第2期84卷 647-663页

作者： Zhou, Kai Sun, Guanglu Wang, Jun Wang, Jiahui Yu, Linsen School of Computer Science and Technology Harbin University of Science and Technology Harbin150080 China Department of Information Engineering and Mathematics University of Siena Siena53100 Italy

Deepfake detection aims to mitigate the threat of manipulated content by identifying and exposing forgeries. However, previous methods primarily tend to perform poorly when confronted with cross-dataset scenarios. To address the above issue, we propose an innovative hybrid network called the Frequency-based Local and Global (FLAG) network to explore local and global information with the help of frequency-domain cues for better generalization capability. In consideration of the fact that forged faces often exhibit flaws in the frequency domain, we design a Frequency-based Attention Enhancement Module (FAEM) to enhance the aggregation of CNN and Vision Transformer (ViT). In this design, local features from CNN are attentively enhanced by selected frequency coefficients in FAEM, facilitating generalizable global features learning by the ViT module. The effectiveness of the proposed method is validated via numerous experiments and the generalization performance is improved under cross-dataset scenarios. Especially, the proposed method have obtained an AUC of 99.26% and an ACC of 96.56% using intra-dataset experimental results on FaceForensics++ (C23). © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Deep Transfer Learning Techniques in Intrusion Detection System-Internet of Vehicles: A State-of-the-Art Review

引用

computers, Materials & Continua 2024年第8期80卷 2785-2813页

作者： Wufei Wu Javad Hassannataj Joloudari Senthil Kumar Jagatheesaperumal Kandala N.V.P.SRajesh Silvia Gaftandzhieva Sadiq Hussain Rahimullah Rabih Najibullah Haqjoo Mobeen Nazar Hamed Vahdat-Nejad Rositsa Doneva School of Information Engineering Nanchang UniversityNanchang330031China Department of Computer Engineering Technical and Vocational University(TVU)Tehran***Iran Department of Computer Engineering University of BirjandBirjand***Iran Department of Computer Engineering Babol BranchIslamic Azad UniversityBabol***Iran Department of Electronics&Communication Engineering Mepco Schlenk Engineering CollegeSivakasi626005India School of Electronics Engineering VIT-AP UniversityNear Vijayawada522237India Faculty of Mathematics and Informatics University of Plovdiv Paisii HilendarskiPlovdiv4000Bulgaria Examination Branch Dibrugarh UniversityDibrugarh786004India Department of Computer Engineering Faculty of EngineeringUniversity of BirjandBirjand***Iran Faculty of Electrical and Computer Engineering University of BirjandBirjand***Iran Malaysian Institute of Information Technology Universiti Kuala LumpurKuala Lumpur50250Malaysia Faculty of Physics and Technology University of Plovdiv Paisii HilendarskiPlovdiv4000Bulgaria

The high performance of IoT technology in transportation networks has led to the increasing adoption of Internet of Vehicles(IoV)*** functional advantages of IoV include online communication services,accident prevention,cost reduction,and enhanced traffic *** these benefits,IoV technology is susceptible to cyber-attacks,which can exploit vulnerabilities in the vehicle network,leading to perturbations,disturbances,non-recognition of traffic signs,accidents,and vehicle *** paper reviews the state-of-the-art achievements and developments in applying Deep Transfer Learning(DTL)models for Intrusion Detection Systems in the Internet of Vehicles(IDS-IoV)based on anomaly ***-IoV leverages anomaly detection through machine learning and DTL techniques to mitigate the risks posed by *** systems can autonomously create specific models based on network data to differentiate between regular traffic and *** these techniques,transfer learning models are particularly promising due to their efficacy with tagged data,reduced training time,lower memory usage,and decreased computational *** evaluate DTL models against criteria including the ability to transfer knowledge,detection rate,accurate analysis of complex data,and *** review highlights the significant progress made in the field,showcasing how DTL models enhance the performance and reliability of IDS-IoV *** examining recent advancements,we provide insights into how DTL can effectively address cyber-attack challenges in IoV environments,ensuring safer and more efficient transportation networks.

关键词： Cyber-attacks internet of things internet of vehicles intrusion detection system

来源：评论

学校读者我要写书评

暂无评论

Implementation of Gamified Programming Learning Assistant System

Implementation of Gamified Programming Learning Assistant Sy...

引用

2025 IEEE International Conference on Consumer Electronics, ICCE 2025

作者： Kyaw, Htoo Htoo Sandi Kaneko, Keiichi Funabiki, Nobuo Kao, Wen-Chung Department of Computer and Information Science Tokyo University of Agriculture and Technology Tokyo Japan Department of Information and Communication Systems Okayama University Okayama Japan Department of Electrical Engineering National Taiwan Normal University Taipei Taiwan

ISBN: (纸本)9798331521165

Despite the rapid growth of the ICT sector, there is a gap between it and STEM education, resulting in high dropout rates in computer science and engineering programs. This has led to many vacancies in the ICT job market. A major challenge is that traditional teaching methods fail to engage students in difficult and abstract STEM subjects like programming. To overcome this, innovative technology-enhanced learning solutions are needed. In the past, we created a Programming Learning Assistant System (PLAS) to help novice students learn programming. PLAS provides various types of exercises to develop code reading and writing skills at different levels. In this paper, we implement the gamification into PLAS to enhance students' understanding of programming concepts, boost their confidence, spark their interest in STEM fields, and increase engagement in the course through interactive and stimulating scenarios. © 2025 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous Ensemble Feature Selection Model(HEFSM)for Big Data Analytics

引用

computer Systems Science & engineering 2023年第5期45卷 2187-2205页

作者： M.Priyadharsini K.Karuppasamy Department of Information Technology Sri Ramakrishna Engineering CollegeCoimbatoreTamilnaduIndia Department of Computer Science&Engineering RVS College of Engineering and TechnologyCoimbatoreTamilnaduIndia

Big Data applications face different types of complexities in *** and purifying data by eliminating irrelevant or redundant data for big data applications becomes a complex operation while attempting to maintain discriminative features in processed *** existing scheme has many disadvantages including continuity in training,more samples and training time in feature selections and increased classification execution *** ensemble methods have made a mark in classification tasks as combine multiple results into a single *** comparing to a single model,this technique offers for improved *** based feature selections parallel multiple expert’s judgments on a single *** major goal of this research is to suggest HEFSM(Heterogeneous Ensemble Feature Selection Model),a hybrid approach that combines multiple *** major goal of this research is to suggest HEFSM(Heterogeneous Ensemble Feature Selection Model),a hybrid approach that combines multiple ***,individual outputs produced by methods producing subsets of features or rankings or voting are also combined in this ***(K-Nearest Neighbor)classifier is used to classify the big dataset obtained from the ensemble learning *** results found of the study have been good,proving the proposed model’s efficiency in classifications in terms of the performance metrics like precision,recall,F-measure and accuracy used.

关键词： PSO(Particle Swarm Optimization) GWO(GreyWolf Optimization) EHO(Elephant Herding Optimization) data mining big data analytics feature selection HEFSM classifier

来源：评论

学校读者我要写书评

暂无评论

Detection of Malaria by Using a CNN Model 4th

Detection of Malaria by Using a CNN Model

引用

4th International Conference on Machine Intelligence and Signal Processing, MISP 2022

作者： Choubey, Dilip Kumar Raj, Sandeep Aman, Arju Deoli, Rajat Hanselia, Rishabh Department of Computer Science and Engineering Indian Institute of Information Technology Bhagalpur Bihar India Department of Electronics and Communication Engineering Indian Institute of Information Technology Bhagalpur Bihar India

ISBN: (纸本)9789819900848

Malaria is a dangerous and potentially fatal disease caused by Plasmodium parasites that are transferred to humans through the bites of infected Anopheles mosquitos. The most common and accepted technique of diagnosing malaria is for a competent technician to visually analyze a blood smear under a microscope for parasitized red blood cells. The individual conducting the inspection’s experience and knowledge is used to make a diagnosis. It’s also time-consuming and, in rare situations, prone to human mistakes. The research work has been processed into two stages: Stage one deals with dataset summarization, whereas Stage two deals with the proposed algorithm. We present a completely automated CNN-based model for identifying malaria in blood smear micrographs in this study. Our proposed algorithm has a ninety-six percent accuracy rate in detecting malarial parasites from microscopic images, which can be improved further when trained and tested on larger datasets. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning Empowered Skin Diseases Detection in Children

引用

computer Modeling in engineering & Sciences 2024年第12期141卷 2609-2623页

作者： Meena N.Alnuaimi Nourah S.Alqahtani Mohammed Gollapalli Atta Rahman Alaa Alahmadi Aghiad Bakry Mustafa Youldash Dania Alkhulaifi Rashad Ahmed Hesham Al-Musallam Department of Computer Science College of Computer Science and Information TechnologyImam Abdulrahman Bin Faisal UniversityP.O.Box 1982Dammam31441Saudi Arabia Department of Computer Information Systems College of Computer Science and Information TechnologyImam Abdulrahman Bin Faisal UniversityP.O.Box 1982Dammam31441Saudi Arabia Department of Computer Engineering College of Computer Science and Information TechnologyImam Abdulrahman Bin Faisal UniversityP.O.Box 1982Dammam31441Saudi Arabia ICS Department King Fahd University of Petroleum and MineralsDhahran31261Saudi Arabia

Human beings are often affected by a wide range of skin diseases,which can be attributed to genetic factors and environmental influences,such as exposure to sunshine with ultraviolet(UV)*** left untreated,these diseases can have severe consequences and spread,especially among *** detection is crucial to prevent their spread and improve a patient’s chances of ***,the branch of medicine dealing with skin diseases,faces challenges in accurately diagnosing these conditions due to the difficulty in identifying and distinguishing between different diseases based on their appearance,type of skin,and *** study presents a method for detecting skin diseases using Deep Learning(DL),focusing on the most common diseases affecting children in Saudi Arabia due to the high UV value in most of the year,especially in the *** method utilizes various Convolutional Neural Network(CNN)architectures to classify skin conditions such as eczema,psoriasis,and *** proposed method demonstrates high accuracy rates of 99.99%and 97%using famous and effective transfer learning models MobileNet and DenseNet121,*** illustrates the potential of DL in automating the detection of skin diseases and offers a promising approach for early diagnosis and treatment.

关键词： Deep learning MobileNet DenseNet121 skin diseases detection transfer learning

来源：评论

学校读者我要写书评

暂无评论

Developing an Esports Assistant System for First Person Shooting Game Based on Multimodal Learning 14th

Developing an Esports Assistant System for First Person Shoo...

引用

14th International Conference on Frontier Computing, FC 2024

作者： Chiu, Wei-Hsiang Hung, Jason C. Ma, Hao-Shang Huang, Chun-Hong Department of Computer Science and Information Engineering National Taichung University of Science and Technology Taichung Taiwan Department of Computer Information and Network Engineering Lunghwa University of Science and Technology Taoyuan City Taiwan

ISBN: (纸本)9789819623945

We plan to develop a specialized training system to enhance the competitive skills of players in the first-person shooter game "Valorant", aiming to improve their abilities and tactical understanding within the game. We will adopt a multimodal image-text fusion technique to enhance the model’s learning of sample similarity. Specifically, we will use the cross-entropy function to maximize the diagonal values of the similarity matrix, thereby capturing the features of similar samples and reducing the similarity between dissimilar samples. Through this process, we ensure that the model can map the same entity across different modalities into similar embedding representations, while distinguishing unrelated samples. Our goal is to find a way of embedding representation during the learning process that enables the model to better understand and represent multimodal data. We will utilize the YOLOv7 model for object detection to identify destructible skills. Based on the results of object detection, we will generate relevant textual descriptions for each object. This will enable novice players to quickly understand the function of diverse and complex skills and take appropriate actions when encountering them. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Object detection

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：