检索结果-内蒙古大学图书馆

SGNR: A Social Graph Neural Network Based Interactive Recommendation Scheme for E-Commerce

Tsinghua Science and Technology 2023年第4期28卷 786-798页

作者： Dehua Ma Yufeng Wang Jianhua Ma Qun Jin School of Communications and lnformation Engineering Nanjing University of Posts and TelecommunicationsNanjing 210003China Department the Faculty of Computer and Information SciencesHosei UniversityTokyo 194-0298Japan Networked Information Systems Laboratory Department of Human Informatics and Cognitive SciencesFaculty of Human SciencesWaseda UniversityTokyo 169-8050Japan

Interactive Recommendation(IR)formulates the recommendation as a multi-step decision-making process which can actively utilize the individuals’feedback in multiple steps and optimize the long-term user benefit of *** Reinforcement Learning(DRL)has witnessed great application in IR for ***,user cold-start problem impairs the learning process of the DRL-based recommendation ***,most existing DRL-based recommendations ignore user relationships or only consider the single-hop social relationships,which cannot fully utilize the social *** fact that those schemes can not capture the multiple-hop social relationships among users in IR will result in a sub-optimal *** address the above issues,this paper proposes a Social Graph Neural network-based interactive Recommendation scheme(SGNR),which is a multiple-hop social relationships enhanced DRL *** this framework,the multiple-hop social relationships among users are extracted from the social network via the graph neural network which can sufficiently take advantage of the social network to provide more personalized recommendations and effectively alleviate the user cold-start *** experimental results on two real-world datasets demonstrate that the proposed SGNR outperforms other state-of-the-art DRL-based methods that fail to consider social relationships or only consider single-hop social relationships.

关键词： Interactive Recommendation(IR) Deep Reinforcement Learning(DRL) Graph Neural Network(GNN)

来源：评论

学校读者我要写书评

暂无评论

Efficient Power Control for UAV Based on Trajectory and Game Theory

引用

computers, Materials & Continua 2023年第3期74卷 5589-5606页

作者： Fadhil Mukhlif Ashraf Osman Ibrahim Norafida Ithnin Roobaea Alroobaea Majed Alsafyani Information Assurance and Security Research Group(IASRG) School of ComputingFaculty of EngineeringUniversiti Teknologi MalaysiaJohorMalaysia Faculty of Computing and Informatics University Malaysia SabahKota KinabaluMalaysia Department of Computer Science College of Computers and Information TechnologyTaif UniversityTaifSaudi Arabia

Due to the fact that network space is becoming more limited,the implementation of ultra-dense networks(UDNs)has the potential to enhance not only network coverage but also network *** Aerial Vehicle(UAV)communications have recently garnered a lot of attention due to the fact that they are extremely versatile and may be applied to a wide variety of contexts and purposes.A cognitive UAV is proposed as a solution for the Internet of Things ground terminal’s wireless nodes in this *** the IoT system,the UAV is utilised not only to determine how the resources should be distributed but also to provide power to the wireless *** quality of service(QoS)offered by the cognitive node was interpreted as a price-based utility function,which was demonstrated in the form of a non-cooperative game theory in order to maximise customers’net utility *** energyefficient non-cooperative game theory power allocation with pricing strategy abbreviated as(EE-NGPAP)is implemented in this study with two trajectories Spiral and Sigmoidal in order to facilitate effective power management in Internet of Things(IoT)wireless *** has also been demonstrated,theoretically and by the use of simulations,that the Nash equilibrium does exist and that it is one of a *** proposed energy harvesting approach was shown,through simulations,to significantly reduce the typical amount of power thatwas *** is taken into consideration to agree with the objective of 5G *** order to converge to Nash Equilibrium(NE),the method that is advised only needs roughly 4 iterations,which makes it easier to utilise in the real world,where things aren’t always the same.

关键词： UAV spiral&sigmoid trajectory drones IoT game theory energy efficiency 6G

来源：评论

学校读者我要写书评

暂无评论

Risk Assessment of Linkedin Profiles 8

Risk Assessment of Linkedin Profiles

引用

8th International Conference on computer Science and engineering, UBMK 2023

作者： Aydin, Arzum Bahtiyar, Serif Istanbul Technical University Cyber Security and Privacy Research Lab SPFLab. Faculty of Computer and Informatics Engineering Maslak Istanbul Turkey

ISBN: (纸本)9798350340815

Fake or fraudulent accounts are a significant problem in social networking that is often addressed by the users of various social networking platforms involving Linkedin. Fraudulent accounts generally try to convince people about their identity that they are authentic. Adversaries use fake profiles or they impersonate a real identity on social networks to obtain more privileges. Therefore, it is critical to understand problems regarding fraudulent profiles. In this paper, we propose new sustainable framework to assess risks about profiles in social networking platforms. The framework is implemented as a web extension and it is analyzed with ITU alumni profiles in Linkedin. The analyses results show that there are different profiles within one community in Linkedin that may be significant threat for social network users. © 2023 IEEE.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Evaluating Gaze Detection for Children with Autism Using the ChildPlay-R Dataset

Evaluating Gaze Detection for Children with Autism Using the...

引用

International Conference on Automatic Face and Gesture Recognition

作者： Nursena Boluk Hatice Kose Department of Computer Engineering Faculty of Computer and Informatics Engineering Istanbul Technical University Istanbul Turkey Department of Artificial Intelligence and Data Engineering Faculty of Computer and Informatics Engineering Istanbul Technical University Istanbul Turkey

ISBN: (数字)9798350394948

ISBN: (纸本)9798350394955

This study focuses on detecting two-dimensional (2D) gaze points in interactions between children both with and without autism and adults. Within the scope of this objective, a novel subset called ChildPlay-R has been created based on the open-source ChildPlay dataset. This new dataset includes explicitly the interactions of children with and without autism with adults in similar uncontrolled environments and relevant 2D gaze points. Moreover, the analyses using the Modified Spatiotemporal Gaze Detection (M-STGD) model, compared to the traditional Spatiotemporal Gaze Architecture (STGA), reveal significant improvements in the Area Under the Curve values and out-of-sample precision. These advancements indicate the M-STGD model's potential to provide a deeper understanding of the social engagement patterns of children with autism. This study contributes to the automatic detection of 2D gaze points in social interactions and supports the social development of children with autism.

关键词： Autism Analytical models Adaptation models Accuracy Two-dimensional displays Face recognition Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

DDoS Attack Detection and Mitigation in Software-Defined Networking-Based 5G Mobile Networks with Multiple Controllers 9

DDoS Attack Detection and Mitigation in Software-Defined Net...

引用

9th International Conference on Future Internet of Things and Cloud, FiCloud 2022

作者： Sheibani, Morteza Konur, Savas Awan, Irfan University of Bradford Faculty of Engineering and Informatics Department of Computer Science Bradford United Kingdom

ISBN: (数字)9781665493505

ISBN: (纸本)9781665493505

The increased risk of Distributed Denial-of Service (DDoS) attacks is one of the crucial security issues for 5G networks. Software defined networking (SDN) is one of the key solutions for the centralised control of network behavior for detection and mitigation of network attacks. Single centralised controllers for the SDN-based 5G networks lead to many problems concerning scalability, reliability and other system-related performance. In this respect, employing dispersed controllers will provide a vital solution. However, there are still some issues such as how to equalise the processing burden among these controllers and how to employ multi-controllers to improve the security aspects of the SDN-based 5G networks. In this paper, we propose a new method to equalise the processing burden among the dispersed controllers in SDN-based 5G networks in a dynamic manner. The proposed system employs two levels of controllers: dispersed controllers and a master controller. The master controller manages and performs the grouping of the dispersed controllers. The decision of the groups' reconstruction is the responsibility of the master controller and it is based on the processing burden of the dispersed controllers. The proposed dispersed algorithm is employed in 5G networks to detect and mitigate the DDoS attacks. The simulation results prove that the proposed system performs well in equalising the processing burden among controllers and detection and mitigation of DDoS attacks. © 2022 IEEE.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Micro Frontend Architecture

Micro Frontend Architecture

引用

Zooming Innovation in Consumer Electronics International Conference (ZINC)

作者： Vladimír Kunštnár Patrik Podhorský Faculty of Informatics and Information Technologies Institute of Computer Engineering and Applied Informatics Bratislava Slovakia

ISBN: (数字)9798350349153

ISBN: (纸本)9798350349160

Our paper focuses on software architectures in web application environments, specifically their evolution in client interface development. We will focus on implementing client interfaces with Micro Frontends, which are based on the principle of microservices. We will explain how to implement this architecture and integrate multiple Micro Frontends into a single web application. Additionally, we will evaluate the efficiency and performance of Micro Frontends compared to monolithic client interfaces. Finally, we will compare the performances of the two architectures and propose an improvement to implementing Micro Frontends. Our improvement proposal will explain how Micro Frontends can be implemented to create more modular and reusable user interfaces using well-known methodologies and design patterns.

关键词： Technological innovation Software architecture Design methodology Microservice architectures computer architecture User interfaces Proposals

来源：评论

学校读者我要写书评

暂无评论

Mask Detection Using Convolutional Neural Network

Mask Detection Using Convolutional Neural Network

引用

2022 International Seminar on Application for Technology of Information and Communication, iSemantic 2022

作者： Abdussalam Pramudya, Elkaf Rachmawan Setiono, Oki Muslih, Muslih Dian Nuswantoro University Faculty of Computer Science Department of Informatics Engineering Semarang Indonesia

ISBN: (数字)9781665488396

ISBN: (纸本)9781665488396

COVID-19 virus has hit Indonesia since early March 2020. One of the government's efforts to prevent the spread of COVID-19 is to do physical distancing to require people to wear masks when doing activities outside the home. One way to overcome this problem is by detecting mask users to be more obedient and obedient to the rules, then the identification process is carried out for mask users and those who do not use masks. The process is carried out using the Convolutional Neural Network method. CNN is known to be superior and does not require pre-processing so it saves more time. In terms of algorithmic competence, CNN is considered capable of carrying out the data detection process well. Of the 1376 datasets used, 30 epochs, accuracy = 0.988, recall = 0.990, precision = 0.987, and F1 = 0.988 with the required detection time for each image between 4 to 5 seconds. © 2022 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Retrieval Augmented Generation in Large Language Models: Development of AI Chatbot for Student Support 15

Retrieval Augmented Generation in Large Language Models: Dev...

引用

15th International Conference on eLearning, eLearning 2024

作者： Oreški, Dijana Vlahek, Dino University of Zagreb Faculty of Organization and Informatics Pavlinska 2 Varaždin42000 Croatia University of Maribor Faculty of Electrical Engineering and Computer Science Koroška cesta 46 MariborSI-2000 Slovenia

Large Language Models (LLMs) are being employed in various domains to support different tasks. There are many challenges when working with LLMs, such as hallucination and domain knowledge gaps. Retrieval Augmented Generation (RAG) has emerged as one of the best paradigms for enabling LLMs to access domain-specific data and as a mechanism for mitigating hallucinations. In this paper, we are employing RAG and investigating how large language models use repositories of pre-existing knowledge to enhance the quality and relevance of generated responses. The focus of the paper is the development of real-world RAG applications in the educational domain. The research aims to develop an AI-based chatbot for university students that could answer students` frequently asked questions. Such a chatbot solves several challenges faced by the faculty administration and guides the improvement of the student's study experience. In the implementation, a low-code approach of Flowise AI is used. As a result, the prototype is developed. From the domain point of view, the prototype represents a step toward an AI-powered educational system that has the potential to further enhance the level of individualized educational support. From the technological point of view, such implementation emphasizes the benefits of LLM and RAG integration and the advantages of generative artificial intelligence. © 2024 Copyright for this paper by its authors.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

A Mixed Reality Interface for Tactical Data Management in Geographic Information Systems 7

A Mixed Reality Interface for Tactical Data Management in Ge...

引用

7th International Conference on computer Science and engineering, UBMK 2022

作者： Keskin, Fatih Ince, Gokhan Istanbul Technical University Faculty of Computer and Informatics Engineering Istanbul Turkey Aselsan A.Ş.

ISBN: (数字)9781665470100

ISBN: (纸本)9781665470100

The requirements of security systems evolve as the complexity of risks and dangers increases in modern times. Due to the nature of security operations, the operator's stress and cognitive load increase, as the operators must strictly report events that occur in certain situations. In this paper, we present an alternative interface design for a command and control software traditionally used in regional security systems. We propose a mixed reality application that uses holograms and superimposition methods to enhance the operator's experience. The proposed interface is tested on four different security operation scenarios which are operational planning, unit tracking, surveillance, and alarm detection. According to the results of applied questionnaires such as NASA TLX, PSSUQ, and SUS, it has been observed that the created interface is more informative and more usable compared to the traditional command and control software in terms of security operations. © 2022 IEEE.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Augmenting Internet of Medical Things Security:Deep Ensemble Integration and Methodological Fusion

引用

computer Modeling in engineering & Sciences 2024年第12期141卷 2185-2223页

作者： Hamad Naeem Amjad Alsirhani Faeiz MAlserhani Farhan Ullah Ondrej Krejcar Faculty of Informatics and Management Center for Basic and Applied ResearchUniversity of Hradec KraloveHradec Kralove50003Czech Republic Department of Computer Science College of Computer and Information SciencesJouf UniversityAl Jouf72388Saudi Arabia Department of Computer Engineering&Networks College of Computer and Information SciencesJouf UniversityAl Jouf72388Saudi Arabia Cybersecurity Center Prince Mohammad Bin Fahd UniversityAl JawharahKhobarDhahran34754Saudi Arabia

When it comes to smart healthcare business systems,network-based intrusion detection systems are crucial for protecting the system and its networks from malicious network *** protect IoMT devices and networks in healthcare and medical settings,our proposed model serves as a powerful tool for monitoring IoMT *** study presents a robust methodology for intrusion detection in Internet of Medical Things(IoMT)environments,integrating data augmentation,feature selection,and ensemble learning to effectively handle IoMT data *** rigorous preprocessing,including feature extraction,correlation removal,and Recursive Feature Elimi-nation(RFE),selected features are standardized and reshaped for deep learning *** using the BAT algorithm enhances dataset *** deep learning models,Transformer-based neural networks,self-attention Deep Convolutional Neural Networks(DCNNs),and Long Short-Term Memory(LSTM)networks,are trained to capture diverse data *** predictions form a meta-feature set for a subsequent meta-learner,which combines model *** classifiers validate meta-learner features for broad algorithm *** comprehensive method demonstrates high accuracy and robustness in IoMT intrusion *** were conducted using two datasets:the publicly available WUSTL-EHMS-2020 dataset,which contains two distinct categories,and the CICIoMT2024 dataset,encompassing sixteen *** results showcase the method’s exceptional performance,achieving optimal scores of 100%on the WUSTL-EHMS-2020 dataset and 99%on the CICIoMT2024.

关键词： Cyberattack ensemble learning feature selection intrusion detection smart cities machine learning BAT augmentation

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：