检索结果-内蒙古大学图书馆

Journal of Network Intelligence 2025年第1期10卷 366-382页

作者： Wen, Yan Sun, Hui-Zheng Liu, Liang Zhou, Ya-Kun Bian, Wei Yan, Ming-Hai College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China Shandong Port Group Co. Ltd Qingdao266000 China Geography and Environment Management Faculty of Environment Universoty of Waterloo WaterlooN2L3G1 Canada

Session-based recommendation aims to predict the anonymous user’s next click action based on his/her latest click sequence. Most state-of-the-art approaches use graph neural networks to model sessions as graphs to capture dynamic transitions between items within a session. Inspired by recent progress on hypergraph-based neural networks, we think it is a good candidate to model the commonly related items within a session, and it can provide a sound complement to the normal graph models. In addition, cross session information may also be helpful. But the excessive noise introduced by other sessions is a big challenge and is still not be well resolved by existing works. To this end, we propose a new approach, called Multi Meta Information Fusion Graph Neural Networks (MM-GNN) to infer user preferences for the current session in a more comprehensive way for the anonymous *** fuse information from normal graph and hypergraph to fully exploit their capabilities of capturing sequential behavior and group intention within a session. In order to better use cross session information, we propose a globallevel subsequent item injection module, which injects information of the most possible subsequent item of the last item in the current session in the global scope. Besides, to learn richer information on the hypergraph structure, we model the whole session as a hyperedge to complement sliding windows-based hyperedges when creating the hypergraph. We have evaluated the method on several benchmark datasets and the results show that our method outperforms state-of-the-art methods. © 2025, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

A Cross Attention Transformer-Mixed Feedback Video Recommendation Algorithm Based on DIEN

引用

computers, Materials & Continua 2025年第1期82卷 977-996页

作者： Jianwei Zhang Zhishang Zhao Zengyu Cai Yuan Feng Liang Zhu Yahui Sun College of Software Engineering Zhengzhou University of Light IndustryZhengzhou450000China Faculty of Information Engineering Xuchang Vocational Technical CollegeXuchang461000China College of Computer Science and Technology Zhengzhou University of Light IndustryZhengzhou450000China College of Electronics and Information Zhengzhou University of Light IndustryZhengzhou450000China

The rapid development of short video platforms poses new challenges for traditional recommendation *** systems typically depend on two types of user behavior feedback to construct user interest profiles:explicit feedback(interactive behavior),which significantly influences users’short-term interests,and implicit feedback(viewing time),which substantially affects their long-term ***,the previous model fails to distinguish between these two feedback methods,leading it to predict only the overall preferences of users based on extensive historical behavior ***,it cannot differentiate between users’long-term and shortterm interests,resulting in low accuracy in describing users’interest states and predicting the evolution of their *** paper introduces a video recommendationmodel calledCAT-MFRec(CrossAttention Transformer-Mixed Feedback Recommendation)designed to differentiate between explicit and implicit user feedback within the DIEN(Deep Interest Evolution Network)*** study emphasizes the separate learning of the two types of behavioral feedback,effectively integrating them through the cross-attention ***,it leverages the long sequence dependence capabilities of Transformer technology to accurately construct user interest profiles and predict the evolution of user *** results indicate that CAT-MF Rec significantly outperforms existing recommendation methods across various performance *** advancement offers new theoretical and practical insights for the development of video recommendations,particularly in addressing complex and dynamic user behavior patterns.

关键词： Video recommendation user interest cross-attention transformer

来源：评论

学校读者我要写书评

暂无评论

Relay Memory Analysis via Constraint Satisfaction Modeling for Malware Detection in the Electrical Power Grid 25

Relay Memory Analysis via Constraint Satisfaction Modeling f...

引用

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

作者： Irma Rrushi John Olijnyk Kawthar Badran Julian Rrushi School of Engineering and Computer Science Oakland University Rochester Michigan USA School of Engineering and Computer Science Oakland University Rochester MI USA

ISBN: (纸本)9798400706295

In this paper, we describe an artificial intelligence (AI) method that recognizes valid power grid physics data in the memory dump of an industrial computer, otherwise known as a protective relay. Protective relays are special-purpose computers that run algorithms specialized in monitoring and controlling power grid equipment such as power transformers. We designed a backtracking search algorithm based on the IEC 61850 specification, which seeks to validate the physics meaning of analyzed data. These data are assigned to the domains of power quantities, which are then structured into a constraint hypergraph. Our approach performs node and arc consistency checks and revisions on the constraint hypergraph, generates power quantities for data assignments during the search, and then generates a search tree while exploring assignments of data to power quantities that are physics compliant. If a complete assignment is reached, the analyzed data are deemed physics compliant. If otherwise a solution is not possible, the analyzed data are deemed to include malicious code and *** rationale behind our work is that the bytes of shellcode or memory addresses, which are commonly injected by exploits and malware, fail to show a relation with the physics of power grid. We implemented our constraint satisfaction modeling and backtracking search in Python, and hence tested the complete AI approach against a large repository of publicly available malicious code.

关键词： industrial control systems

来源：评论

学校读者我要写书评

暂无评论

Emerging Trends in AI-Powered IoT: Innovations, Key Challenges, and Future Directions

Emerging Trends in AI-Powered IoT: Innovations, Key Challeng...

引用

2025 IEEE SoutheastCon, SoutheastCon 2025

作者： Abdelraouf, Hussien Abouyoussef, Mahmoud Fouda, Mostafa M. Fadlullah, Zubair Md Ibrahem, Mohamed I. School of Computer and Cyber Sciences Augusta University AugustaGA30912 United States North Carlina A&T State University Department of Computer Systems Technology GreensboroNC27411 United States Idaho State University Department of Electrical and Computer Engineering PocatelloID83209 United States Western University Department of Computer Science LondonON Canada

ISBN: (纸本)9798331504847

This survey provides a comprehensive overview of recent emerging technologies in artificial intelligence (AI) applied to the Internet of Things (IoT), highlighting their significance and applications across various domains. Our study covers key advancements, including Concept Drift, Transformers, TinyML, Explainable AI (XAI), and Federated Learning (FL). Concept Drift addresses changes in data patterns to maintain the accuracy of machine learning models in dynamic environments. Transformers revolutionize Natural language processing (NLP) by efficiently capturing long-range dependencies. TinyML enables smart IoT applications on low-power devices, while XAI promotes transparency in AI decisions. FL facilitates decentralized model training while preserving data privacy. Our discussion also covers challenges, limitations, and future research directions to improve AI and IoT integration. © 2025 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

GenAI-powered Itinerary Planner

GenAI-powered Itinerary Planner

引用

Advancements in Electrical, Electronics, Communication, Computing and Automation (ICAECA), International Conference on

作者： T.Primya G.Kanagaraj Kanika S Kaviyapriya VK Niruba S Department of Computer Science and Engineering KPR Institute of Engineering and Technology Coimbatore India Department of Computer Science and Engineering Kumaraguru College of Technology Coimbatore Tamilnadu India

ISBN: (数字)9798331525439

ISBN: (纸本)9798331525446

The emergence of AI-driven tools has significantly transformed various domains, including travel planning. This project introduces an intelligent travel itinerary planner designed to enhance the trip-planning experience through automation, adaptability, and interactive natural language processing. Built with Python and FastAPI, the system enables users to generate personalized travel plans with minimal manual effort, ensuring accuracy and convenience. It incorporates secure authentication, scalable data management, and cloud-based deployment on AWS, ensuring high reliability and data security. The planner dynamically updates itineraries in response to real-time factors such as flight changes, weather conditions, and availability, providing a seamless and responsive travel experience. Its modular architecture allows smooth integration with existing travel management platforms, making it a valuable asset for both individuals and businesses. By streamlining complex planning tasks and offering AI-driven recommendations, this tool redefines how travelers organize, modify, and optimize their schedules. Designed with scalability in mind, it remains adaptable to emerging trends in travel technology, ensuring long-term efficiency and continuous improvement in user experiences.

关键词： Technological innovation Schedules Automation Accuracy Authentication Chatbots Real-time systems Telecommunication computing Reliability Meteorology

来源：评论

学校读者我要写书评

暂无评论

Enhanced Body Composition Estimation from 3D Body Scans

Enhanced Body Composition Estimation from 3D Body Scans

引用

18th International Joint Conference on Biomedical engineering Systems and Technologies, BIOSTEC 2025

作者： Feng, Boyuan Zheng, Yijiang Cheng, Ruting Feng, Shuya Vaziri, Khashayar Hahn, James Department of Computer Science George Washington University WashingtonDC United States Department of Computer Science and Engineering University of Connecticut StorrsCT United States Department of Surgery The George Washington University Medical Faculty Associates WashingtonDC United States

Accurate body composition assessment is essential for evaluating health and diagnosing conditions like sar copenia and cardiovascular disease. Approaches for accurately measuring body composition, such as Dual Energy X-ray Absorptiometry (DXA) and Magnetic Resonance Imaging (MRI), are precise but costly and limited in accessibility. Some studies have explored predicting body composition by using shapes since 3D scanning techniques allow for precise and efficient digital measurements of body shape. This study introduces an enhanced method using 3D body scanning integrated with a part-to-global Multilayer Perceptron (MLP) network that incorporates predefined high-level features for body composition prediction. For lean mass es timation, our method achieved a root mean square error (RMSE) of 2.85 kg. For fat mass estimation, the RMSE was 2.50 kg, and for bone mineral content (BMC), the RMSE was 193.50 g. These results represent substantial improvements over existing methods, highlighting the effectiveness and reliability of our approach in accurately predicting body composition metrics. © 2025 by SCITEPRESS– science and Technology Publications, Lda.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Detecting Suicidal Intentions through Analysis of Social Media Content

Detecting Suicidal Intentions through Analysis of Social Med...

引用

International Conference on Electrical, computer and Communication engineering (ECCE)

作者： Saikat Chowdhury Md Wajih Tousif Raafi Mohammed Mushfiq Ali Mohammad Shamsul Arefin Department of Computer Science and Engineering Chittagong University of Engineering & Technology Chattogram Bangladesh Department of Computer Science and Engineering International Islamic University Chittagong Chattogram Bangladesh

ISBN: (数字)9798350357509

ISBN: (纸本)9798350357516

Suicide prevention remains a critical challenge, and the detection of suicidal intentions through social media content has emerged as a promising method to identify individuals at risk. This study investigates the use of advanced machine learning, deep learning, and transformer-based models to detect signs of suicidal ideation in bilingual social media posts. A carefully curated dataset, consisting of Bengali and English posts which were collected from various social media like Facebook, Twitter and Youtube, was annotated with expert verification to ensure accuracy. The models were evaluated on their ability to capture the complex linguistic and cultural nuances inherent in both languages. Among the models tested, MultilingualBERT achieved the best performance with a F1 score of 0.90, demonstrating its effectiveness in handling the intricacies of bilingual data. The results emphasize the effectiveness of advanced models in practical applications for mental health monitoring and suicide prevention, offering a powerful tool for early detection and intervention.

关键词： Deep learning Video on demand Social networking (online) Prevention and mitigation Computational modeling Mental health Linguistics Transformers Web sites Monitoring

来源：评论

学校读者我要写书评

暂无评论

Distributed Channel Estimation and Optimization for 6D Movable Antenna: Unveiling Directional Sparsity

引用

IEEE Journal on Selected Topics in Signal Processing 2025年第2期19卷 349-365页

作者： Shao, Xiaodan Zhang, Rui Jiang, Qijun Park, Jihong Quek, Tony Q. S. Schober, Robert Friedrich-Alexander-University Erlangen-Nurnberg Institute for Digital Communications Erlangen91054 Germany Shenzhen Research Institute of Big Data The Chinese University of HongKong School of Science and Engineering Shenzhen518172 China National University of Singapore Department of Electrical and Computer Engineering 117583 Singapore The Chinese University of HongKong School of Science and Engineering Shenzhen518172 China Singapore University of Technology and Design 487372 Singapore

Six-dimensional movable antenna (6DMA) is an innovative and transformative technology to improve wireless network capacity by adjusting the 3D positions and rotations of antennas/antenna surfaces based on the channel spatial distribution. To achieve optimal antenna positions and rotations, acquiring statistical channel state information (CSI) is essential for 6DMA systems. However, existing works assume that a central processing unit (CPU) jointly processes the signals of all 6DMA surfaces. This incurs prohibitively high processing cost and latency for channel estimation due to the vast numbers of 6DMA candidate positions/rotations and antenna elements. Therefore, we propose a distributed 6DMA processing architecture to reduce the processing complexity of the CPU by equipping each 6DMA surface with a local processing unit (LPU). Furthermore, we unveil for the first time the directional sparsity property of the 6DMA channels with respect to distributed users, where each user has significant channel gains only for a (small) subset of 6DMA position-rotation pairs. Based on this property, we propose a practical three-stage protocol for the 6DMA system and corresponding algorithms to conduct statistical CSI acquisition for all 6DMA candidate positions/rotations, 6DMA position/rotation optimization based on statistical CSI, and instantaneous CSI estimation for user data transmission with optimized 6DMA positions/rotations. Simulation results show that the proposed channel estimation algorithms achieve higher accuracy than benchmark schemes, while requiring lower pilot overhead. Moreover, the proposed 6DMA system with statistical CSI-based position/rotation optimization achieves a higher ergodic sum rate than fixed-position and fluid antenna systems, even if the latter have perfect instantaneous CSI. © 2025 IEEE.

关键词： Channel estimation

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cyberbullying Detection: A Comprehensive Framework Using Machine Learning, Deep Learning, and NLP Techniques

Enhancing Cyberbullying Detection: A Comprehensive Framework...

引用

International Conference on Electrical, computer and Communication engineering (ECCE)

作者： Mohammed Mushfiq Ali Mohammad Nafizul Islam Saikat Chowdhury Md Shafiul Abrar Department of Computer Science and Engineering International Islamic University Chittagong Chattogram Bangladesh Department of Computer Science and Engineering Chittagong University of Engineering and Technology Chattogram Bangladesh

ISBN: (数字)9798350357509

ISBN: (纸本)9798350357516

Cyberbullying has emerged as a significant societal issue in the digital age, causing emotional and psychological harm to individuals on social media platforms. The anonymity and reach of these platforms amplify harmful behaviors, necessitating effective interventions. Traditional moderation techniques, such as manual review or user reports, are insufficient to handle the growing scale and complexity of online content. This study introduces a comprehensive framework for cyberbullying classification, leveraging advanced machine learning (ML) techniques and natural language processing (NLP). It highlights the innovative application of SMOTETS to mitigate class imbalance and improve model robustness. A variety of classification models, including ensemble methods and deep learning approaches, were evaluated, with the highest accuracy reaching 92%. Emphasis is placed on preprocessing strategies like tokenization, stemming, and word embeddings to capture nuanced linguistic patterns, such as sarcasm and slang, commonly used in harmful content. By demonstrating the effectiveness of ensemble learning techniques, this work contributes to the development of scalable solutions for cyberbullying detection. The findings aim to advance research in automated abuse detection and promote safer digital environments for all users.

关键词： Deep learning Accuracy Reviews Cyberbullying Psychology Transformers Tokenization Robustness Real-time systems Ensemble learning

来源：评论

学校读者我要写书评

暂无评论

Intrusion Detection in Cybersecurity: A Machine Learning Classifier with Optimized Feature Selection 3

Intrusion Detection in Cybersecurity: A Machine Learning Cla...

引用

3rd International Conference on Integrated Circuits and Communication Systems, ICICACS 2025

作者： Ahamed, S. Niyas Thayanandeswari, C. S. Sree Vasanth, R. Durai Subharathna, N. Malik, M. Abdul Tamizharasi, A. Anna University Department of Electronics and Communication Engineering Chennai India Pet Engineering College Department of Electronics and Communication Engineering Tirunelveli India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Chennai India Bannari Amman Institute of Technology Department of Electronics and Communication Engineering Erode India R.M.D Engineering College Department of Computer Science and Engineering Thiruvallur India

ISBN: (纸本)9798331508456

Concerns about security and privacy were heightened by the increasing dependence on interconnected networks, underscoring the vital role intrusion detection systems (IDS) play in protecting private data. As essential components of modern cybersecurity frameworks, IDS are designed to detect and prevent malicious activities. However, traditional systems face challenges such as handling high-dimensional data, addressing class imbalance, and detecting unknown threats due to the rising sophistication of cyberattacks and growing network traffic. This study proposes a Selective Features Optimized Machine Learning (ML) Classifier that improves IDS performance by utilizing Support Vector Machine (SVM) classification and Genetic Algorithm (GA) based feature selection. The model achieves impressive results, with accuracy of 96%, precision of 95.4%, and recall of 94%, demonstrating its reliability and effectiveness in identifying malicious network traffic. By integrating GA driven feature selection with SVM classification, the proposed system significantly improves threat detection, offering robust solution for real world cybersecurity challenges. © 2025 IEEE.

关键词： Network intrusion

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：