检索结果-内蒙古大学图书馆

OLMS: A Flexible Online Learning Multi-Path Scheduling Framework

IEEE Transactions on Network science and engineering 2025年第3期12卷 2277-2291页

作者： Cai, Kechao Chen, Zhuoyue Zhang, Jinbei Lui, John C. S. Shenzhen Campus of Sun Yat-sen University School of Electronics and Communication Engineering Shenzhen510275 China The Chinese University of Hong Kong Department of Computer Science and Engineering Shatin Hong Kong

Over the past decade, there has been a tremendous surge in the inter-connectivity among hosts in networks. Many multi-path transport protocols, such as MPTCP, MPQUIC, and MPRDMA, have emerged to facilitate multi-path data transmissions between pairs of hosts. However, existing packet schedulers in these protocols are quite limited as they neglect the stochastic nature inherent in heterogeneous paths, such as, round-trip time and available bandwidth. Moreover, users have diverse requirements;for instance, some prioritize low latency, while others consistently seek to achieve high bandwidth. In this paper, we propose a flexible Online Learning Multi-path Scheduling (OLMS) framework to schedule packets to multiple paths and meet various user-defined requirements by learning the dynamic characteristics of paths in various applications. Specifically, we consider two types of applications, which are 1) maxRTT constrained and 2) bandwidth constrained, and use OLMS to schedule packets to satisfy the distinct user-defined requirements. Our theoretical analysis demonstrates that OLMS achieves guarantees with sublinear regret and sublinear violation. Furthermore, we implement a prototype of OLMS in MPQUIC and conduct experiments across different scenarios. Our experiments on Mininet show that OLMS enables an 8.42%–18.71% increase in bandwidth utilization in the maxRTT constrained application and negligible violations of user-defined requirements in both applications compared to other schedulers. Additionally, OLMS reduces flow completion times by 4.22%–10.26% compared to other schedulers, all without incurring large overhead. © 2013 IEEE.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

GSA-DT: A Malicious Traffic Detection Model Based on Graph Self-Attention Network and Decision Tree

引用

IEEE Transactions on Network and Service Management 2025年第2期22卷 2059-2073页

作者： Cai, Saihua Tang, Han Chen, Jinfu Lv, Tianxiang Zhao, Wenjun Huang, Chunlei Jiangsu University School of Computer Science and Communication Engineering Zhenjiang212013 China Jiangsu Provincial Key Laboratory of Industrial Cyberspace Security Technology Zhenjiang212013 China

Malicious attack has shown a rapid growth in recent years, it is very important to accurately detect malicious traffic to defend against malicious attacks. Compared with machine learning and deep learning technologies, graph convolutional neural network (GCN) achieves better detection results of malicious traffic due to additional consideration of the correlation between network traffic features. However, existing GCN-based detection models suffer from fixed weight assignment, only focusing on local features, lack the ability to model graph structure and relationships as well as having gradient disappearance. To solve these problems, this paper proposes the GSA-DT model based on graph self-attention network and decision tree. GSA-DT first preprocesses the original network traffic to obtain better traffic features and labels, and then uses GCN to extract the topological structure of network traffic as well as capture the correlation relationships among traffic features, where the ReLU activation function is replaced by LeakyReLU to overcome the problems of neuron "death"and gradient disappearance during the training process;It also introduces the self-attention mechanism into GCN to assign larger weights to the key features to reduce the interference of redundant features. Finally, GSA-DT uses decision tree to perform the detection of malicious traffic. Experimental results on five network traffic datasets show that GSA-DT model improves the detection accuracy over 1% on average than seven advanced malicious traffic detection models, and it also performs better in F1-measure, TPR, FPR as well as stability. © 2004-2012 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Zero-dynamics attack detection based on data association in feedback pathway

引用

Cognitive Robotics 2025年 5卷 126-139页

作者： Zhang, Zeyu Li, Hongran Todo, Yuki Division of Electrical Engineering and Computer Science Kanazawa University Ishikawa Kanazawa9201192 Japan School of Computer Engineering Jiangsu Ocean University Jiangsu Lianyungang222005 China Faculty of Electrical Information and Communication Engineering Kanazawa University Ishikawa Kanazawa9201192 Japan

This paper considers the security of non-minimum phase systems, a typical kind of cyber-physical systems. Non-minimum phase systems are characterized by unstable zeros in their transfer functions, making them particularly susceptible to disturbances and attacks. The non-minimum phase systems are more vulnerable to zero-dynamics attack (ZDA) than minimum phase systems. ZDA is a stealthy attack strategy that exploits the internal dynamics of a system, remaining undetectable while causing gradual system destabilization. Recent cyber incidents have demonstrated the increasing risk of such hidden attacks in critical infrastructures, such as power grids and transportation systems. This paper first demonstrates that the existing ZDA has the limitation of falling into local convergence, and then proposes an enhanced zero-dynamics attack (EZDA), which overcomes local convergence by diverging system data. Furthermore, this paper presents an autoregressive model which can build the data association between the original data and the forged data. By observing the fluctuations in state values, the presented model can detect not only ZDA, but also EZDA. Finally, numerical simulations and an application example are provided to verify the theoretical results. © 2025

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Fake News Detection Based on Cross-Modal Ambiguity Computation and Multi-Scale Feature Fusion

引用

computers, Materials & Continua 2025年第5期83卷 2659-2675页

作者： Jianxiang Cao Jinyang Wu Wenqian Shang Chunhua Wang Kang Song Tong Yi Jiajun Cai Haibin Zhu State Key Laboratory of Media Convergence and Communication Communication University of ChinaBeijing100024China School of Computer Science and Engineering Guangxi Normal UniversityGuilin541004China Department of Computer Science Nipissing UniversityNorth BayON P1B 8L7Canada

With the rapid growth of socialmedia,the spread of fake news has become a growing problem,misleading the public and causing significant *** social media content is often composed of both images and text,the use of multimodal approaches for fake news detection has gained significant *** solve the problems existing in previous multi-modal fake news detection algorithms,such as insufficient feature extraction and insufficient use of semantic relations between modes,this paper proposes the MFFFND-Co(Multimodal Feature Fusion Fake News Detection with Co-Attention Block)***,the model deeply explores the textual content,image content,and frequency domain ***,it employs a Co-Attention mechanism for cross-modal ***,a semantic consistency detectionmodule is designed to quantify semantic deviations,thereby enhancing the performance of fake news *** verified on two commonly used datasets,Twitter and Weibo,the model achieved F1 scores of 90.0% and 94.0%,respectively,significantly outperforming the pre-modified MFFFND(Multimodal Feature Fusion Fake News Detection with Attention Block)model and surpassing other baseline *** improves the accuracy of detecting fake information in artificial intelligence detection and engineering software detection.

关键词： Fake news detection multimodal cross-modal ambiguity computation multi-scale feature fusion

来源：评论

学校读者我要写书评

暂无评论

An Efficient Dialogue Policy Agent with Model-Based Causal Reinforcement Learning 31

An Efficient Dialogue Policy Agent with Model-Based Causal R...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Xu, Kai Wang, Zhenyu Zhao, Yangyang Fang, Bopeng School of Software Engineering South China University of Technology Guangdong China Department of Computer and Communication Engineering Changsha University of Science and Technology Changsha China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (纸本)9798891761964

Dialogue policy trains an agent to select dialogue actions frequently implemented via deep reinforcement learning (DRL). The model-based reinforcement methods built a world model to generate simulated data to alleviate the sample inefficiency. However, traditional world model methods merely consider one-step dialogues, leading to an inaccurate environmental simulation. Furthermore, different users may have different intention preferences, while most existing studies lack consideration of the intention-preferences causal relationship. This paper proposes a novel framework for dialogue policy learning named MCA, implemented through model-based reinforcement learning with automatically constructed causal chains. The MCA model utilizes an autoregressive Transformer to model dialogue trajectories, enabling a more accurate simulation of the environment. Additionally, it constructs a causal chains module that outputs latent preference distributions for intention-action pairs, thereby elucidating the relationship between user intentions and agent actions. The experimental results show that MCA can achieve state-of-the-art performances on three dialogue datasets over the compared dialogue agents, highlighting its effectiveness and robustness. © 2025 Association for Computational Linguistics.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Air quality and dust level monitoring systems in hospitals using IoT

引用

Discover Internet of Things 2025年第1期5卷 1-18页

作者： Parkavi, A. Sowmya, B.J. Alex, Sini Anna Supreeth, S. Shruthi, G. Rohith, S. Chatterjee, Sudipta Lingaraj, K. Department of Computer Science and Engineering Ramaiah Institute of Technology Bengaluru560054 India Department of Artificial Intelligence and Data Science Ramaiah Institute of Technology Bengaluru560054 India Ramaiah Institute of Technology Bengaluru560054 India School of Computer Science and Engineering REVA University Bengaluru560064 India Department of Electronics and Communication Engineering Nagarjuna College of Engineering and Technology Bengaluru562164 India Department of Electronics and Communication Engineering Brainware University Barasat West Bengal Kolkata700125 India Department of Computer Science and Engineering Rao Bahadur Y. Mahabaleswarappa Engineering College Bellary583104 India

This system provides a comprehensive overview of hospital environments by tracking air quality, dust, temperature, and humidity simultaneously, offering a more complete picture of indoor conditions than systems that focus on fewer parameters. The use of IoT technology enables real-time monitoring and alerts, allowing hospital staff to respond immediately to any issues. Additionally, predictive analytics anticipate future changes, giving staff time to take preventive measures. The integration with a mobile app and cloud-based data storage ensures easy access to data, convenient monitoring, and the ability to scale the system across multiple hospital facilities, catering specifically to the unique needs of different healthcare environments. © The Author(s) 2025.

关键词： Indoor air pollution

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Convolutional Neural Network with Squeeze and Excitation Module for Security Authentication Using Wireless Channel

引用

computers, Materials & Continua 2025年第5期83卷 2025-2040页

作者： Xiaoying Qiu Xiaoyu Ma Guangxu Zhao Jinwei Yu Wenbao Jiang Zhaozhong Guo Maozhi Xu College of Computer Science Beijing Information Science and Technology UniversityBeijing100192China School of Information and Communication Engineering Beijing University of Posts and TelecommunicationsBeijing100876China School of Mathematical Sciences Peking UniversityBeijing100871China

Physical layer authentication(PLA)in the context of the Internet of Things(IoT)has gained significant *** with traditional encryption and blockchain technologies,PLA provides a more computationally efficient alternative to exploiting the properties of the wireless medium *** existing PLA solutions rely on static mechanisms,which are insufficient to address the authentication challenges in fifth generation(5G)and beyond wireless ***,with the massive increase in mobile device access,the communication security of the IoT is vulnerable to spoofing *** overcome the above challenges,this paper proposes a lightweight deep convolutional neural network(CNN)equipped with squeeze and excitation module(SE module)in dynamic wireless environments,namely *** be more specific,a convolution factorization is developed to reduce the complexity of PLA models based on deep ***,an SE module is designed in the deep CNN to enhance useful features andmaximize authentication *** with the existing solutions,the proposed SE-ConvNet enabled PLA scheme performs excellently in mobile and time-varying wireless environments while maintaining lower computational complexity.

关键词： Physical layer authentication blockchain squeeze and excitation module computational cost mobile scenario

来源：评论

学校读者我要写书评

暂无评论

Breaking the Interference and Fading Gridlock in Backscatter communications: State-of-the-Art, Design Challenges, and Future Directions

引用

IEEE communications Surveys and Tutorials 2025年第2期27卷 870-911页

作者： Gu, Bowen Li, Dong Ding, Haiyang Wang, Gongpu Tellambura, Chintha Macau University of Science and Technology School of Computer Science and Engineering China National University of Defense Technology College of Information and Communication Wuhan430019 China Beijing Jiaotong University School of Computer and Information Technology Beijing100044 China University of Alberta Department of Electrical and Computer Engineering EdmontonABT6G 2R3 Canada

As the Internet of Things (IoT) advances by leaps and bounds, a multitude of devices are becoming interconnected, marking the onset of an era where everything is connected. While this growth opens up opportunities for novel products and applications, it also leads to increased energy reliance on IoT devices, creating a significant bottleneck that hinders sustainable progress. Backscatter communication (BackCom), as a low-power and passive communication technology, emerges as one of the promising solutions to this energy impasse by reducing the manufacturing cost and energy consumption for IoT devices. However, BackCom systems also face some challenges, such as complex interference environments, including the direct-link interference (DLI) and the mutual interference (MI) between tags, which severely disrupt the efficiency of BackCom networks. Moreover, the double-path fading is another major issue that leads to a degraded system performance. To fully unleash the potential of BackComs, the purpose of this paper is to furnish a comprehensive review of existing solutions with a focus on addressing these challenges, offering an insightful analysis and comparison of various strategies. Specifically, we begin by introducing the preliminaries for BackCom, including its history, operating mechanisms, main architectures, etc., providing a foundational understanding of this field. Then, we delve into fundamental issues related to BackCom systems, such as solutions for the DLI, the MI, and the double-path fading. This paper thoroughly provides state-of-the-art advances for each case, particularly highlighting how the latest innovations in theoretical approaches and system design can strategically address these challenges. Finally, we explore emerging trends and challenges in BackComs by forecasting potential technological advancements and providing insights and guidelines for navigating the intricate landscape of future communication needs in a rapidly evolving IoT ecosystem.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Quantifying Racial Segregation Through Continuous-Time Quantum Walks 27th

Quantifying Racial Segregation Through Continuous-Time Quant...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Jiang, Yutong Wu, Xing Wang, Jianjia School of Computer Engineering and Science Shanghai University Shanghai China Engineering and Science Shanghai Institute for Advanced Communication and Data Science School of Computer Shanghai University Shanghai China Xi’an Jiaotong-Liverpool University Suzhou215123 China

ISBN: (纸本)9783031781919

With the development of cities, racial segregation is one of the reasons for social inequality on a large scale, it is also a major factor affecting economic development. However, racial segregation has received comparatively limited attention in research. In the paper, we propose a segregation index independent of any parameters( titled Quantum Walk Convergence Time), which calculates the convergence time statistics for accessing different racial categories through quantum walks on complex networks constructed from urban systems. The magnitude of the time statistics represents the degree of racial segregation. The results generated by our method can also be applied to other social factors, including family situation, income level, and education level. We evaluate our method using large-scale real datasets, including statistics from the U.S. Census Bureau and the Office for National Statistics in the UK. The results demonstrate the close correlation between our method and the degree of racial segregation, showing advantages over traditional random walk methods. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Continuous time systems

来源：评论

学校读者我要写书评

暂无评论

DeepFakeGuard: Safeguarding Digital Platforms Against Fake Profiles Using AI 4

DeepFakeGuard: Safeguarding Digital Platforms Against Fake P...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Swarna Sudha, M. Manjula, S. Bharathi, Indira Krishnasamy, Valarmathi Vijayalakshmi, K. Ramco Institute of Technology Department of Computer Science and Engineering Rajapalayam India School of Computer Science and Engineering Vellore Institute of Technology Chennai India PSR Engineering College Department of Electronics and Communication Engineering Sivakasi India

ISBN: (纸本)9798331523923

This research introduces DeepFakeGuard, a hybrid deep learning framework designed to detect fake profiles on social media platforms, addressing the growing threat of fraudulent accounts online. DeepFakeGuard integrates multiple data modalities, including textual, visual, behavioral, and network features, to accurately classify profiles as real or fake. Leveraging advanced deep learning models such as BERT for textual analysis, ResNet for image processing, and LSTM for modeling behavioral patterns, DeepFakeGuard provides a comprehensive and robust solution for identifying fake profiles across diverse platforms. The framework processes a rich set of profile characteristics, including account information, posting behavior, post sentiment, and network relationships, ensuring a multi-dimensional analysis of social media accounts. The hybrid architecture of DeepFakeGuard merges outputs from individual sub-models, which are then processed through dense layers for final classification using a sigmoid activation function. This multi-faceted approach significantly enhances detection accuracy, precision, and recall compared to traditional methods. The framework is highly scalable and adaptable to various social media platforms, offering a versatile tool for strengthening online security. With strong performance metrics, including high classification accuracy, DeepFakeGuard demonstrates its potential for real-world applications in mitigating the risks associated with fake profiles. By fostering secure and trustworthy social media environments, this research contributes to the ongoing fight against fraudulent accounts, paving the way for safer online interactions. © 2025 IEEE.

关键词： Contrastive Learning

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：