检索结果-内蒙古大学图书馆

RDG-TE: Link reliability-aware DRL-GNN-based traffic engineering in SDN

Expert Systems with Applications 2025年 265卷

作者： Farhan, Muhammad Shah, Nadir Wang, Lei Muntean, Gabriel-Miro Song, Houbing Herbert School of Software Dalian University of Technology Dalian China Department of Computer Science COMSATS University Islamabad Wah Campus Pakistan Key Lab of Ubiquitous Network and Service Software of Liaoning Province China School of Electronic Engineering Dublin City University Dublin Ireland Department of Information Systems University of Maryland Baltimore United States

The existing advanced machine learning approaches based on Graph Neural Networks (GNN) for efficient traffic engineering (TE) in software Defined Networking (SDN) overlook consideration of link reliability values. Link reliability is a very important parameter, directly linked to end-to-end delay for data packet transmission, and can be used to improve the delivery performance. This research article proposes two versions of RDG-TE, a novel model that integrates Deep Reinforcement Learning (DRL) and GNN in order to solve efficiently network TE problems by considering link reliability in both model training and reward computation. The proposed model enables improved performance by more accurately predicting the SDN network behavior in case of link failure. Testing results show that, in comparison to the closest state-of-art approach, our proposed approach reduces the number of disturbed flows by 24.19% and the hop count by 35.38% while also increases the reliable route prediction accuracy by 40.17%. © 2024 Elsevier Ltd

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

HealthEdge: A Machine Learning-Based Smart Healthcare Framework for Prediction of Type 2 Diabetes in an Integrated IoT, Edge, and Cloud Computing System 14

HealthEdge: A Machine Learning-Based Smart Healthcare Framew...

引用

14th International Conference on Ambient Systems, Networks and Technologies Networks, ANT 2023 and The 6th International Conference on Emerging Data and Industry 4.0, EDI40 2023

作者： Hennebelle, Alain Materwala, Huned Ismail, Leila Melbourne Australia Research Laboratory Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates University United Arab Emirates National Water and Energy Center United Arab Emirates University United Arab Emirates Lab School of Computing and Information Systems The University of Melbourne Australia

Diabetes Mellitus has no permanent cure to date and is one of the leading causes of death globally. The alarming increase in diabetes calls for the need to take precautionary measures to avoid/predict the occurrence of diabetes. This paper proposes HealthEdge, a machine learning-based smart healthcare framework for type 2 diabetes prediction in an integrated IoT-edge-cloud computing system. Numerical experiments and comparative analysis were carried out between the two most used machine learning algorithms in the literature, Random Forest (RF) and Logistic Regression (LR), using two real-life diabetes datasets. The results show that RF predicts diabetes with 6% more accuracy on average compared to LR. © 2023 Elsevier B.V.. All rights reserved.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

UncTrack: Reliable Visual Object Tracking With Uncertainty-Aware Prototype Memory Network

引用

IEEE Transactions on Image Processing 2025年 34卷 3533-3546页

作者： Siyuan Yao Yang Guo Yanyang Yan Wenqi Ren Xiaochun Cao School of Computer Science (National Pilot Software Engineering School) Beijing University of Posts and Telecommunications Beijing China State Key Laboratory of Processors Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Cyber Science and Technology Sun Yat-sen University Shenzhen Campus Shenzhen China

Transformer-based trackers have achieved promising success and become the dominant tracking paradigm because of their accuracy and efficiency. Despite the substantial progress, most of the existing approaches handle object tracking as a deterministic coordinate regression problem, while the target localization uncertainty has been largely overlooked, which hampers trackers’ ability to maintain reliable target state prediction in challenging scenarios. To address this issue, we propose UncTrack, a novel uncertainty-aware transformer-based tracker that predicts the target localization uncertainty and incorporates this uncertainty information for accurate target state inference. Specifically, UncTrack uses a transformer encoder to perform feature interactions between the template and search images. The output features are passed into an uncertainty-aware localization decoder (ULD) to coarsely predict the corner-based localization and the corresponding localization uncertainty. Then, the localization uncertainty is sent into a prototype memory network (PMN) to excavate valuable historical information to identify whether the target state prediction is reliable. To enhance the template representation, the samples with high confidence are fed back into the prototype memory bank for memory updating, which makes the tracker more robust to challenging appearance variations. Extensive experiments demonstrate that our method outperforms the state-of-the-art methods. Our code is available at https://***/ManOfStory/UncTrack

关键词： Uncertainty Location awareness Target tracking Transformers Reliability Prototypes Object tracking Visualization Accuracy Training

来源：评论

学校读者我要写书评

暂无评论

Capturing Users Requirements Using a Data Mining Approach 3

Capturing Users Requirements Using a Data Mining Approach

引用

3rd International Conference on Communication Technologies, ComTech 2021

作者： Qureshi, Muhammad Zeeshan Azhar, Anique Abubakar, Qazi Rana, Tauseef Ahmad Maqbool, Ayesha National University of Sciences and Technology MCS Department of Software Engineering Islamabad Pakistan National University of Sciences and Technology NBS Department of Computer Science NUST Islamabad Pakistan

ISBN: (纸本)9781665419017

In success or failure of software project, software requirements plays a critical role. Requirement engineering is a human intensive process so the chances of errors, and failure to elicit and specify the right requirements, are more. The software practitioners have to be cautious about what is actually required by the stakeholders and elicit only those features and functionalities rather than some features that may look good but are impractical, and may lead to project failure or timeline delays, without adding much value to the project. In this paper, we introduced a data mining approach to capture user's requirement for a generic software project, which in our case, was a campus management system (CMS). Initially, we started with a set of software Requirement Specification (SRS) documents for similar type of projects done before and we extracted the most frequently appearing requirements which would potentially be the 'Needs' of the stakeholders, using text mining technique. After that, the low frequency requirements were extracted which could potentially be the 'Wants' of some particular stakeholder. Later on, we applied association rule mining to find out links between multiple requirements that led us to the requirement that frequently appeared together, as such links can be useful in identifying requirement dependencies and specification of further requirements. In order to validate the extracted requirements, elicitation sessions in the form of interviews and questionnaires were held with the potential stakeholders of the project and the results of the comparison between the extracted and elicited requirements are discussed at the end of this paper. © 2021 IEEE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Cost-Optimized Microservice Deployment for IoT Application in Cloud-Edge Collaborative Environment

Cost-Optimized Microservice Deployment for IoT Application i...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Xiaoyuan Zhang Bing Tang Qing Yang Wei Xu Feiyan Guo School of Computer Science and Engineering Hunan University of Science and Technology and Hunan Key Laboratory for Service Computing and Novel Software Technology Xiangtan China School of Information and Communication Engineering Guangzhou Maritime University Guangzhou China

With the popularity of cloud native and DevOps, container technology is widely used and combined with microservices. The deployment of container-based microservices in distributed cloud-edge infrastructure requires suitable strategies to ensure the quality of service for users. However, the existing container orchestration tools cannot flexibly select the best deployment location according to the user’s cost budget, and are insufficient in personalized deployment solutions. From the perspective of application providers, this paper considers the location distribution of users, application dependencies, and server price differences, and proposes a genetic algorithm-based Internet-of-Things (IoT) application deployment strategy for personalized cost budgets. The application deployment problem is defined as an optimization problem that minimizes user service latency under cost constraints. This problem is an NP-hard problem, and genetic algorithm is introduced to solve the optimization problem effectively and improve the deployment efficiency. The proposed algorithm is compared with four baseline algorithms, Time-Greedy, Cost-Greedy, Random and PSO, using real datasets and some synthetic datasets. The results show that the proposed algorithm outperforms other competing baseline algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Intent Classification of Nepali Factoid Questions

Intent Classification of Nepali Factoid Questions

引用

Cognitive Computing and Complex Data (ICCD), International Conference on the

作者： Sushil Timilsina Ashim Khadka Jianchu Lin Faculty of Science and Technology Gandaki College of Engineering and Science Pokhara Nepal Faculty of Science and Technology Nepal College of Information Technology Lalitpur Nepal Faculty of Computer and Software Engineer Huaiyin Institute of Technology Jiangsu China

Question Classification plays a vital role in identifying the accurate answer to any question, and is considered as a core component of Question Answering Systems. In Nepali Natural Language Processing, the area of Question Answering has not even been initiated due to a lack of dataset. The dataset of Nepali factual questions has been created by collecting questions from general knowledge books and labelling them with developed taxonomy. The problem of Nepali factoid question classification has been studied with a Support Vector Machine, which works as a baseline classification algorithm and obtained a 0.74 weighted F1-score in the imbalance dataset. The experimental results of the proposed model show the effectiveness of the approach in classifying factoid questions accurately compared with the state-of-the-art approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Blockchain and PUF-based secure key establishment protocol for cross-domain digital twins in industrial Internet of Things architecture

引用

Journal of Advanced Research 2024年 62卷 155-163页

作者： Mahmood, Khalid Shamshad, Salman Saleem, Muhammad Asad Kharel, Rupak Das, Ashok Kumar Shetty, Sachin Rodrigues, Joel J.P.C. School of Psychology and Computer Science University of Central Lancashire Preston United Kingdom Graduate School of Intelligent Data Science National Yunlin University of Science and Technology Yunlin 64002 Taiwan Department of Software Engineering The University of Lahore Lahore 54590 Pakistan Department of Computer Science University of Sahiwal Punjab Sahiwal 57000 Pakistan Center for Security Theory and Algorithmic Research International Institute of Information Technology Hyderabad 500 032 India Department of Modeling Simulation and Visualization Engineering Virginia Modeling Analysis and Simulation Center and Center for Cybersecurity Education and Research Old Dominion University Suffolk 23435 VA United States COPELABS Lusófona University Campo Grande 376 Lisbon 1749-024 Portugal

Introduction: The Industrial Internet of Things (IIoT) is a technology that connects devices to collect data and conduct in-depth analysis to provide value-added services to industries. The integration of the physical and digital domains is crucial for unlocking the full potential of the IIoT, and digital twins can facilitate this integration by providing a virtual representation of real-world entities. Objectives: By combining digital twins with the IIoT, industries can simulate, predict, and control physical behaviors, enabling them to achieve broader value and support industry 4.0 and 5.0. Constituents of cooperative IIoT domains tend to interact and collaborate during their complicated operations. Methods: To secure such interaction and collaborations, we introduce a blockchain-based cross-domain authentication protocol for IIoT. The blockchain maintains only each domain's dynamic accumulator, which accumulates crucial materials derived from devices, decreasing the overhead. In addition, we use the on-chain accumulator to effectively validate the unlinkable identities of cross-domain IIoT devices. Results: The implementation of the concept reveals the fact that our protocol is efficient and reliable. This efficiency and reliability of our protocol is also substantiated through comparison with state-of-the-art literature. In contrast to related protocols, our protocol exhibits a minimum 22.67% increase in computation cost efficiency and a 16.35% rise in communication cost efficiency. Conclusion: The developed protocol guarantees data transfer security across the domain and thwarts IoT devices from potential physical attacks. Additionally, in order to protect privacy, anonymity and unlinkability are also guaranteed. © 2024

关键词： Digital twins Industrial Internet of Things (IIoT) Key agreement Mutual authentication Physically Unclonable Functions (PUFs)

来源：评论

学校读者我要写书评

暂无评论

XRF V2: A Dataset for Action Summarization with Wi-Fi Signals, and IMUs in Phones, Watches, Earbuds, and Glasses

arXiv

引用

arXiv 2025年

作者： Lan, Bo Li, Pei Yin, Jiaxi Song, Yunpeng Wang, Ge Ding, Han Han, Jinsong Wang, Fei School of Software Engineering Xi’an Jiaotong University Shaanxi Xi’an China MOE KLINNS Lab Xi’an Jiaotong University Shaanxi Xi’an China School of Computer Science and Technology Xi’an Jiaotong University Shaanxi Xi’an China College of Computer Science and Technology Zhejiang University Zhejiang Hangzhou China

Human Action Recognition (HAR) plays a crucial role in applications such as health monitoring, smart home automation, and human-computer interaction. While HAR has been extensively studied, action summarization, which involves identifying and summarizing continuous actions, remains an emerging task. This paper introduces the novel XRF V2 dataset, designed for indoor daily activity Temporal Action Localization (TAL) and action summarization. XRF V2 integrates multimodal data from Wi-Fi signals, IMU sensors (smartphones, smartwatches, headphones, and smart glasses), and synchronized video recordings, offering a diverse collection of indoor activities from 16 volunteers across three distinct environments. To tackle TAL and action summarization, we propose the XRFMamba neural network, which excels at capturing long-term dependencies in untrimmed sensory sequences and outperforms state-of-the-art methods, such as ActionFormer and WiFiTAD. We envision XRF V2 as a valuable resource for advancing research in human action localization, action forecasting, pose estimation, multimodal foundation models pre-training, synthetic data generation, and more. Copyright © 2025, The Authors. All rights reserved.

关键词： Wi-Fi

来源：评论

学校读者我要写书评

暂无评论

Free-space Continuous-variable Quantum Secret Sharing

arXiv

引用

arXiv 2025年

作者： Yang, Fangli Chang, Liang Qiu, Daowen Pan, Minghua Xiong, Wanjun Guangxi Key Laboratory of Trusted Software Guilin University of Electronic Technology Guilin541004 China Institute of Quantum Computing and Software School of Computer Science and Engineering Sun Yat-sen University Guangzhou510006 China Guangxi Key Laboratory of Cryptography and Information Security Guilin University of Electronic Technology Guilin541004 China

Free-space quantum cryptography has the potential to enable global quantum communication. However, most existing continuous-variable quantum secret sharing (CV-QSS) schemes rely on fiber channels. In this paper, we present a CV-QSS protocol designed for free-space transmission and construct models of crucial parameters, including channel transmittance, excess noise, and interruption probability, thus deriving the bound of the secret key rate. In particular, we provide a multi-source excess noise model for free-space CV-QSS based on the local local oscillator (LLO) scheme and a straightforward optimization of the noise. Furthermore, our research considers the impact of atmospheric turbulence on the protocol. Simulation results demonstrate that the intensification of atmospheric turbulence adversely affects the aforementioned crucial parameters, leading to a significant reduction in the key rate. However, our protocol shows its capability to securely share secrets over a distance of exceeding 60 km among five participants in the presence of turbulence with Cn2 = 1 × 10−15m−2/3, while maintaining a high key rate of approximately 0.55 bit/pulse over a distance of 10 km across twenty participants. These findings suggest that efficient CV-QSS in free space is indeed achievable. This research may serve as a reference for the design and optimization of the practical CV-QSS system. Copyright © 2025, The Authors. All rights reserved.

关键词： Atmospheric turbulence

来源：评论

学校读者我要写书评

暂无评论

Edge intelligent collaborative privacy protection solution for smart medical

Cyber Security and Applications

引用

Cyber Security and Applications 2023年 1卷

作者： Lai, Jinshan Song, Xiaotong Wang, Ruijin Li, Xiong School of information and software engineering University of Electronic Science and Technology of China Chengdu 611731 China School of Computer Science and Engineering University and Technology of china Chengdu 611731 China

In the era of big data, competent medical care has entered people's lives. However, the existing intelligent diagnosis models have low accuracy and poor universality. At the same time, there is a risk of privacy leakage in the process of health monitoring and auxiliary diagnosis. This paper combines edge computing and federated learning ensure model accuracy and protect patient privacy by proposing an Edge intelligent collaborative privacy protection solution for smart medical (EICPP). First, we offer a lightweight edge intellectual collaborative federated learning framework named KubeFL to support health monitoring and auxiliary diagnosis;secondly, we design a federated learning training model based on device-edge-cloud layering, with complete accuracy of up to 95.8%;Finally, a differential privacy algorithm for edge-cloud model transmission is proposed, which can exchange a lower accuracy loss for solid privacy protection. © 2022

关键词： Differential privacy Edge intelligent collaboration Privacy protection Smart medical care

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：