检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Wang, Fang Al Hamadi, Hussam Damiani, Ernesto C2PS Department of Electrical Engineering and Computer Science Khalifa University Abu Dhabi United Arab Emirates College of Engineering and IT University of Dubai Dubai United Arab Emirates

Malware visualization analysis incorporating with Machine Learning (ML) has been proven to be a promising solution for improving security defenses on different platforms. In this work, we propose an integrated framework for addressing common problems experienced by ML utilizers in developing malware detection systems. Namely, a pictorial presentation system with extensions is designed to preserve the identities of benign/malign samples by encoding each variable into binary digits and mapping them into black and white pixels. A conditional Generative Adversarial Network based model is adopted to produce synthetic images and mitigate issues of imbalance classes. Detection models architected by Convolutional Neural Networks are for validating performances while training on datasets with and without artifactual samples. Result demonstrates accuracy rates of 98.51% and 97.26% for these two training scenarios. © 2024, CC BY.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Semantic Segmentation with Attention Dense U-Net for Lung Extraction from X-ray Images

Semantic Segmentation with Attention Dense U-Net for Lung Ex...

引用

International Conference on Electrical engineering and Information & Communication Technology (ICEEICT)

作者： Akib Al Mahmud Auvy Rafiatul Zannah Mahbub-E-Elahi Shezhan Sharif Washik Al Mahmud Jannatun Noor Department of Computer Science and Engineering Computing for Sustainability and Social Good (C2SG) Research Group School of Data and Sciences BRAC University Dhaka Bangladesh

ISBN: (数字)9798350385779

ISBN: (纸本)9798350385786

Deep learning and digital image processing are crucial in medical imaging research. Lung segmentation is particularly challenging, demanding accurate differentiation of complex structures, sophisticated algorithms, and deep learning models for reliable results. In our research, We used the Shen-zhen chest X-ray dataset, comprising 566 frontal chest X-rays focused on pulmonary tuberculosis. This dataset, compiled by the Guangdong Medical College and Shenzhen No. 3 People's Hospital, was released by the United States National Library of Medicine. Images, captured using a Philips DR Digital Diagnostic system, were resized from $3000 \times 3000$ pixels to $512 \times 512$ pixels for computer-aided diagnosis research. We initially used the Attention Dense U-Net to extract lungs from chest X-rays, leveraging attention mechanisms to focus on relevant features and dense blocks to improve feature reuse. Our goal is to assess its performance for chest X-ray segmentation, comparing it with other deep learning models due to limited research in this area. So, the model is compared with four other variants of U-Net architectures to segment lung pixels from an X-ray image. After implementing the approach using a benchmark dataset and comparing it to other existing architectures, we present that Attention Dense U-Net gives the best accuracy for all given parameters, with a result of accuracy: 97.48%, Dice coefficient: 94.87%, and IoU: 93.87%.

关键词： Deep learning Tuberculosis Semantic segmentation Lung computer architecture Feature extraction Libraries

来源：评论

学校读者我要写书评

暂无评论

Guest Editorial to the Special Issue Public Transport Optimization: From Theory to Practice

引用

Operations Research Forum 2024年第3期5卷 73页

作者： Cacchiani, Valentina Müller-Hannemann, Matthias Rojas-Marcos, Federico Perea Department of Electrical Electronic and Information Engineering “Guglielmo Marconi” University of Bologna Viale Risorgimento 2 Bologna 40136 Italy Institute for Computer Science Martin Luther University Halle-Wittenberg Von-Seckendorff-Platz 1 Halle D 06120 Germany Department of Applied Mathematics II and Institute of Mathematics (IMUS) University of Seville Avda. Reina Mercedes s/n Seville 41012 Spain

来源：评论

学校读者我要写书评

暂无评论

Robust Active Learning (RoAL): Countering Dynamic Adversaries in Active Learning with Elastic Weight Consolidation

arXiv

引用

arXiv 2024年

作者： Fajri, Ricky Maulana Pei, Yulong Yin, Lu Pechenizkiy, Mykola Department of Mathematics and Computer Science Groene Loper 3 North Brabant Eindhoven5612 AE Netherlands School of Computer Science and Electronic Engineering Address Stag Hill University Campus Guildford Surrey GuildfordGU2 7XH United Kingdom

Despite significant advancements in active learning and adversarial attacks, the intersection of these two fields remains underexplored, particularly in developing robust active learning frameworks against dynamic adversarial threats. The challenge of developing robust active learning frameworks under dynamic adversarial attacks is critical, as these attacks can lead to catastrophic forgetting within the active learning cycle. This paper introduces Robust Active Learning (RoAL), a novel approach designed to address this issue by integrating Elastic Weight Consolidation (EWC) into the active learning process. Our contributions are threefold: First, we propose a new dynamic adversarial attack that poses significant threats to active learning frameworks. Second, we introduce a novel method that combines EWC with active learning to mitigate catastrophic forgetting caused by dynamic adversarial attacks. Finally, we conduct extensive experimental evaluations to demonstrate the efficacy of our approach. The results show that RoAL not only effectively counters dynamic adversarial threats but also significantly reduces the impact of catastrophic forgetting, thereby enhancing the robustness and performance of active learning systems in adversarial environments. © 2024, CC BY.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Augmenting Cybersecurity in WSN: AI-Based Clone Attacks Recognition Framework

Augmenting Cybersecurity in WSN: AI-Based Clone Attacks Reco...

引用

Communication and Networks (ASIANComNet), Asian Conference on

作者： Seelam Ch Vijaya Bhaskar Gedela Kalyani Ramy Al-Fatlawy Fatima Alsalamy Waleed Hadi Madhloom Kurdi H.M. Al-Aboudy G. Sujatha Department of IT MVSR Engineering College Hyderabad Telangana India Big Data Analytics Karpaga Vinayaga College of Engineering and Technology Chengalpattu Tamil Nadu India Department of Computer Technical Engineering College of Technical Engineering The Islamic University Najaf Iraq Medical Laboratories Techniques Department Al-Mustaqbal University Hillah Iraq Department of Computer Science Altoosi University College 2 Iraq Department of Computer Techniques Engineering Mazaya University College DhiQar Iraq Department of ECE Arunai Engineering College Tiruvannamalai Tamil Nadu India

ISBN: (数字)9798350367003

ISBN: (纸本)9798350367225

Applications such as industrial automation, healthcare, and environmental monitoring need the use of wireless sensor networks (WSNs). However, due to their dispersed organizational makeup, they have become vulnerable to security risks, particularly clone assaults. To protect confidentiality, availability, and confidentiality, several attacks must be recognized and prevented. This project aims to offer an effective method for identifying and averting clone assaults. To identify cloned both nationally and internationally use a low-cost verification process. In this study, we offer a new adaptive sea-horse optimized light gradient boosting machine (ASHO-LGBM) technique for protecting the network against node identity duplicates. The ASHO approach is used in the ASHO-LGBM framework to improve the recognition accuracy of the light gradient boosting machine (LGBM) characteristics. The replications with the nodes intrusion detection (ID) are used to choose a most trustworthy communication mode. The procedure is intended to be implemented and used for gathering data through an internet component. Using a Python tool, the suggested technique is simulated and its delay, packet delivery ratio, packet drop, and energy are evaluated. When compared to other approaches, the study’s results show that the ASHO-LGBM strategy’s performance analysis achieves the highest accuracy rate.

关键词： Wireless sensor networks Accuracy Cloning Intrusion detection Medical services Boosting Delays Performance analysis Environmental monitoring Manufacturing automation

来源：评论

学校读者我要写书评

暂无评论

Nanoscale manipulating plasmonic silver adatoms for dynamic light modulation 27

Nanoscale manipulating plasmonic silver adatoms for dynamic ...

引用

Ultrafast Phenomena and Nanophotonics XXVII 2023

作者： Zhang, Wu Li, Haizeng Elezzabi, Abdulhakem Y. Ultrafast Optics and Nanophotonics Laboratory Department of Electrical and Computer Engineering University of Alberta EdmontonABT6G 2V4 Canada Optics and Thermal Radiation Research Center Institute of Frontier & Interdisciplinary Science Shandong University Qingdao266237 China

ISBN: (纸本)9781510659438

Plasmonic colors have gained significant interest for flat panel displays due to their broad color gamut and high subwavelength resolution. The reversible metal deposition, having tunable nanostructures, along with their localized surface plasmon resonance (LSPR), is considered as a promising strategy for dynamic color displays. Herein, a demonstration of the manipulation of plasmonic silver adatoms through reversible metal deposition is presented for dynamic light modulation. The voltage-activated reversible silver nanoparticles deposition enables a wide range of dynamic plasmonic color change of 100 nm, and also facilitates a size and shape control of the grown silver nanoparticles. The silver nanoparticles interact with visible light through LSPR, the size and shape of the particles affect their optical properties. Our findings provide a favorable and novel platform for low energy-consumption tunable photonic and nanoplasmonic devices, as well as provide a simple and reliable process for rapid, scalable, and green preparation of tunable plasmonic Ag nanoparticles. © 2023 SPIE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Handoff and Deposit: Designing Temporal Coordination in Cross-Device Transfer Techniques for Mixed-Focus Collaboration

引用

Proceedings of the ACM on Human-computer Interaction 2022年第CSCW2期6卷 1-23页

作者： Homaeian, Leila Wallace, James R. Scott, Stacey D. School of Public Health and Health Systems University of Waterloo WaterlooONN2L 3G1 Canada School of Computer Science University of Guelph GuelphONN1G 2W1 Canada Department of Systems Design Engineering University of Waterloo WaterlooONN2L 3G1 Canada

When working together, people frequently share information with each other to enable division of labour, assistance, and delegation of responsibility. The literature has explored both synchronous and asynchronous transfer techniques, known as Handoff and Deposit, respectively. However, current cross-device environments tend to only provide a single mechanism. Moreover, we have little understanding of the impact of different techniques on collaborative process. To understand how Handoff and Deposit may be designed to support complex sensemaking tasks, we followed a Research through Design process to iteratively design Handoff and Deposit techniques using paper and digital sketches and high-fidelity prototypes. We consulted the HCI literature to corroborate our findings with studies and descriptions of existing cross-device transfer designs and to understand the potential impact of those designs on mixed-focus collaboration. We learned that as we move away from a restricted physical workspace and leverage the flexibility of digital personal devices, there is a large design space for realizing cross-device transfer. To inform these designs, we provide five design considerations for cross-device transfer techniques: Transfer Acceptance, Action Dependencies, Immediate Usability, Interruption Potential, and Connection Actions. © 2022 ACM.

关键词： Design

来源：评论

学校读者我要写书评

暂无评论

Multi-view Unsupervised Representation Learning via Integration of Fuzzy Rules and Graph-Based Adaptive Regularization

引用

IEEE Transactions on Fuzzy Systems 2025年

作者： Zhu, Yi Li, Dong Xi, Chao Pedrycz, Witold Macau University of Science and Technology School of Computer Science and Engineering China East China University of Technology School of Mechanical and Electronic Engineering Nanchang330013 China Gliwice Department of Measurement and Control Systems Gliwice44-100 Poland University of Alberta Department of Electrical and Computer Engineering EdmontonABT6G 2R3 Canada Istinye University Research Center of Performance and Productivity Analysis Istanbul34010 Turkey

With the rapid advancement of data acquisition technologies, multiview data have been widely applied in fields such as social networks, computer vision, and natural language processing. Multiview data typically contain information arising from different views or sensors, offering more perspectives for observation. The multiview nature also brings challenges, such as high dimensionality, noise, heterogeneity, and redundancy. Particularly, in scenarios with limited labeled data, traditional single-view learning methods often struggle to handle these complex issues. To address this, this article proposes an unsupervised multiview learning framework that integrates Takagi–Sugeno–Kang fuzzy systems and graph-based adaptive regularization (MvTSK-GAR) to handle the heterogeneity and redundancy in multiview data effectively. Specifically, this article first captures the uncertainty in multiview data through fuzzy rules and models the structural relationships between the data using graph-based adaptive regularization. The framework does not rely on a large amount of labeled data. Instead, it integrates complementary information coming from different views to automatically mine latent patterns, thus generating more accurate and stable data representations. Experimental results demonstrate that the proposed framework performs well in various real-world applications, particularly excelling in high-dimensional data processing and noise reduction. Good performance in multiple publicly available datasets validates the effectiveness of our approach. Thecode is available at https://***/r/MvTSK-GAR-E3FB/***. © 1993-2012 IEEE.

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

DrivAerNet: A Parametric Car Dataset for Data-Driven Aerodynamic Design and Prediction

引用

Journal of Mechanical Design 2025年第4期147卷 041712页

作者： Elrefaie, Mohamed Dai, Angela Ahmed, Faez Department of Mechanical Engineering https://***/042nb2s44Massachusetts Institute of Technology Cambridge MA 02139 Department of Computer Science https://***/02kkvpp62Technical University of Munich Garching 85748 Germany Department of Mechanical Engineering Massachusetts Institute of Technology Cambridge MA 02139

This study introduces DrivAerNet, a large-scale high-fidelity CFD dataset of 3D industry-standard car shapes, and RegDGCNN, a dynamic graph convolutional neural network model for regression, both aimed at aerodynamic car design through machine learning. DrivAerNet, with its 4000 detailed 3D car meshes using 0.5 million surface mesh faces and comprehensive aerodynamic performance data comprising of full 3D pressure, velocity fields, and wall-shear stresses, addresses the critical need for extensive datasets to train deep learning models in engineering applications. It is 60% larger than the previously available largest public dataset of cars and is the only open-source dataset that also models wheels and underbody. RegDGCNN leverages this large-scale dataset to provide high-precision drag estimates directly from 3D meshes, bypassing traditional limitations such as the need for 2D image rendering or signed distance fields (SDFs). By enabling fast drag estimation in seconds, RegDGCNN facilitates rapid aerodynamic assessments, offering a substantial leap toward integrating data-driven methods in automotive design. Together, DrivAerNet and RegDGCNN promise to accelerate the car design process and contribute to the development of more efficient cars. To lay the groundwork for future innovations in the field, the dataset and code used in our study are publicly accessible.

关键词： Turbulence creativity and concept generation Simulation Aerodynamics simulation-based design design evaluation design automation Design machine learning Drag (Fluid dynamics) Shapes Deep learning Modeling Machine learning computer-aided design Computational fluid dynamics product design conceptual design data-driven design design of experiments Metamodeling Pressure design representation artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Average Consensus over Directed Networks in Open Multi-Agent Systems with Acknowledgement Feedback

arXiv

引用

arXiv 2024年

作者： Makridis, Evagoras Grammenos, Andreas Oliva, Gabriele Kalyvianaki, Evangelia Hadjicostis, Christoforos N. Charalambous, Themistoklis Department of Electrical and Computer Engineering School of Engineering University of Cyprus Aglantzia Nicosia2109 Cyprus Department of Computer Science and Technology University of Cambridge CambridgeCB2 1TN United Kingdom Department of Engineering University Campus Bio-Medico of Rome Via Alvaro del Portillo Roma21–00128 Italy

In this paper, we address the distributed average consensus problem over directed networks in open multi-agent systems (OMAS), where the stability of the network is disrupted by frequent agent arrivals and departures, leading to a time-varying average consensus target. To tackle this challenge, we introduce a novel ratio consensus algorithm (OPENRC) based on acknowledgement feedback, designed to be robust to agent arrivals and departures, as well as to unbalanced directed network topologies. We demonstrate that when all active agents execute the OPENRC algorithm, the sum of their state variables remains constant during quiescent epochs when the network remains unchanged. By assuming eventual convergence during such quiescent periods following persistent variations in system composition and size, we prove the convergence of the OPENRC algorithm using column-stochasticity and mass-preservation properties. Finally, we apply and evaluate our proposed algorithm in a simulated environment, where agents are departing from and arriving in the network to highlight its resilience against changes in the network size and topology. © 2024, CC BY.

关键词： Consensus algorithm

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：