检索结果-内蒙古大学图书馆

Privacy-Preserving Node Classification in Customer Services With Federated Graph Neural Networks

IEEE Transactions on Consumer Electronics 2024年第1期71卷 630-642页

作者： Zengyi Huang Min Tang Yuxing Wei Guoqiang Deng School of Mathematics and Computing Science Guangxi Colleges and Universities Key Laboratory of Data Analysis and Computation and the Center for Applied Mathematics of Guangxi Guilin University of Electronic Technology Guilin China Guangxi Key Laboratory of Digital Infrastructure Guangxi Zhuang Autonomous Region Information Center Nanning China

As the Internet of Things progresses, the volume of information stored in electronic devices has surged dramatically. Employing Graph Convolutional Networks (GCNs) to model graph data derived from link relationships has led to widespread applications in consumer electronics, such as user preference analysis and personalized recommendations. However, with practical graph data scattered among various owners, traditional centralized GCN methods falter owing to privacy constraints. Thus, creating a distributed GCN framework that upholds model quality and user privacy remains a daunting task. In this paper, we pioneer the use of functional encryption in a federated learning GCN framework, termed FPGCN. This innovative technique achieves performance parity with centralized GCNs, capable of producing equivalent node representations without the need for direct access to raw data. By employing a hierarchical split learning framework coupled with privacy-preserving aggregation mechanisms, it enables secure and collaborative multi-party GCN training, ensuring confidentiality while maintaining model efficacy. Comprehensive experimental results in three real-world datasets demonstrate the capacity of FPGCN to match the predictive accuracy observed in centralized scenarios, while also showcasing its performance efficiency.

关键词： Data privacy Privacy Training Accuracy Consumer electronics Cryptography Data models Protection Federated learning Distributed databases

来源：评论

学校读者我要写书评

暂无评论

Buck Boost Converter Control in an IoT-Based Wind System Using Supervised Learning Technique 1

Buck Boost Converter Control in an IoT-Based Wind System Usi...

引用

1st International Conference on Innovative Sustainable Technologies for Energy, Mechatronics and Smart Systems, ISTEMS 2024

作者： Anbuselvan, N. Hemalatha, S. Lakshminarayanan, Suresh Sivanantham, E. Mohankumar, N. Thamizhamuthu, R. Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Department of Electrical and Electronics Engineering Tamil Nadu Chennai India Tagore Engineering College Department of Artificial Intelligence and Data Science Tamil Nadu Chennai India University of Technology and Applied Sciences - Almusanna Oman Department of Engineering and Electronics South Al Batina Oman Rajalakshmi Institute of Technology Department of Electronics and Communication Engineering Tamil Nadu Chennai India B.V Raju Institute of Technology Department of Electronics and Communication Engineering Telangana India Srm Institute of Science and Technology Kattankulathur Campus-Chengalpattu Department of Computing Technologies Tamil Nadu Chennai India

ISBN: (纸本)9798350384246

In recent years, distributed energy resources (DERs) have gained significance as a way of introducing a substantial quantity of renewable energy sources (RESs) into power grids. Wind turbines are accessible in windy areas, giving wind energy systems (WES) a realistic alternative for clients. This work attempts to increase the effectiveness and adaptability of WES by presenting a novel way of managing DC-DC buck-boost converters. The suggested method combines an Internet of Things (IoT) system for monitoring with supervised learning algorithms to make energy conversion more stable, efficient, and able to adapt in real time to changing wind conditions. In this research, creating a reliable supervised learning control method is the primary goal. The second goal is to optimize the most important parameters of the converter. Using the new supervised learning algorithm, the study changes variables like duty cycle, switching frequency, and inductance to get the best results based on past performance data and how the system is working now. It investigates the influence of these parameters on overall system efficiency and stability. The incorporation of an IoT monitoring system into the WES is an essential component of the study. Various sensors monitor variables such as wind speed, converter input and output voltages, and currents in real-time and are shown as results. © 2024 IEEE.

关键词： Buck-Boost converter

来源：评论

学校读者我要写书评

暂无评论

L-Arginine Supplementation Mitigates Dichlorvos-Induced Haematocardiotoxicity, and Oxidative Stress in Male Wistar Rats

引用

Open Journal of applied Sciences 2024年第7期14卷 1886-1903页

作者： Waidi Adeoye Saka Yusuff Dimeji Igbayilola Jabba Hamidu Lawan Taoheed Kolawole Muftaudeen Ridwanullahi Adejumo Tolulope Deborah Alu Mary Ikuomola Joshua Tinuade Ojelere Victor Odufa Adegoke Department of Physiology College of Health Sciences Ladoke Akintola University of Technology Ogbomoso Oyo State Nigeria Department of Human Physiology College of Medicine and Health Sciences Baze University Abuja Nigeria Department of Biological Sciences Faculty of Computing and Applied Sciences Baze University Abuja Nigeria

Due to its toxicity, dichlorvos—a common organophosphate pesticide—poses significant risks to human health. This study utilized male Wistar rats to explore the potential protective effects of L-arginine supplementation against dichlorvos-induced toxicity, focusing on cardiotoxicity, haematotoxicity and oxidative stress. The rats were divided into four groups: Control, L-arginine (L), Dichlorvos (D), and L-arginine + Dichlorvos (L + D). Dichlorvos was administered to the D group, L-arginine (100 mg/kg) to the L group, and both L-arginine and dichlorvos to the L + D group. The study evaluated various parameters, including cardiovascular, oxidative stress markers, and haematological indices. Significant changes in haematological parameters such as haemoglobin (Hb), haematocrit (HCT), and red blood cell count (RBC) indicated haematotoxicity after dichlorvos administration. Additionally, elevated cardiac markers, including lactate dehydrogenase (LDH) and creatine kinase-MB (CK-MB), suggested cardiotoxic effects. Exposure to dichlorvos also resulted in decreased antioxidant enzyme levels and increased oxidative stress indicators like malondialdehyde (MDA). Remarkably, L-arginine supplementation mitigated the damage caused by dichlorvos. It normalized the altered haematological parameters, demonstrating its protective effect against haematotoxicity. The rise in cardiac markers was reduced with L-arginine supplementation, indicating protection against cardiotoxicity. Moreover, L-arginine significantly decreased oxidative stress, as evidenced by lower MDA levels and restored antioxidant enzyme activity. In conclusion, L-arginine supplementation in male Wistar rats showed promising protective effects against dichlorvos-induced cardiotoxicity, haematotoxicity and oxidative stress. This suggests that L-arginine may offer a beneficial intervention to mitigate the adverse effects of dichlorvos on blood and heart health, paving the way for potential treatments for pesticide poison

关键词： Dichlorvos L-Arginine Cardiovascular Function Haematological Parameters Oxidative Stress

来源：评论

学校读者我要写书评

暂无评论

A Neurobehavioral Evaluation of the Efficacy of 1mA Longitudinal, Anodal TDCS on Multitasking and Transfer Performance

A Neurobehavioral Evaluation of the Efficacy of 1mA Longitud...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Akash K Rao Shashank Uttrani Darshil Shah Vishnu K Menon Arnav Bhavsar Shubhajit Roy Chowdhury Ramsingh Negi Varun Dutt Manipal Academy of Higher Education Applied Cognitive Science Laboratory Indian Institute of Technology Mandi School of Computing and Electrical Engineering Indian Institute of Technology Mandi Cognitive Control and Machine Learning Group at the Institute of Nuclear Medicine and Allied Sciences Defence Research and Development Organization

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Multitasking requires rapid switching of attention and cognitive resources between different tasks in a dynamic environment, relying on cognitive processes, such as working memory, executive control, and selective attention. Although studies have investigated the efficacy of various neurobehavioral interventions in improving multitasking capabilities, the effects of longitudinal anodal transcranial direct current stimulation (tDCS) in enhancing multitasking performance have not been investigated. This research investigated the efficacy of 1mA anodal tDCS administered longitudinally on multitasking performance. 42 participants were randomly and equally divided into the experimental and placebo control conditions in this study conducted for 10 days. All participants executed two multitasking tasks on day 1 and received 1mA anodal/placebo tDCS during task training from day 2 to day 8. Various behavioral and neurophysiological measures have been measured. The findings revealed that tDCS had the propensity to augment multitasking capabilities in the trained task but had limited transfer capabilities. EEG-based brain connectivity analysis also revealed the formation of network hubs in the prefrontal and frontal regions, indicating enhanced cortical activation in the beta band. We intend to use these findings to design interventional frameworks to enhance multitasking performance using tDCS.

关键词： Training Atmospheric measurements Memory management Switches Multitasking Particle measurements Dynamic scheduling Control systems Transcranial direct current stimulation Cybernetics

来源：评论

学校读者我要写书评

暂无评论

Who should I trust? A Visual Analytics Approach for Comparing Net Load Forecasting Models

arXiv

引用

arXiv 2024年

作者： Bhattacharjee, Kaustav Kundu, Soumya Chakraborty, Indrasis Dasgupta, Aritra Department of Data Science New Jersey Institute of Technology United States Optimization and Control Group Pacific Northwest National Laboratory United States Center for Applied Scientific Computing Lawrence Livermore National Laboratory United States

Net load forecasting is crucial for energy planning and facilitating informed decision-making regarding trade and load distributions. However, evaluating forecasting models' performance against benchmark models remains challenging, thereby impeding experts' trust in the model's performance. In this context, there is a demand for technological interventions that allow scientists to compare models across various timeframes and solar penetration levels. This paper introduces a visual analytics-based application designed to compare the performance of deep-learning-based net load forecasting models with other models for probabilistic net load forecasting. This application employs carefully selected visual analytic interventions, enabling users to discern differences in model performance across different solar penetration levels, dataset resolutions, and hours of the day over multiple months. We also present observations made using our application through a case study, demonstrating the effectiveness of visualizations in aiding scientists in making informed decisions and enhancing trust in net load forecasting models. © 2024, CC BY-NC-SA.

关键词： Visual analytics

来源：评论

学校读者我要写书评

暂无评论

Double Threshold based Optimal Device Selection Scheme for D2D or Sidelink Network

arXiv

引用

arXiv 2022年

作者： Kumarapandian, Shamganth Ahmed, Qasim Zeeshan Khan, Faheem A. Department of Engineering University of Technology and Applied Sciences Ibra Oman School of Computing and Engineering University of Huddersfield Huddersfield United Kingdom

Device-to-device (D2D) or Sidelink aided communication is regarded as one of the most promising technologies to improve the spectral efficiency of the 5G and beyond communication system. However, two main challenges exist: 1) the selection of the optimal number of devices for improving the spectral efficiency, and 2) improving the physical layer security of such a communication system. The optimal device improves the secrecy capacity, and the selection of optimal devices enhances the physical layer security. Therefore, in this paper, we propose a double threshold-based optimal device selection (ODS) scheme for a cooperative wireless network with amplify and forward (AF) protocol in the presence and absence of an eavesdropper to enhance the physical layer security for the D2D network. The proposed scheme is analyzed with different distance cases, device scenarios, and modulation schemes. The bit error rate (BER) performance analysis concludes that a performance gain of more than 4 dB is achieved at the BER of 0.004 for the proposed double threshold-based ODS scheme compared to the existing ODS scheme at a high signal to noise ratio (SNR). Furthermore, the proposed scheme enhances the physical layer security. Copyright © 2022, The Authors. All rights reserved.

关键词： Cooperative communication

来源：评论

学校读者我要写书评

暂无评论

Reflecting on a community of practice for engineering education research capacity in Africa: who are we and where are we going?

引用

Australasian Journal of Engineering Education 2023年第1期28卷 74-84页

作者： Matemba, Esther Smith, Lelanie Wolff, Karin Inglis, Helen Mogashana, Disaapele Jansen, Lauren Gwynne-Evans, Alison Campbell, Anita L. Kwuimy, Cedrick Nassar, Shamim Magara, Irene Kloot, Bruce Hattingh, Teresa Raji, Atanda Musa, Tagwa Nyamapfene, Abel School of Civil and Mechanical Engineering Curtin University Perth Australia Faculty of Engineering Built Environment and Information Technology University of Pretoria Pretoria South Africa Faculty of Engineering Stellenbosch University Stellenbosch South Africa Faculty of Engineering and the Built Environment University of Cape Town Cape Town South Africa Department of Engineering and Computing Education University of Cincinnati Cincinnati United States Department of Electrical Electronic and Information Engineering South Eastern Kenya University Kitui Kenya Faculty of Applied Sciences and Technology Mbarara University of Science and Technology Mbarara Uganda Faculty of Engineering and the Built Environment University of Johannesburg Johannesburg South Africa Faculty of Engineering and the Built Environment Cape Peninsula University of Technology Cape Town South Africa Department of Petroleum Engineering Sudan University of Science and Technology Khartoum Sudan Faculty of Engineering Sciences University College London London United Kingdom

The Engineering Education Research Network in Africa (EERN-Africa) was created to enable connections between practitioners and researchers with a shared interest in African engineering education contexts. Recognising the importance of developing an African voice in the engineering education research space, the EERN-Africa community has interacted in a dynamic and dialogic way with our own teaching and research practices across diverse African contexts, with an ethical commitment to democratic and inclusive community-building. The objective of this paper is to reflect on the current status of the Community of Practice (CoP), and the challenges and opportunities in sustaining and growing the CoP. A collaborative analysis of perspectives on this emerging identity is presented, using an Appreciative Inquiry (AI) methodology and drawing on collective written reflections and discussions. Six broad themes on the value that the CoP has for both individuals and the group were identified: networking, capacity development, emotional support, impact on professional identity, social and environmental impact, and breaking borders. This paper contributes an approach for collaborative capacity-building in EER through a virtual CoP, underpinned by the spirit of ubuntu. © 2023 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.

关键词： Environmental impact

来源：评论

学校读者我要写书评

暂无评论

Evaluation of a Digital Tracking Calorimeter for In-Situ Range Verification during Particle Therapy

Evaluation of a Digital Tracking Calorimeter for In-Situ Ran...

引用

IEEE Symposium on Nuclear Science (NSS/MIC)

作者： Alexander Schilling Ralf Keidel Nicolas R. Gauger Center for Technology and Transfer University of Applied Sciences Worms Worms Germany Chair for Scientific Computing TU Kaiserslautern Kaiserslautern Germany

When protons or heavier ions are used for radiation treatment, it is paramount to assure quality by performing range verification during or right after treatment. This work presents, for the first time, a feasibility study for proton therapy range verification based on secondary charged particles using the digital tracking calorimeter designed by the Bergen pCT collaboration. Additionally, we compare the precision achievable with protons and carbon ions, by applying regression models to predict the beam range with Monte Carlo-simulated data. The simulated treatment scenario contains a water cuboid phantom of different thicknesses, with protons and carbon ions as treatment modality at different medically relevant energy levels. Results show that the error for carbon ions is lower despite having 100 times fewer primaries simulated, due to the much higher readout yield. The lowest mean absolute error was observed with a kernel regression as 0.27 ± 0.04 mm for protons, and with a Gaussian process as 0.18 ± 0.02 mm for carbon ions, which shows feasibility of range verification for proton and carbon therapy based on charged secondary particles using the digital tracking calorimeter.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimizing Handwritten Numeral Recognition for English and Devanagari Using MNIST and CPAR Data 7

Optimizing Handwritten Numeral Recognition for English and D...

引用

7th International Symposium on Innovative Approaches in Smart Technologies, ISAS 2023

作者： Singh, Kamred Udham Kumar, Ankit Kumar, Gaurav Singh, Teekam Choudhury, Tanupriya Kotecha, Ketan Graphic Era Hill University School of Computing Dehradun India GLA University Department of Computer Engineering & Applications UP Mathura India Graphic Era Deemed to Be University Dehradun Department of Computer Science and Engineering India Symbiosis Institute of Technology CSE Dept. Lavale Campus Pune India Symbiosis Centre for Applied Artificial Intelligence Pune India

ISBN: (纸本)9798350383065

In this paper, a technique for the categorization of offline handwritten digits in the Devanagari script as well as the Roman script (English numbers) is presented. Finding out how to get the best possible recognition results while concurrently working with several scripts is the primary purpose of this study. The approach that has been described makes use of an easy profiling method for the extraction of features, together with an innovative implementation of Linear Discriminant Analysis (LDA), and a neural network architecture that has been adapted specifically for numeral classification. An exhaustive series of trials including 36,000 examples of handwritten numerals were carried out as part of the evaluation of the effectiveness of this approach. These samples were chosen at random from the CPAR datasets, with 22,000 being put to use in the construction of the training set and the remaining 14,000 being assigned to the role of the test set. In addition, the well-known MNIST database was used, which provided 60,000 samples for training purposes and 10,000 samples specifically for testing. It was determined via thorough testing that the LDA classifier produced variable results. These varying results are essential in emphasising the success of the method as well as possible areas for improvement for the method. According to the results, this strategy, which combines profile-based feature extraction with advanced classification algorithms, has the potential to lead to major breakthroughs in the area of handwritten number identification. © 2023 IEEE.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Probing the Robustness of Vision-Language Pretrained Models: A Multimodal Adversarial Attack Approach

arXiv

引用

arXiv 2024年

作者： Guan, Jiwei Ding, Tianyu Cao, Longbing Pan, Lei Wang, Chen Zheng, Xi School of Computing Macquarie University Sydney Australia Applied Sciences Group Microsoft Corporation Redmond United States School of Information Technology Deakin University Waurn Ponds Australia Data61 CSIRO Sydney Australia

Vision-language pretraining (VLP) with transformers has demonstrated exceptional performance across numerous multimodal tasks. However, the adversarial robustness of these models has not been thoroughly investigated. Existing multimodal attack methods have largely overlooked cross-modal interactions between visual and textual modalities, particularly in the context of cross-attention mechanisms. In this paper, we study the adversarial vulnerability of recent VLP transformers and design a novel Joint Multimodal Transformer Feature Attack (JMTFA) that concurrently introduces adversarial perturbations in both visual and textual modalities under white-box settings. JMTFA strategically targets attention relevance scores to disrupt important features within each modality, generating adversarial samples by fusing perturbations and leading to erroneous model predictions. Experimental results indicate that the proposed approach achieves high attack success rates on vision-language understanding and reasoning downstream tasks compared to existing baselines. Notably, our findings reveal that the textual modality significantly influences the complex fusion processes within VLP transformers. Moreover, we observe no apparent relationship between model size and adversarial robustness under our proposed attacks. These insights emphasize a new dimension of adversarial robustness and underscore potential risks in the reliable deployment of multimodal AI systems. Copyright © 2024, The Authors. All rights reserved.

关键词： Generative adversarial networks

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：