检索结果-内蒙古大学图书馆

Federated Learning With Client Clustering Selection and Quality-Aware Model Aggregation(2024)

IEEE Internet of Things Journal 2025年

作者： Peng, Y. Wang, C. Shi, H. Ma, R. Guan, H. Yang, Hanbo Shanghai Jiao Tong University Department of Computer Science and Engineering Shanghai China Beijing Simulation Center National Key Laboratory of Modeling and Simulation for Complex Systems Beijing China

The Industrial Internet of Things (IIoT) is revolutionizing industries through device interconnectivity, enabling real-time data collection and transmission for enhanced monitoring, control, and automation. This has led to improvements in predictive maintenance, production optimization, and supply chain management. The integration of machine learning (ML) and deep learning (DL) within IIoT has been accelerated by increased data availability, computational advancements, and algorithmic innovations, with applications ranging from image processing to autonomous vehicles. Foundation models, such as ChatGPT, are becoming prevalent in IIoT for their capabilities in natural language processing and computer vision. However, the growth of IIoT and foundation models presents challenges, including data volume, real-time processing requirements, computational costs, and security vulnerabilities. Federated learning (FL) addresses these issues by allowing distributed model training without raw data transfer, enhancing privacy and security. FL is particularly beneficial for IIoT’s decentralized architecture and real-time decision-making needs. Despite the advantages, FL faces challenges such as data heterogeneity and communication overhead. To overcome these, we propose a federated learning framework, Fed-CCSQMA, which includes client selection and model aggregation modules to mitigate data heterogeneity’s impact. The client selection module uses Principal Component Analysis (PCA) and clustering to select clients with diverse yet representative data, while the model aggregation module assigns weights based on model accuracy to ensure faster global model convergence. We test our proposed framework on FMNIST and CIFAR-10 datasets, with accuracy surpassing baseline methods and faster convergence, demonstrating an improvement in overall generalizability and learning efficiency. © 2014 IEEE.

关键词： Client Selection Clustering Federated Learning Model Aggregation

来源：评论

学校读者我要写书评

暂无评论

Visual Episodic Memory-based Exploration 36th

Visual Episodic Memory-based Exploration

引用

36th International Florida Artificial Intelligence Research Society Conference, FLAIRS-36 2023

作者： Vice, Jack Ruiz-Sanchez, Natalie Douglas, Pamela K. Sukthankar, Gita Dept of Computer Science University of Central Florida OrlandoFL United States Dept. of ECE University of Central Florida OrlandoFL United States Dept. of Modeling and Simulation University of Central Florida OrlandoFL United States

In humans, intrinsic motivation is an important mechanism for open-ended cognitive development;in robots, it has been shown to be valuable for exploration. An important aspect of human cognitive development is episodic memory which enables both the recollection of events from the past and the projection of subjective future. This paper explores the use of visual episodic memory as a source of intrinsic motivation for robotic exploration problems. Using a convolutional recurrent neural network autoencoder, the agent learns an efficient representation for spatiotemporal features such that accurate sequence prediction can only happen once spatiotem-poral features have been learned. Structural similarity between ground truth and autoencoder generated images is used as an intrinsic motivation signal to guide exploration. Our proposed episodic memory model also implicitly accounts for the agent's actions, motivating the robot to seek new interactive experiences rather than just areas that are visually dissimilar. When guiding robotic exploration, our proposed method outperforms the Curiosity-driven Variational Autoencoder (CVAE) at finding dynamic anomalies. © 2023 by the authors. All rights reserved.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Trustworthy Artificial Intelligence Framework for Proactive Detection and Risk Explanation of Cyber Attacks in Smart Grid

Trustworthy Artificial Intelligence Framework for Proactive ...

引用

2023 Winter simulation Conference, WSC 2023

作者： Munir, Md. Shirajum Shetty, Sachin Rawat, Danda B. Old Dominion University Virginia Modeling Analysis and Simulation Center 1030 University Blvd SuffolkVA23435 United States Howard University Department of Electrical and Computer Science 2400 Sixth Street NW WashingtonDC20059 United States

ISBN: (纸本)9798350369663

The rapid growth of distributed energy resources (DERs), such as renewable energy sources, generators, consumers, and prosumers in the smart grid infrastructure, poses significant cybersecurity and trust challenges to the grid controller. Consequently, it is crucial to identify adversarial tactics and measure the strength of the attacker's DER. To enable a trustworthy smart grid controller, this work investigates a trustworthy artificial intelligence (AI) mechanism for proactive identification and explanation of the cyber risk caused by the control/status message of DERs. Thus, proposing and developing a trustworthy AI framework to facilitate the deployment of any AI algorithms for detecting potential cyber threats and analyzing root causes based on Shapley value interpretation while dynamically quantifying the risk of an attack based on Ward's minimum variance formula. The experiment with a state-of-the-art dataset establishes the proposed framework as a trustworthy AI by fulfilling the capabilities of reliability, fairness, explainability, transparency, reproducibility, and accountability. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

NEAR-INFRARED AND LOW-RANK ADAPTATION OF VISION TRANSFORMERS IN REMOTE SENSING

arXiv

引用

arXiv 2024年

作者： Ulku, Irem Ozgur Tanriover, O. Akagündüz, Erdem Dept. of Computer Science Ankara University Ankara Turkey Dept. of Modeling and Simulation Graduate School of Informatics METU Ankara Turkey

Plant health can be monitored dynamically using multispectral sensors that measure Near-Infrared reflectance (NIR). Despite this potential, obtaining and annotating high-resolution NIR images poses a significant challenge for training deep neural networks. Typically, large networks pre-trained on the RGB domain are utilized to fine-tune infrared images. This practice introduces a domain shift issue because of the differing visual traits between RGB and NIR images. As an alternative to fine-tuning, a method called low-rank adaptation (LoRA) enables more efficient training by optimizing rank-decomposition matrices while keeping the original network weights frozen. However, existing parameter-efficient adaptation strategies for remote sensing images focus on RGB images and overlook domain shift issues in the NIR domain. Therefore, this study investigates the potential benefits of using vision transformer (ViT) backbones pre-trained in the RGB domain, with low-rank adaptation for downstream tasks in the NIR domain. Extensive experiments demonstrate that employing LoRA with pre-trained ViT backbones yields the best performance for downstream tasks applied to NIR images. © 2024, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

BCTM: A Topic modeling Method Based on External Information 13th

BCTM: A Topic Modeling Method Based on External Information

引用

Proceedings of the 13th EAI International Conference on Broadband Communications, Networks, and Systems, BROADNETS 2022

作者： Liu, Gang Wan, Taiying Yu, Jinfeng Zhan, Kai Wang, Wei College of Computer Science and Technology Harbin Engineering University Harbin150001 China PwC Enterprise Digital PricewaterhouseCoopers SydneyNSW2070 Australia National Engineering Laboratory of E-Government Modeling Simulation Harbin Engineering University Harbin150001 China

ISBN: (纸本)9783031404665

Topic models are often used as intermediate algorithms for text mining and semantic analysis in natural language processing, and have a wide range of functions. However, most of the existing improvements to the topic model use word embedding to improve the accuracy of text modeling, but ignore the external information in the text. This paper proposes a topic model BCTM (Bi-Concept Topic Model) using the word feature information and concept information. Based on the BTM topic model, BCTM introduces word feature information through word vector technology and concept information based on ConceptNet to optimize topic modeling. The construction method of Bi-Concept pair is proposed. Based on ConceptNet semantic network, and the content of text is enriched with concept information. A more accurate topic distribution is obtained through the improved topic model, at the same time, due to the rich feature information, the model is also superior to the baseline model in short text modeling. The experiments prove that the bilingual topic model proposed in this paper has a good performance in modeling accuracy. © 2023, ICST Institute for computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

School re-opening simulations with covid-19 agent-based model for quezon city, philippines

School re-opening simulations with covid-19 agent-based mode...

引用

2021 Philippine Geomatics Symposium 2021

作者： Celeste, J.J. Bongolan, V.P. System Modeling and Simulation Laboratory Department of Computer Science University of the Philippines Diliman Quezon City Philippines

The COVID-19 pandemic prompted schools to close in 2020, and with its negative impact on the quality of learning, the conversation shifts to the re-opening scenarios. In this study, we coupled a COVID-19 agent-based model (ABM) with social contact probabilities from pre-pandemic estimates. We then simulated school re-opening and vaccination scenarios in Quezon City, Philippines using our ABM. Our toy simulations suggest that the city could already re-open schools with 50% vaccination coverage. However, we suggest that students shall be vaccinated first, mask-wearing and physical distance shall be strictly observed, and schools shall only be re-opened by 25% as a precaution. Policymakers may take insights from the study. © International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Broadening Access to simulations for End-Users via Large Language Models: Challenges and Opportunities 24

Broadening Access to Simulations for End-Users via Large Lan...

引用

Proceedings of the Winter simulation Conference

作者： Philippe J. Giabbanelli Jose J. Padilla Ameeta Agrawal Virginia Modeling Analysis and Simulation Center Old Dominion University Norfolk VA USA Dept. of Computer Science Portland State University Portland OR USA

ISBN: (纸本)9798331534202

Large Language Models (LLMs) are becoming ubiquitous to create intelligent virtual assistants that assist users in interacting with a system, as exemplified in marketing. Although LLMs have been discussed in modeling & simulation (M&S), the community has focused on generating code or explaining results. We examine the possibility of using LLMs to broaden access to simulations, by enabling non-simulation end-users to ask what-if questions in everyday language. Specifically, we discuss the opportunities and challenges in designing such an end-to-end system, divided into three broad phases. First, assuming the general case in which several simulation models are available, textual queries are mapped to the most relevant model. Second, if a mapping cannot be found, the query can be automatically reformulated and clarifying questions can be generated. Finally, simulation results are produced and contextualized for decision-making. Our vision for such system articulates long-term research opportunities spanning M&S, LLMs, information retrieval, and ethics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Client Selection Method Based on Loss Function Optimization for Federated Learning

引用

computer modeling in Engineering & Sciences 2023年第10期137卷 1047-1064页

作者： Yan Zeng Siyuan Teng Tian Xiang Jilin Zhang Yuankai Mu Yongjian Ren Jian Wan School of Computer Science and Technology Hangzhou Dianzi UniversityHangzhou310018China Key Laboratory of Complex System Modeling and Simulation Ministry of EducationHangzhou310018China Zhejiang Engineering Research Center of Data Security Governance Hangzhou310018China Intelligent Robotics Research Center Zhejiang LabHangzhou311100China HDU-ITMO Joint Institute Hangzhou Dianzi UniversityHangzhou310018China

Federated learning is a distributedmachine learningmethod that can solve the increasingly serious problemof data islands and user data privacy,as it allows training data to be kept locally and not shared with other *** trains a globalmodel by aggregating locally-computedmodels of clients rather than their ***,the divergence of local models caused by data heterogeneity of different clients may lead to slow convergence of the global *** this problem,we focus on the client selection with federated learning,which can affect the convergence performance of the global model with the selected local *** propose FedChoice,a client selection method based on loss function optimization,to select appropriate local models to improve the convergence of the global *** firstly sets selected probability for clients with the value of loss function,and the client with high loss will be set higher selected probability,which can make them more likely to participate in ***,it introduces a local control vector and a global control vector to predict the local gradient direction and global gradient direction,respectively,and calculates the gradient correction vector to correct the gradient direction to reduce the cumulative deviationof the local gradient causedby *** experiments to verify the validity of FedChoice on CIFAR-10,CINIC-10,MNIST,EMNITS,and FEMNIST datasets,and the results show that the convergence of FedChoice is significantly improved,compared with FedAvg,FedProx,and FedNova.

关键词： Federated learning model aggregation Non-IID

来源：评论

学校读者我要写书评

暂无评论

Categorizing Social Media Screenshots for Identifying Author Misattribution

arXiv

引用

arXiv 2024年

作者： Farris, Ashlyn M. Nelson, Michael L. Mathematics Department Harding University United States Department of Computer Science Virginia Modeling Analysis and Simulation Center Old Dominion University United States

Mis/disinformation is a common and dangerous occurrence on social media. Misattribution is a form of mis/disinformation that deals with a false claim of authorship, which means a user is claiming someone said (posted) something they never did. We discuss the difference between misinformation and disinformation and how screenshots are used to spread author misattribution on social media platforms. It is important to be able to find the original post of a screenshot to determine if the screenshot is being correctly attributed. To do this we have built several tools to aid in automating this search process. The first is a Python script that aims to categorize Twitter posts based on their structure, extract the metadata from a screenshot, and use this data to group all the posts within a screenshot together. We tested this process on 75 Twitter posts containing screenshots collected by hand to determine how well the script extracted metadata and grouped the individual posts, F1 = 0.80. The second is a series of scrapers being used to collect a dataset that can train and test a model to differentiate between various social media platforms. We collected 16,620 screenshots have been collected from Facebook, Instagram, Truth Social, and Twitter. Screenshots were taken by the scrapers of the web version and mobile version of each platform in both light and dark mode. Copyright © 2024, The Authors. All rights reserved.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

"Why not looking backward?" a robust two-step method to automatically terminate Bayesian optimization 23

"Why not looking backward?" a robust two-step method to auto...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Shuang Li Ke Li Wei Li Control and Simulation Center Harbin Institute of Technology China and National Key Laboratory of Modeling and Simulation for Complex Systems China Department of Computer Science University of Exeter Exeter UK

Bayesian Optimization (BO) is a powerful method for tackling expensive blackbox optimization problems. As a sequential model-based optimization strategy, BO iteratively explores promising solutions until a predetermined budget, either iterations or time, is exhausted. The decision on when to terminate BO significantly influences both the quality of solutions and its computational efficiency. In this paper, we propose a simple, yet theoretically grounded, two-step method for automatically terminating BO. Our core concept is to proactively identify if the search is within a convex region by examining previously observed samples. BO is halted once the local regret within this convex region falls below a predetermined threshold. To enhance numerical stability, we propose an approximation method for calculating the termination indicator by solving a bilevel optimization problem. We conduct extensive empirical studies on diverse benchmark problems, including synthetic functions, reinforcement learning, and hyperparameter optimization. Experimental results demonstrate that our proposed method saves up to ≈ 80% computational budget yet is with an order of magnitude smaller performance degradation, comparing against the other peer methods. In addition, our proposed termination method is robust in terms of the setting of its termination criterion.

关键词：

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：