检索结果-内蒙古大学图书馆

Personalized Graph Federated Learning With Differential Privacy

IEEE Transactions on Signal and information Processing over Networks 2023年 9卷 736-749页

作者： Gauthier, Francois Gogineni, Vinay Chakravarthi Werner, Stefan Huang, Yih-Fang Kuh, Anthony Norwegian University of Science and Technology Department of Electronic Systems Trondheim7034 Norway Norwegian University of Science and Technology Trondheim7034 Norway University of Southern Denmark Sdu Applied Ai and Data Science The Maersk Mc-Kinney Moller Institute Odense5230 Denmark Aalto University Department of Information and Communications Engineering Aalto00076 Finland University of Notre Dame Department of Electrical Engineering Notre DameIN46556 United States University of Hawaii at Manoa Department of Electrical Engineering HonoluluHI96822 United States

This paper presents a personalized graph federated learning (PGFL) framework in which distributedly connected servers and their respective edge devices collaboratively learn device or cluster-specific models while maintaining the privacy of every individual device. The proposed approach exploits similarities among different models to provide a more relevant experience for each device, even in situations with diverse data distributions and disproportionate datasets. Furthermore, to ensure a secure and efficient approach to collaborative personalized learning, we study a variant of the PGFL implementation that utilizes differential privacy, specifically zero-concentrated differential privacy, where a noise sequence perturbs model exchanges. Our mathematical analysis shows that the proposed privacy-preserving PGFL algorithm converges to the optimal cluster-specific solution for each cluster in linear time. It also reveals that exploiting similarities among clusters could lead to an alternative output whose distance to the original solution is bounded and that this bound can be adjusted by modifying the algorithm's hyperparameters. Further, our analysis shows that the algorithm ensures local differential privacy for all clients in terms of zero-concentrated differential privacy. Finally, the effectiveness of the proposed PGFL algorithm is showcased through numerical experiments conducted in the context of regression and classification tasks using some of the National Institute of Standards and Technology's (NIST's) datasets, namely, MNIST, and MedMNIST. © 2015 IEEE.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

WHAT USERS WANT: A NATURAL LANGUAGE PROCESSING APPROACH TO DISCOVER USERS' NEEDS FROM ONLINE REVIEWS 24

WHAT USERS WANT: A NATURAL LANGUAGE PROCESSING APPROACH TO D...

引用

24th International Conference on engineering Design, ICED 2023

作者： Spada, Irene Barandoni, Simone Giordano, Vito Chiarello, Filippo Fantoni, Gualtiero Martini, Antonella School of Engineering Department of Information Engineering University of Pisa Italy Department of Computer Science University of Pisa Italy School of Engineering Department of Energy Systems Land and Construction Engineering University of Pisa Italy School of Engineering Department of Civil and Industrial Engineering University of Pisa Italy B4DS - Business Engineering for Data Science Lab University of Pisa Italy

Digital media are a means to deliver products and services, but also a channel to interact with consumers and a source of information on users' preferences. data shared by customers on the web, the User-Generated Content (UGC), can give entrepreneurs a detailed perspective of the market. This work examines an application of Natural Language Processing techniques on UGC to discover insights on users' opinions. We collected more than 13.000 reviews of software from digital stores and review website to gather information on the customers' perspective and their response to a given marketing strategy in two case studies on digital product's launch. The objective is to give support to two Italian companies in the process of business model development through data-driven evidence. We aim to discover who are the users and which are their needs using a lexicon-based approach to mine unstructured text. The results provide qualitative and quantitative descriptions of the market segments. We propose a method to examine UGC and to explore customers' behavior on social media. The findings helped managers for the development of their business model, enhancing an informed decision-making process. © The Author(s), 2023. Published by Cambridge university Press.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

Handwritten Text and Digit Classification on Rwandan Perioperative Flowsheets via YOLOv5

Handwritten Text and Digit Classification on Rwandan Periope...

引用

2022 systems and information engineering Design Symposium, SIEDS 2022

作者： Annapareddy, Navya Fallin, Kara Folks, Ryan Jarrard, William Durieux, Marcel Moradinasab, Nazanin Naik, Bhiken Sengupta, Saurav Ndaribitse, Christian Brown, Donald University of Virginia School of Data Science CharlottesvilleVA United States Systems and Environment University of Virginia Department of Engineering CharlottesvilleVA United States University of Virginia Department of Anesthesiology CharlottesvilleVA United States

ISBN: (纸本)9781665451116

The African Surgical Outcomes Study, a seven-day, prospective, observational cohort study across 25 countries in Africa reported a rate of serious postoperative complications of 18% and mortality of 2% [1]. 95% of these deaths occurred in the postoperative period and were considered preventable. There are many factors that contribute to postoperative outcomes, but a key approach to decreasing complications is the ability to predict patient outcome trajectories from perioperative parameters [2]. In order to efficiently predict these outcomes, electronic medical record systems are needed. As compared to handwritten paper records, these systems offer profound advantages, including automated transfer of medical information, dynamic search queries, and improved resilience for data backups. In this paper, we implement the digitization of the drug and physiological indicator portions of 363 handwritten perioperative flowsheets sourced from the university Teaching Hospital of Kigali in Rwanda. In both sections, the detection of handwritten words and digits is accomplished using a YOLOv5 model trained on a single class. The bounding boxes are then cropped and classified by a convolutional neural network (CNN). Our experimental results suggest that our proposed method can successfully detect handwritten digits and words as evaluated on object mean average precision (mAP). © 2022 IEEE.

关键词： Hospitals

来源：评论

学校读者我要写书评

暂无评论

Comparative Effectiveness of Classification Algorithms in Predicting Diabetes 16

Comparative Effectiveness of Classification Algorithms in Pr...

引用

16th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2024

作者： Dael, Fares A. Mareyev, D. Shayea, Ibraheem Kulniyazova Korlan, S. Abitova, Gulnara İzmir Bakirçay University Management Information Systems Izmir Turkey Astana It University Department of Computational and Data Science Astana Kazakhstan Istanbul Technical University Electronic and Communication Engineering Istanbul Turkey L.N. Gumilyov Eurasian National University Department of Systems Analysis and Control Astana Kazakhstan Astana It University Department of Intelligent Systems and Cybersecurity Astana Kazakhstan

ISBN: (纸本)9798331505264

Diabetes mellitus poses a significant global health challenge, with increasing prevalence, particularly in low socioeconomic regions. Accurate and early diagnosis is crucial to prevent the severe long-term complications associated with diabetes. This study conducts a comprehensive comparison of six prominent machine learning algorithms-K-Nearest Neighbors (K-NN), Naive Bayes, Support Vector Machine (SVM), Decision Trees, Random Forest, and Logistic Regression-in predicting diabetes using a dataset of 768 individuals with diverse diabetic indicators from Kaggle. Each algorithm is rigorously evaluated based on precision, recall, and F1-score to determine the most effective method for diabetes diagnosis. The results indicate that Logistic Regression outperforms the other algorithms, achieving an accuracy of 81%. This superior performance is attributed to Logistic Regression's ability to effectively delineate linear separations, which is crucial for distinguishing between diabetic and non-diabetic individuals. The study underscores the importance of feature selection and model tuning in enhancing predictive performance. The findings suggest that integrating Logistic Regression into clinical settings can significantly improve the accuracy and timeliness of diabetes diagnosis, potentially leading to better patient outcomes and reduced healthcare costs. © 2024 IEEE.

关键词： Support vector regression

来源：评论

学校读者我要写书评

暂无评论

Incremental Learning with Pseudo Labels for Enhanced Glomeruli Segmentation Using SAM

Incremental Learning with Pseudo Labels for Enhanced Glomeru...

引用

2024 IEEE International Conference on E-Health Networking, Application and Services, HealthCom 2024

作者： Liu, Xinkai Peng, Boyuan Zhu, Xin Iwasaki, Tsuyoshi Sato, Atsuya Kazama, Junichiro James Huang, Jie Graduate Department of Computer Science and Engineering The University of Aizu Fukushima Aizu-Wakamatsu Japan Department of AI Technology Development M&D Data Science Center Institute of Science Tokyo Tokyo Japan Department of Nephrology and Hypertension Fukushima Medical University Fukushima Japan Graduate Department of Computer Science and Engineering Division of Information Systems The University of Aizu Fukushima Aizu-Wakamatsu Japan

ISBN: (纸本)9798350350548

The advent of the Segment Anything Model (SAM) marks a significant milestone in deep learning semantic segmentation tasks. In this study, an incremental learning model based on pseudo labels is proposed. The model generates bounding box prompts for SAM, enhancing the accuracy of glomeruli segmentation in renal pathology images. The model uses DenseNet-121 along with contrastive learning to enable self-supervised pre-training using mouse glomeruli images. Transfer learning is then conducted using labeled human renal pathology images to develop a binary classification model for glomeruli. Unlabeled images of human renal pathology are subsequently introduced for incremental learning. Class activation maps (CAMs) generated by the incremental learning model are post-processed to extract bounding rectangles for connected regions. These rectangles are then used as prompts for SAM segmentation. The proposed approach resulted in an average Dice similarity coefficient (DSC) of 0.825 in the glomeruli segmentation task. This result demonstrates the effectiveness of the incremental learning model and post-processing algorithms in improving SAM’s segmentation accuracy for renal pathology. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Performance Optimization for Vehicular Cooperative Sensing: A Graph Attention Based Reinforcement Learning Approach

Performance Optimization for Vehicular Cooperative Sensing: ...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Li, Xuefei Chen, Mingzhe Liu, Danpu Zhang, Zhilong Quek, Tony Q. S. Beijing Laboratory of Advanced Information Network Beijing University of Posts and Telecommunications Beijing100876 China University of Miami Department of Electrical and Computer Engineering Institute for Data Science and Computing Coral GablesFL33146 United States Information Systems Technology and Design Pillar Singapore University of Technology and Design 487372 Singapore

ISBN: (纸本)9798350351255

In this paper, the problem of collaborative vehicle sensing is investigated. In the considered model, a set of cooperative vehicles provide sensing information to sensing request vehicles with limited sensing and communication resources. A base station (BS) determines the subset of sensing request vehicles that each cooperative vehicle will serve and the sub-regions that each cooperative vehicle will detect. We formulate an optimization problem aiming to maximize the number of successfully detected sub-regions of sensing request vehicles while satisfying the cooperative sensing energy requirement by jointly determining the cooperative vehicle association and the sensing sub-region selection. To solve this problem, we propose a graph attention based reinforcement learning (RL) algorithm that can generate the graph information vectors based on the correlation between each cooperative vehicle and each sensing request vehicle. Using the learned graph information, the joint cooperative vehicle association and sensing sub-region selection strategy will be determined. Simulation results show that the proposed scheme can improve the number of successfully detected sub-regions of sensing request vehicles by up to 12.5% compared to the conventional RL algorithm without using graph attention networks (GANs). © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

TERMS: Task management policies to achieve high performance for mixed workloads using surplus resources

引用

Journal of Parallel and Distributed Computing 2022年 170卷 74-85页

作者： Yu, Jinyu Tong, Wei Lv, Pengze Feng, Dan Wuhan National Laboratory for Optoelectronics Key Laboratory of Information Storage System Engineering Research Center of Data Storage Systems and Technology School of Computer Science and Technology Huazhong University of Science and Technology Ministry of Education of China Hubei Wuhan China

Resource contentions and performance interferences can lead to workload performance degradation in mixed-workload deployment clusters. Previous work guarantees the resource requirements of latency-sensitive tasks and reduces performance losses to batch jobs by reclaiming surplus resources from over-provisioned tasks. While the fragmentation of resources leads to a mismatch between provisioned resources and task requirements, resulting in high operation overheads and losses of task fairness. This paper proposes TERMS, the task management policies based on task relevance, resource distribution, and task fairness to achieve efficient and low-cost task management. TERMS mainly includes three types of management policies. The task scheduling policy can schedule new tasks according to task relevance. Task selection strategies select tasks for resource provisioning and task resumption based on resource requirements and task fairness. If necessary, the node selection strategy can be used to choose befitting target nodes based on task relevance and node resource information for task migration when eliminating straggler tasks. Evaluation results show that TERMS can further improve the performance of latency-sensitive services and batch jobs, reduce management overheads, and avoid operation failures. © 2022 Elsevier Inc.

关键词： Scheduling

来源：评论

学校读者我要写书评

暂无评论

UAV-Assisted data Synchronization for Digital-Twin-Enabled Vehicular Networks

UAV-Assisted Data Synchronization for Digital-Twin-Enabled V...

引用

2023 IEEE/CIC International Conference on Communications in China, ICCC 2023

作者： Wu, Guoquan Nie, Jiangtian Tang, Jianhang Zhang, Yang Xiao, Jiang Xiong, Zehui Yanshan University School of Information Science and Engineering China Nanyang Technological University School of Computer Science and Engineering Singapore Guizhou University State Key Laboratory of Public Big Data China Nanjing University of Aeronautics and Astronautics College of Computer Science and Technology China Huazhong University of Science and Technology School of Computer Science and Technology China Singapore University of Technology and Design Pillar of Information Systems Technology and Design Singapore

ISBN: (纸本)9798350345384

Digital twin (DT) is becoming a promising solution for vehicular networks to improve the interoperability of distributed autonomous driving systems. Mobile edge computing (MEC) has been introduced to provide low-latency services for DT-enabled vehicular networks at the edge of the network. However, it is hard to obtain the dynamic network topology for moving vehicles by the ground-based MEC system, which may deteriorate the service quality for DT synchronization. In this paper, we propose a novel unmanned aerial vehicle (UAV)-assisted synchronization framework for DT-enabled vehicular networks. With the proposed framework, an intelligent resource allocation algorithm is developed to improve UAV resource utilization and maximize the synchronization completion ratio. By leveraging an advantage actor-critic (A2C) algorithm, the synchronization decisions are obtained with low time complexity. Experiment results demonstrate that the proposed algorithm can reduce the synchronization latency and improve the synchronization completion ratio effectively. © 2023 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Public Decision-Making Analysis in Urban Heat Islands Based on Socioeconomic Modelling by Deep Learning Techniques

引用

Remote Sensing in Earth systems sciences 2024年第1期8卷 108-117页

作者： Prakash, S. Wilson Kiruthigha, R. Yadav, Ajay Kumar Kanna, S. K. Rajesh Shaik, Khasimbee Krishna, B. Murali Department of Data Science and Business Systems SRM Institute of Science and Technology Chennai Kattankulathur India Department of Information Technology SRM Institute of Science and Technology Chennai Ramapuram India Department of Computer Application United Institute of Management UP Prayagraj 211010 India Department of Mechanical Engineering Rajalakshmi Institute of Technology Chennai India Department of Computer Science and Engineering Aditya University Andhra Pradesh Surampalem India Department of Computer Science and Engineering MLR Institute of Technology Hyderabad India

Urban heat island (UHI) effects, especially in highly urbanised areas, and greenhouse gas emissions from human activity are two elements that accelerate global climate change (GCC). Sustainable city planning and modification may benefit from the quantification of the surface UHI (SUHI) effect utilising land surface temperature (LST), local climate zones (LCZ), and deep learning methods like convolutional neural networks (CNN) and pix2pix. The findings show that socioeconomic variables account for 12–20% of variability in UHI intensity. In general, the contribution rate of urban economic scale is higher than that of population and industrial structure variables. The increase in urban economic expansion increased summertime heat discomfort. This research propose novel method in socioeconomic analysis based on urban heat pattern analysis with public healthcare system using decision-making with DL (deep learning) model. Input is collected as urban heat pattern dataset and processed for noise removal and normalisation. This data has been features are extracted and classified using convolutional fuzzy Q-Gaussian neural network and variational K-C-means regressive learning. The simulation analysis has been carried out based on training accuracy, average precision, recall, and F-measure. The proposed model attained average precision was 94%, recall was 90%, training accuracy was 97%, and F1-score was 92%. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Decision-making Deep learning model Public healthcare system Socioeconomic analysis Urban heat pattern

来源：评论

学校读者我要写书评

暂无评论

Scavenger: Better Space-Time Trade-Offs for Key-Value Separated LSM-trees 40

Scavenger: Better Space-Time Trade-Offs for Key-Value Separa...

引用

40th IEEE International Conference on data engineering, ICDE 2024

作者： Zhang, Jianshun Wang, Fang Qiu, Sheng Wang, Yi Ou, Jiaxin Huang, Junxun Li, Baoquan Fang, Peng Feng, Dan School of Computer Science and Technology Huazhong University of Science and Technology Wuhan National Laboratory for Optoelectronics Key Laboratory of Information Storage System Engineering Research Center of Data Storage Systems and Technology Ministry of Education of China China Shenzhen Huazhong University of Science and Technology Research Institute China Bytefrance Inc.

ISBN: (纸本)9798350317152

Key-Value Stores (KVS) implemented with log-structured merge-tree (LSM-tree) have gained widespread ac-ceptance in storage systems. Nonetheless, a significant challenge arises in the form of high write amplification due to the compaction process. While KV-separated LSM-trees successfully tackle this issue, they also bring about substantial space am-plification problems, a concern that cannot be overlooked in cost-sensitive scenarios. Garbage collection (GC) holds significant promise for space amplification reduction, yet existing GC strategies often fall short in optimization performance, lacking thorough consideration of workload characteristics. Additionally, current KV-separated LSM-trees also ignore the adverse effect of the space amplification in the index LSM-tree. In this paper, we systematically analyze the sources of space amplification of KV-separated LSM-trees and introduce Scavenger, which achieves a better trade-off between performance and space amplification. Scavenger initially proposes an I/O-efficient garbage collection scheme to reduce I/O overhead and incorporates a space-aware compaction strategy based on compensated size to minimize the space amplification of index LSM-trees. Extensive experiments show that Scavenger significantly improves write performance and achieves lower space amplification than other KV-separated LSM-trees (including BlobDB, Titan, and TerarkDB). © 2024 IEEE.

关键词： Economic and social effects

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：