检索结果-内蒙古大学图书馆

Efficient Federated Learning Using Dynamic Update and Adaptive Pruning with Momentum on Shared Server Data

ACM Transactions on Intelligent Systems and Technology 2024年第6期15卷 1-28页

作者： Liu, Ji Jia, Juncheng Zhang, Hong Yun, Yuhui Wang, Leye Zhou, Yang Dai, Huaiyu Dou, Dejing Hithink RoyalFlush Information Network Co. Ltd. Hangzhou China School of Computer Science and Technology Soochow University Suzhou China Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing China Baidu Research Beijing China Key Lab of High Confidence Software Technologies Ministry of Education and Software Institute Peking University Beijing China Department of Computer Science and Software Engineering Auburn University AuburnAL United States Department of Electrical and Computer Engineering North Carolina State University RaleighNC United States Bedi Cloud and School of Computer Science Fudan University Beijing China

Despite achieving remarkable performance, Federated Learning (FL) encounters two important problems, i.e., low training efficiency and limited computational resources. In this article, we propose a new FL framework, i.e., FedDUMAP, with three original contributions, to leverage the shared insensitive data on the server in addition to the distributed data in edge devices so as to efficiently train a global model. First, we propose a simple dynamic server update algorithm, which takes advantage of the shared insensitive data on the server while dynamically adjusting the update steps on the server in order to speed up the convergence and improve the accuracy. Second, we propose an adaptive optimization method with the dynamic server update algorithm to exploit the global momentum on the server and each local device for superior accuracy. Third, we develop a layer-adaptive model pruning method to carry out specific pruning operations, which is adapted to the diverse features of each layer so as to attain an excellent tradeoff between effectiveness and efficiency. Our proposed FL model, FedDUMAP, combines the three original techniques and has a significantly better performance compared with baseline approaches in terms of efficiency (up to 16.9 times faster), accuracy (up to 20.4% higher), and computational cost (up to 62.6% smaller). © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Joint Optimization of Compression, Transmission and Computation for Cooperative Perception Aided Intelligent Vehicular Networks

引用

IEEE Transactions on Vehicular Technology 2025年第5期74卷 8201-8214页

作者： Lu, Binbin Huang, Xumin Wu, Yuan Qian, Liping Zhou, Sheng Niyato, Dusit University of Macau State Key Laboratory of Internet of Things for Smart City The Department of Computer and Information Science Macau China Guangdong University of Technology School of Automation Guangzhou510006 China University of Macau State Key Lab of Internet of Things for Smart City Macau China University of Macau State Key Laboratory of Internet of Things for Smart City The Department of Computer Information Science Macau China Zhuhai UM Science and Technology AQ2 Research Institute Zhuhai519301 China Zhejiang University of Technology Institute of Cyberspace Security Hangzhou310023 China Tsinghua University Beijing National Research Center for Information Science and Technology Department of Electronic Engineering Beijing100084 China Nanyang Technological University School of Computer Science and Engineering Singapore

Cooperative perception is a promising paradigm to tackle the perception limitations of a single intelligent vehicle (IV) to enhance the driving safety and efficiency in intelligent vehicular networks. However, the real-time transmission and computation-intensive fusion of raw sensing data raise new challenges for satisfying the stringent delay requirement of delay-sensitive applications. In this paper, we formulate a joint optimization problem of the cooperative IV selection, compression ratio selection, transmit power control, task offloading decision and computation allocation to minimize the end-to-end delay consisting of compression, transmission and computation. In particular, to meet the perception probability requirement, the quality and quantity-aware matching algorithm is proposed to optimize the cooperative IV selection. To guarantee the queue stability of offloading tasks, we develop the Lyapunov optimization algorithm to determine the upper bound of the offloading tasks and the corresponding optimal computation allocation. The Lyapunov aided deep reinforcement learning algorithm is further proposed to dynamically adjust the task offloading decision and compression ratio selection to minimize the end-to-end delay with the transmit power control being optimized by the successive convex approximation algorithm. Simulation results demonstrate that, compared to several benchmark algorithms, our proposed algorithm achieves the lowest end-to-end delay while guaranteeing the requirements on perception probability and queue stability effectively. © 1967-2012 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Integrating Deep and Handcrafted Features for Enhanced Remote Sensing Image Classification 21

Integrating Deep and Handcrafted Features for Enhanced Remot...

引用

2024 IEEE/ACS 21st International Conference on computer Systems and Applications, AICCSA 2024

作者： Ahmed, Vian Abdulmajeed Jouini, Khaled Tuama, Amel Korbaa, Ouajdi University of Sousse MARS Research Lab LR17ES05 ISITCom Sousse Tunisia Northern Technical University Computer Engineering Techniques Department Mosul Iraq MARS Research Lab LR17ES05 ISITCom University of Sousse Sousse Tunisia

ISBN: (纸本)9798331518240

Satellite imagery supports critical applications such as land cover mapping, environmental monitoring, disaster assessment, and urban planning. Despite significant advancements, challenges in analyzing satellite imagery persist, primarily due to data variability, atmospheric conditions, and complex land cover patterns. Traditional handcrafted descriptors like Scale-Invariant Feature Transform (SIFT) and encoding techniques such as Bag-of-Visual-Words (BoVW) are effective but often fall short in capturing global context and spatial relationships due to their inherent local nature. The advent of deep learning (DL), propelled by ample data and computational resources, has markedly improved satellite image analysis. However, the reliance on extensive annotated data constrains the wider applicability of DL methods. This study harnesses the strengths of both deep and hand-crafted features to enhance the classification accuracy of remote sensing images. Specifically, we synergize SIFT descriptors with pretrained MobileNetV2 and VGG16 deep features. While SIFT excels in capturing local features essential for identifying specific image characteristics, pretrained DL models provide enriched representations with global context, spatial relationships, and hierarchical features. This integration aims to overcome the individual limitations of each method, enabling the model to effectively handle perturbations, scale variations, and diverse landscapes. Extensive evaluations on the EuroSAT dataset demonstrate that our approach outperforms, not only SIFT, VGG16, and MobileNetV2 when used separately, but also surpasses state-of-the-art remote sensing image classification approaches. Another salient advantage of our approach is its robust applicability in scenarios with limited labeled data - a prevalent challenge in remote sensing image classification. © 2024 IEEE.

关键词： Satellite imagery

来源：评论

学校读者我要写书评

暂无评论

Optimal Control Problem and Its Application in COVID-19 Transmission Dynamics

Optimal Control Problem and Its Application in COVID-19 Tran...

引用

International Conference on Advanced engineering, Technology and Applications, ICAETA 2024

作者： Rahman, Md. Habibur Uddin, Mahtab Hossain, Yamin Sarkar, Nijam Uddin Islam, Md Aminul Siddique, Nafees Ahmed, Ashek Birahim, Shaikh Afnan Department of Mathematics University of Chittagong Chittagong Bangladesh Institute of Natural Sciences United International University Dhaka Bangladesh Department of Computer Science and Engineering VIT-AP University Andhra Pradesh India Institute of Statistical Research and Training University of Dhaka Dhaka Bangladesh Lead Researcher RNB Lab Dhaka Bangladesh Department of Computer Science American International University Dhaka Bangladesh Department of Computer Science and Engineering Royal University of Dhaka Dhaka Bangladesh

ISBN: (纸本)9783031709234

Optimal control techniques are among the most significant technical concepts that can be applied to medical concerns. Establishing a control law for a particular system mathematical model under specified restrictions to meet a specific optimality criterion is known as optimal control. To evaluate the effect of vaccination on the spread of infectious disease and try to decrease the infected group, an optimal control strategy known as Pontryagin’s principle applied in this project. This work develops and thoroughly analyzes and assesses two crucial COVID-19 therapeutic interventions: immunizing susceptible individuals and treating infected individuals under quarantine. A relevant set of conditions is met by proving the presence, distinctiveness, positivity, and unchanging domain of response, among other essential aspects of the model system. The model shows two equilibrium points: one is disease-free and the other that, under some circumstances, is endemic. The fundamental reproduction number R0 is obtained using the next-generation matrix technique, and the model’s dynamic behavior is thoroughly examined. When the corresponding primary reproduction number is smaller than unity, the analytical study shows that the unaffected-by-illness balance approach is both globally and locally stable over time, indicating that COVID-19 has died out in the population. Additionally, anytime the corresponding primary reproduction number surpasses a unity, suggesting that COVID-19 becomes established among the population. The primary reproduction number is subjected to a sensitivity analysis to determine the most critical factors that influence the spread of infection and its control. These are factors that intervention efforts should focus on. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Optimizing emissions for machine learning training

Optimizing emissions for machine learning training

引用

2023 IEEE Conference on Technologies for Sustainability, SusTech 2023

作者： Ekanayake, Sachini Piyoni Shah, Tapan Evans, Scott University at Albany Department of Electrical and Computer Engineering AlbanyNY United States GE Research Machine Learning Lab San RamonCA United States GE Research Machine Learning Lab NiskayunaNY United States

来源：评论

学校读者我要写书评

暂无评论

What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding 41

What Improves the Generalization of Graph Transformers? A Th...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Li, Hongkang Wang, Meng Ma, Tengfei Liu, Sijia Zhang, Zaixi Chen, Pin-Yu Department of Electrical Computer and System Engineering Rensselaer Polytechnic Institute TroyNY United States Department of Biomedical Informatics Stony Brook University Stony BrookNY United States Department of Computer Science and Engineering Michigan State University East LansingMI United States MIT-IBM Watson AI Lab IBM Research MA United States Department of Computer Science and Engineering University of Science and Technology of China Anhui Hefei China IBM Thomas J. Watson Research Center Yorktown HeightsNY United States

Graph Transformers, which incorporate self-attention and positional encoding, have recently emerged as a powerful architecture for various graph learning tasks. Despite their impressive performance, the complex non-convex interactions across layers and the recursive graph structure have made it challenging to establish a theoretical foundation for learning and generalization. This study introduces the first theoretical investigation of a shallow Graph Transformer for semi-supervised node classification, comprising a self-attention layer with relative positional encoding and a two-layer perceptron. Focusing on a graph data model with discriminative nodes that determine node labels and non-discriminative nodes that are class-irrelevant, we characterize the sample complexity required to achieve a desirable generalization error by training with stochastic gradient descent (SGD). This paper provides the quantitative characterization of the sample complexity and number of iterations for convergence dependent on the fraction of discriminative nodes, the dominant patterns, and the initial model errors. Furthermore, we demonstrate that self-attention and positional encoding enhance generalization by making the attention map sparse and promoting the core neighborhood during training, which explains the superior feature representation of Graph Transformers. Our theoretical results are supported by empirical experiments on synthetic and real-world benchmarks. Copyright 2024 by the author(s)

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Kalman Filter based Attack Detection for Adaptive Cruise Control Systems 5

Kalman Filter based Attack Detection for Adaptive Cruise Con...

引用

5th International Conference on Industrial Artificial Intelligence, IAI 2023

作者： Yang, Nachuan Nan, Fuhai Revadigar, Girish Shi, Ling Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Clear Water Bay Hong Kong Huawei Singapore Research Center Shield Lab Singapore

ISBN: (纸本)9798350325294

In this paper, we investigate the security issues of adaptive cruise control (ACC) systems for autonomous vehicles. Different from the research on cyber-layer security, we focus on cyber-physical system (CPS) security which incorporates the vehicle's control and dynamics into the security design. More specifically, we first analyze the longitudinal dynamics of on-road vehicles and then formulate a leader-follower model for the ACC system. Moreover, we establish a continuous-time Kalman filter for the leader-follower model and characterize its innovation's probabilistic properties. Finally, we develop multiple attack detectors based on Kalman filtering and statistical testing. The effectiveness of the proposed methods is validated via numerical simulations and experiments on Carla, an open-source platform for autonomous driving research. © 2023 IEEE.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Psycho Acoustic Testing to Determine the Optimal Frequency for Audible Safety Alerts for Freediving

Psycho Acoustic Testing to Determine the Optimal Frequency f...

引用

IEEE Symposium on Systems and Information engineering Design, SIEDS

作者： Arnav Nanda Mohammad Zoraiz Dhruva Barua Raghad Mohamed Department of Electrical & Computer Engineering & Duke Marine Lab Research Supported by Duke Pratt School of Engineering

ISBN: (数字)9798350385144

ISBN: (纸本)9798350385151

Freediving is a captivating sport that involves diving underwater on a single breath, pushing the boundaries of human capability and exploring the depths of the ocean with minimal equipment. While free diving offers a unique and thrilling underwater experience, it also poses several difficulties. Having been in the water for long periods, many divers can develop hypoxia or decompression sickness. To solve this issue many divers use watches that allow them to monitor the heart rate, oxygen levels, and depth levels. Most of these watches can track and monitor vital signs and warn in case of potential harm or risk to the diver. While these watches are helpful, they are not preventative and many divers have passed away due to oxygen-related issues, decompression sickness, and a myriad of other problems. This project aims to address these problems and improve upon current products produced by Garmin Inc. Duke’s EGR102 team’s goal is to create an effective data collection and signal analysis algorithm dedicated for efficiently analyzing data regarding different pitches, timbers, and audible tones at varying depths of water. More importantly, the product should be able to stay underwater at 6 meters depth for more than an hour.

关键词： Meters Heart rate Oceans Data collection Hypoxia Safety Biomedical monitoring

来源：评论

学校读者我要写书评

暂无评论

Analyzing Digital Image Anti-Forensics Techniques and Countermeasures 27

Analyzing Digital Image Anti-Forensics Techniques and Counte...

引用

27th International Conference on Advanced Communications Technology, ICACT 2025

作者： Agarwal, Saurabh Kumar, Rajeev Devi, Abha Jung, Ki-Hyun Department of Information and Communication Engineering Yeungnam University Gyeongsan38541 Korea Republic of Blockchain Technology Research Lab Department of Computer Science and Engineering Delhi Technological University New Delhi110042 India Department of Software Convergence Andong National University Gyeongbuk36729 Korea Republic of College Uttar Pradesh Sikandrabad India

ISBN: (纸本)9791188428137

With the increasing use of digital media, digital forensics has become a crucial method for ascertaining authenticity and detecting manipulations in images. However, intentional anti-forensic manipulations to hide forensic clues have made verification more difficult. The efforts to develop countermeasures against anti-forensics have contributed to the evolution toward robust techniques in the field of anti-forensics;hence, the development of anti-forensic methods and their respective countermeasures will remain continuous. This work provides a scientometric analysis, a powerful tool for the study of the growth of research output in accordance with time and citation, author, organizational, and keyword co-occurrence analysis. It enhances state-of-the-art analysis by underlining highly influential authors, organizations, and works and stipulates knowledge gaps. This would consequently provide a platform for building a community where insights and inclusiveness among researchers, industry practitioners, and policymakers would all come together to guide their strategies and decisions for innovation in this dynamic field. Copyright 2025 Global IT research Institute (GIRI). All rights reserved.

关键词： Fake detection

来源：评论

学校读者我要写书评

暂无评论

CLIMS++: Cross Language Image Matching with Automatic Context Discovery for Weakly Supervised Semantic Segmentation

引用

International Journal of computer Vision 2025年 1-20页

作者： Xie, Jinheng Deng, Songhe Hou, Xianxu Luo, Zhaochuan Shen, Linlin Huang, Yawen Zheng, Yefeng Shou, Mike Zheng Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Department of Computer Science Wenzhou-Kean University Wenzhou325060 China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China Show Lab National University of Singapore Singapore639798 Singapore School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University Suzhou215400 China Jarvis Research Center Tencent YouTu Lab Shenzhen518703 China

While promising results have been achieved in weakly-supervised semantic segmentation (WSSS), limited supervision from image-level tags inevitably induces discriminative reliance and spurious relations between target classes and background regions. Thus, Class Activation Map (CAM) usually tends to activate discriminative object regions and falsely includes lots of class-related backgrounds. Without pixel-level supervisions, it could be very difficult to enlarge the foreground activation and suppress those false activation of background regions. In this paper, we propose a novel framework of Cross Language Image Matching with Automatic Context Discovery (CLIMS++), based on the recently introduced Contrastive Language-Image Pre-training (CLIP) model, for WSSS. The core idea of our framework is to introduce natural language supervision to activate more complete object regions and suppress class-related background regions in CAM. In particular, we design object, background region, and text label matching losses to guide the model to excite more reasonable object regions of each category. In addition, we propose to automatically find spurious relations between foreground categories and backgrounds, through which a background suppression loss is designed to suppress the activation of class-related backgrounds. The above designs enable the proposed CLIMS++ to generate a more complete and compact activation map for the target objects. Extensive experiments on PASCAL VOC 2012 and MS COCO 2014 datasets show that our CLIMS++ significantly outperforms the previous state-of-the-art methods. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Semantic Segmentation

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：