检索结果-内蒙古大学图书馆

Snowball Effect in Federated Learning: An Approach of Exponentially Expanding Structures for Optimizing the Training Efficiency

引用

IEEE Transactions on Cognitive Communications and Networking 2024年第3期11卷 1803-1817页

作者： Cheng, Guoliang Li, Peichun Tan, Beihai Yu, Rong Wu, Yuan Pan, Miao Guangdong University of Technology School of Automation Guangzhou China Guangdong Key Laboratory of IoT Information Technology Guangzhou China University of Macau State Key Laboratory of Internet of Things for Smart City China University of Macau Department of Computer and Information Science China Guangdong University of Technology School of Integrated Circuits Guangzhou China University of Houston Department of Electrical and Computer Engineering Houston United States

Efficient federated learning (FL) in mobile edge networks faces challenges due to energy-consuming on-device training and wireless transmission. Optimizing the neural network structures is an effective approach to achieving energy savings. In this paper, we present a Snowball FL training with expanding neural network structure, which starts with a small-sized submodel and gradually progresses to a full-sized model. To achieve this, we first design the submodel and embedding extraction schemes for fine-grained model structure expansion. We then investigate the joint minimization problem of the global training loss and system-wise energy consumption. After that, we decompose the optimization problem into a long-term model structure expansion subproblem and a single-round local resource allocation subproblem. Specifically, the former subproblem is transformed into a variational calculus problem by leveraging theoretical analysis of the convergence bound. The Euler-Lagrange method is used to derive the solution, where the optimal evolution strategy for the model structure exponentially increases with the global round (i.e., the Snowball effect). Meanwhile, the latter subproblem is solved by convex optimization to acquire the optimal computing frequency and transmission power. Experiments indicate that the proposed framework can save about 50% of energy consumption to achieve on-par accuracy against state-of-the-art algorithms. © 2015 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Critical Infrastructure Security Goes to Space: Leveraging Lessons Learned on the Ground

Critical Infrastructure Security Goes to Space: Leveraging L...

引用

Accelerating Space Commerce, Exploration, and New Discovery Conference, ASCEND 2023

作者： Ellis, Tim Hitaj, Briland Lindqvist, Ulf Shands, Deborah Tinnel, Laura DeBruhl, Bruce Computer Science Laboratory SRI International California Polytechnic State University United States Computer Science and Software Engineering Department California Polytechnic State University United States

ISBN: (数字)9781624107054

ISBN: (纸本)9781624107054

Space systems enable essential communications, navigation, imaging and sensing for a variety of domains, including agriculture, commerce, transportation, and emergency operations by first responders. Protecting the cybersecurity of these critical infrastructure systems is essential. While the space environment brings unique constraints to managing cybersecurity risks, lessons learned about risks and effective defenses in other critical infrastructure domains can help us to design effective defenses for space systems. In particular, discoveries regarding cybersecurity for industrial control systems (ICS) for energy, manufacturing, transportation, and the consumer and industrial Internet of Things (IoT) offer insights into cybersecurity for the space domain. This paper provides an overview of ICS and space system commonalities, lessons learned about cybersecurity for ICS that can be applied to space systems, and recommendations for future research and development to secure increasingly critical space systems. © 2023, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

EEiF: Efficient Isolated Forest with e Branches for Anomaly Detection 24

EEiF: Efficient Isolated Forest with e Branches for Anomaly ...

引用

24th IEEE International Conference on Data Mining, ICDM 2024

作者： Zhang, Yifan Xiang, Haolong Zhang, Xuyun Xu, Xiaolong Fan, Wei Zhang, Qin Qi, Lianyong School of Software Nanjing University of Information Science and Technology China Jiangsu Province Engineering Research Center of Advanced Computing and Intelligent Services China School of Computing Macquarie University Australia University of Oxford Uffield Department of Women's & Reproductive Health United Kingdom College of Computer Science and Software Engineering Shenzhen University China Faculty of Science and Engineering China

ISBN: (纸本)9798331506681

Anomaly detection is a popular research topic in Artificial Intelligence and has been widely applied in network security, financial fraud detection, and industrial equipment failure detection. Isolation forest based methods are the base algorithms to detect anomalies in these scenarios for their simplicity and efficiency, which has been further exploited with multi-folk trees and learning mechanisms to realize the optimal isolation forest for high detection accuracy. However, the optimal isolation forest is time-consuming with the learning mechanisms, resulting in the task failing of time-constrained applications. Moreover, the original optimal isolation forest fails to construct the optimal tree structure restricted by the time complexity. To address the above challenges, we propose an efficient anomaly detection method called EEIF, which realizes the real e-folk structure of the optimal isolation forest in our practical algorithm design. Specifically, we design a distribution that perfectly matches the e-branch theory to construct the optimal isolation forest. Then, we design an FR clustering scheme to achieve fast training of the isolation forest with learning to hash and provide related proofs of accuracy and efficiency. Besides, a parallel algorithm is integrated into our method to reduce prediction time. Finally, extensive experiments are conducted on a large amount of real-world datasets and the results demonstrate that our method significantly improves efficiency while ensuring effectiveness, compared with the state-of-the-art methods. © 2024 IEEE.

关键词： Anomaly Detection Efficient FR clustering Parallel Algorithm

来源：评论

学校读者我要写书评

暂无评论

A Survey on Indoor Visible Light Positioning Systems: Fundamentals, Applications, and Challenges

引用

IEEE Communications Surveys and Tutorials 2024年第3期27卷 1656-1686页

作者： Zhu, Zhiyu Yang, Yang Chen, Mingzhe Guo, Caili Cheng, Julian Cui, Shuguang Beijing University of Posts and Telecommunications Beijing Key Laboratory of Network System Architecture and Convergence School of Information and Communication Engineering Beijing100876 China University of Miami Department of Electrical and Computer Engineering and Institute for Data Science and Computing Coral GablesFL33146 United States Beijing University of Posts and Telecommunications Beijing Laboratory of Advanced Information Networks School of Information and Communication Engineering Beijing100876 China The University of British Columbia Faculty of Applied Science School of Engineering KelownaBCV1V 1V7 Canada 518172 Hong Kong

The growing demand for location-based services in areas like virtual reality, robot control, and navigation has intensified the focus on indoor localization. Visible light positioning (VLP), leveraging visible light communications (VLC), becomes a promising indoor positioning technology due to its high accuracy and low cost. This paper provides a comprehensive survey of VLP systems. In particular, since VLC lays the foundation for VLP, we first present a detailed overview of the principles of VLC. Then, we provide an in-depth overview of VLP algorithms. The performance of each positioning algorithm is also compared in terms of various metrics such as accuracy, coverage, and orientation limitation. Beyond the physical layer studies, the network design for a VLP system is also investigated, including multi-access technologies, resource allocation, and light-emitting diode (LED) placements. Next, the applications of the VLP systems are overviewed. Finally, this paper outlines open issues, challenges, and opportunities for the research field. In a nutshell, this paper constitutes the first holistic survey on VLP from state-of-the-art studies to practical uses. © 1998-2012 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Improving ECAPA-TDNN Performance with Coordinate Attention

引用

Journal of Shanghai Jiaotong University (science) 2024年 1-7页

作者： Liu, Shuanghong Song, Zhida He, Liang School of Computer Science and Technology Xinjiang University Urumqi830017 China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi830017 China Department of Electronic Engineering and Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China

The current mainstream networks, such as squeeze and excitation residual neural network (SE-ResNet) and emphasized channel attention, propagation and aggregation based time delay neural network (ECAPA-TDNN), enhance the capability of speaker embedding extractors to extract more discriminative speaker embeddings by incorporating squeeze and excitation (SE) attention within the convolutional blocks. However, the SE attention focuses solely on encoding inter-channel information, overlooking the importance of spatial positional information and time-frequency information, which are crucial for the model’s performance. In this paper, we first experimentally compare the effectiveness of several mainstream attention mechanisms in the computer vision domain for the ECAPA-TDNN model. Next, we focus on the substantial improvements that coordinate attention (CA) brings to the ECAPA-TDNN model. The introduction of CA can help the model embed time-frequency information into the channel representation. Even without using AS-Norm, our proposed model achieves relative reductions of about 5.3% equal error rate (EER) and 5.5% minimum detection cost function (minDCF) on both the Voxceleb-O and Voxceleb-H test sets compared to the ECAPA-TDNN baseline model. In addition, the EER is relatively reduced by 9.46% on the CN-Celeb1 test set. This result strongly demonstrates that the CA module can effectively improve the generalization ability of the ECAPA-TDNN model. © Shanghai Jiao Tong University 2024.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Adaptive Occlusion Face Recognition Feature Fusion Network Based on Precise Guidance Mask Extraction

引用

Journal of Shanghai Jiaotong University (science) 2025年 1-12页

作者： Ye, Jihua Zhang, Lei Wang, Chao Tu, Qixuan Zheng, Rehua Huang, Huiyuan Jiang, Aiwen School of Computer and Information Engineering Jiangxi Normal University Nanchang330022 China Jiangxi Provincial Key Laboratory for High Performance Computing Jiangxi Normal University Nanchang330022 China State International Science & Technology Cooperation Base of Networked Supporting Software Jiangxi Normal University Nanchang330022 China

The uncertainty in the position and size of occluding objects greatly affects the extraction of identity features in facial recognition, which is a challenge that existing methods fail to effectively address. To tackle this issue, this paper introduces a novel feature fusion network for occluded facial recognition that adaptively handles arbitrary occlusions and accurately extracts occlusion information masks. The network effectively mitigates the impact of occlusions on facial identity features through a feature fusion module. The proposed method employs an occlusion classification module and an occlusion classification loss to precisely guide the extraction of accurate occlusion masks. Subsequently, an occlusion-aware hybrid attention module is introduced, which focuses on the relationship between facial features and occlusion masks across channel and spatial dimensions. This fusion strategy enables the extraction of facial identity features that are resilient to occlusions. Experimental results indicate that the proposed method holds a significant advantage in handling facial recognition tasks with arbitrary occlusions. On the LFW and MF1 synthetic occlusion datasets, the average accuracy rates reached 93.19% and 72.57%, respectively, showing improvements of 1.7 and 2.39 percent points over mainstream methods. © Shanghai Jiao Tong University 2025.

关键词： A feature fusion occluded facial recognition occlusion mask occlusion perception TP391.41

来源：评论

学校读者我要写书评

暂无评论

Functional plastic films:nano-engineered composite based flexible microwave antennas with near-unity relative visible transmittance

引用

Light(Advanced Manufacturing) 2024年第2期5卷 95-105页

作者： Cheng Zhang Liang Zhu Chengang Ji Zhilu Ye Nabeel Alsaab Minye Yang Yuhui Hu Pai-Yen Chen L.Jay Guo School of Optical and Electronic Information&Wuhan National Laboratory for Optoelectronics Huazhong University of Science and TechnologyWuhan430074China Department of Electrical and Computer Engineering University of Illinois at ChicagoChicagoIL 60607USA Department of Electrical Engineering and Computer Science University of MichiganAnn ArborMI 48109USA

Microwave antennas are essential elements for various applications,such as telecommunication,radar,sensing,and wireless power *** antennas are conventionally manufactured on rigid substrates using opaque materials,such as metal strips,metallic tapes,or epoxy pastes;thus,prohibiting their use in flexible and wearable devices,and simultaneously limiting their integration into existing optoelectronic ***,we demonstrate that mechanically flexible and optically transparent microwave antennas with high operational efficiencies can be readily fabricated using composite nanolayers deposited on common plastic *** composite nanolayer structure consists of an ultra-thin copper-doped silver film sandwiched between two dielectric films of tantalum pentoxide and aluminum *** material and thickness of each constituent layer are judiciously selected such that the whole structure exhibits an experimentally measured averaged visible transmittance as high as 98.94%compared to a bare plastic substrate,and simultaneously,a sheet resistance as low as 12.5Ω/*** representative types of microwave antennas are implemented:an omnidirectional dipole antenna,unidirectional Yagi-Uda antenna,low-profile patch antenna,and Fabry-Pérot cavity *** devices exhibit great mechanical flexibility with bending angle over 70°,high gain of up to 13.6 dBi,and large radiation efficiency of up to 84.5%.The proposed nano-engineered composites can be easily prepared over large areas on various types of substrates and simultaneously overcome the limitations of poor mechanical flexibility,low electrical conductivity,and reduced optical transparency usually faced by other constituent materials for flexible transparent microwave *** demonstrated flexible microwave antennas have various applications ranging from fifth-generation and vehicular communication systems to bio-signal monitors and wearable electronics.

关键词： Optically transparent antenna Flexible microwave antenna Transparent conductor Ultra-thin silver Doped silver Wearable optoelectronics

来源：评论

学校读者我要写书评

暂无评论

Digital Assistant for Visually Impaired People 5

Digital Assistant for Visually Impaired People

引用

5th International Conference on Advancements in Computing, ICAC 2023

作者： Thayaparan, Thuvaraka Jayakumar, Sanjay Fernando, B.A.I. Ananthanadarajan, Gobisan Abeywardana, Lakmini Kasthurirathna, Dharshana Sri Lanka Institute of Information Technology Department of Information Technology Malabe Sri Lanka Sri Lanka Institute of Information Technology Computer Science and Software Engineering Malabe Sri Lanka

ISBN: (纸本)9798350358131

This research paper presents a comprehensive exploration of various components to enhance the capabilities of a digital assistant tailored for visually impaired individuals. The first component explores how various image captioning architectures and Vision Encoder Decoder models can be used for better environmental interaction. The second component concerns with facial expression recognition for better social interaction and the third component is a currency note identification component that aims to aid visually impaired individuals with cash transaction whilst the final component that explores a voice bot aims to improve a voice bot and how to manage accents, speech accuracy and naturality using modern deep learning techniques. By investigating these components, this research advances assistive technology, empowering visually impaired individuals with a conversational digital assistant that enhances environmental interaction, supports social interactions, and aids in currency identification. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Contextual defeasible reasoning framework for heterogeneous knowledge sources

Contextual defeasible reasoning framework for heterogeneous ...

引用

作者： Mahfooz ul Haque, Hafiz Muhammad Akhtar, Salwa Uddin, Ijaz Department of Software Engineering University of Lahore Lahore Pakistan Department of Computer Science University of Lahore Lahore Pakistan Department of Computer Science City University of Science and Information Technology Peshawar Pakistan University of Lahore Lahore Pakistan

Recent years have witnessed the rapid advances of smart computing paradigms in a ubiquitous environment. These paradigms make human life much easier, comfortable, secure and hassle free. In a smart computing environment, it is a fact that human users interact with the systems dynamically with or without human intervention using different modalities. The core emphasize is given on the intelligent systems that run in a highly decentralized environment with different communication mechanism. Literature highlighted numerous formalisms to bridge the communication modalities for different knowledge sources. Among others, Multi-context System (MCS) has been advocated as one of the most suitable formalism to interlink different contexts (domains) dynamically in the distributed environment. However, interaction of these knowledge sources sometime may produce inconsistent and conflicting results. In this work, we presents a contextual defeasible reasoning based multi-agent formalism to handle the inconsistency issues. This framework relies on the semantic knowledge sources which allow us to model context-aware non-monotonic reasoning agents to infer the desired goals using the extracted rules from the ontologies and handles inconsistencies using conflicting contextual information. We illustrate the validity and correctness of the proposed formalism using a simple case study of a smart healthcare system with the prototypal implementation of the system. © 2021 John Wiley & Sons Ltd.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Autonomous sortie scheduling for carrier aircraft fleet under towing mode

引用

Defence Technology(防务技术) 2025年第1期43卷 1-12页

作者： Zhilong Deng Xuanbo Liu Yuqi Dou Xichao Su Haixu Li Lei Wang Xinwei Wang Department of Engineering Mechanics State Key Laboratory of Structural AnalysisOptimization and CAE Software for Industrial EquipmentDalian University of TechnologyDalian116024China School of Mathematical Sciences Dalian University of TechnologyDalian 116024China Naval Aviation University Yantai 264001China China State Shipbuilding Corporation Systems Engineering Research Institute Beijing 100094China Department of Automation School of Information Science and TechnologyTsinghua UniversityBeijing 100084China

Safe and efficient sortie scheduling on the confined flight deck is crucial for maintaining high combat effectiveness of the aircraft *** primary difficulty exactly lies in the spatiotemporal coordination,i.e.,allocation of limited supporting resources and collision-avoidance between heterogeneous dispatch *** this paper,the problem is investigated in the perspective of hybrid flow-shop scheduling problem by synthesizing the precedence,space and resource ***,eight processing procedures are abstracted,where tractors,preparing spots,catapults,and launching are virtualized as *** analyzing the constraints in sortie scheduling,a mixed-integer planning model is *** particular,the constraint on preparing spot occupancy is improved to further enhance the sortie *** basic trajectory library for each dispatch entity is generated and a delayed strategy is integrated to address the collision-avoidance *** efficiently solve the formulated HFSP,which is essentially a combinatorial problem with tightly coupled constraints,a chaos-initialized genetic algorithm is *** solution framework is validated by the simulation environment referring to the Fort-class carrier,exhibiting higher sortie efficiency when compared to existing *** animation of the simulation results is available at ***/video/BV14t421A7Tt/.The study presents a promising supporting technique for autonomous flight deck operation in the foreseeable future,and can be easily extended to other supporting scenarios,e.g.,ammunition delivery and aircraft maintenance.

关键词： Carrier aircraft Autonomous sortie scheduling Resource allocation Collision-avoidance Hybrid flow-shop scheduling problem

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：