检索结果-内蒙古大学图书馆

Federated Learning With Meta-Layers Training for Privacy-Preserving in Vehicular Consumer Electronics

IEEE Transactions on Consumer Electronics 2024年

作者： Shen, Xiaoyang Li, Haibin Li, Yaqian Zhang, Wenming Alenazi, Mohammed J.F. Agarwal, Kadambri Yanshan University College of Electrical Engineering Hebei Qinhuangdao066000 China Key Laboratory of Industrial Computer Control Engineering of Hebei Province Hebei Qinhuangdao066000 China King Saud University College of Computer and Information Sciences Department of Computer Engineering Riyadh11451 Saudi Arabia ABES Engineering College Department of Computer Science and Engineering Ghaziabad201009 India

Vehicular consumer electronics, such as autonomous vehicles (AVs), need collecting large amounts of private user information, which face the risk of privacy leakage. To protect the privacy of consumers, researchers have proposed to apply federated learning (FL) to privacy-preserving vehicular consumer electronics, that is, leveraging FL for collaborative training of a decision model without exchanging the sensitive information generated by AVs. However, FL generally needs to exchange the gradients of client models periodically with the central server, which can be attacked by adversaries to infer user information. Thereby, it may still face the risk of privacy leakage. To solve that challenge, we put forward a novel FL framework, called FL with Meta-Layers Training (FL-MLT). Instead of exchanging the gradients of the client models, it exchanges, meta-layers with the central servers. Since meta-layers are only a slice of the client models, exchanging them helps protect privacy. On the other hand, they contain meta-knowledge to help the FL training process. In the experiments, we conduct extensive visual classification simulation to evaluate FL-MLT, and the experimental results demonstrate the superior performance of FL-MLT. © 1975-2011 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Ultra-compact and broadband polarization-insensitive mode-order converting power splitter

引用

Chinese Optics Letters 2024年第3期22卷 36-41页

作者：陈浩琪姚润葵汪鹏君符强陈伟伟戴世勋孔德军林健金涛李军戴庭舸杨建义 Faculty of Electrical Engineering and Computer Science Ningbo UniversityNingbo 315211China College of Electrical and Electronic Engineering Wenzhou UniversityWenzhou 325035China College of Science and Technology Ningbo UniversityNingbo 315211China Laboratory of Infrared Materials and Devices The Research Institute of Advanced TechnologiesNingbo UniversityNingbo 315211China Department of Information Science and Electronics Engineering Zhejiang UniversityHangzhou 310027China

A polarization-insensitive mode-order converting power splitter using a pixelated region is presented and investigated in this *** TE_(0)and TM_(0)modes are injected into the input port,they are converted into TE_(1)and TM_(1)modes,which evenly come out from the two output *** finite-difference time-domain method and direct-binary-search optimization algorithm are utilized to optimize structural parameters of the pixelated region to attain small insertion loss,low crosstalk,wide bandwidth,excellent power uniformity,polarization-insensitive property,and compact *** results reveal that the insertion loss,crosstalk,and power uniformity of the fabricated device at 1550 nm are 0.57,-19.67,and 0.094 d B in the case of TE polarization,while in the TM polarization,the relevant insertion loss,crosstalk,and power uniformity are 0.57,-19.40,and 0.11 d *** a wavelength range from 1520 to 1600 nm,for the fabricated device working at TE polarization,the insertion loss,crosstalk,and power uniformity are lower than 1.39,-17.64,and 0.14 *** the case of TM polarization,we achieved an insertion loss,crosstalk,and power uniformity less than 1.23,-17.62,and 0.14 dB.

关键词： integrated optics optical waveguide polarization-insensitive property mode-order converting power splitter

来源：评论

学校读者我要写书评

暂无评论

Experimental Study on Motion Controller based on NN-ARX and ARMAX Actuator Identification for 3-DoF Delta Parallel Robot

Experimental Study on Motion Controller based on NN-ARX and ...

引用

RSI/ISM International Conference on Robotics and Mechatronics (ICROM)

作者： Hasan Jalali Hossein Damavandi Ahmad Kalhor Mehdi Tale Masouleh Human and Robot Interaction Laboratory School of Electrical and Computer Engineering University of Tehran Tehran Iran Faculty of Computer Engineering and Information Technology Sadjad University Mashhad Iran Control and Intelligent Processing Center of Excellence School of Electrical and Computer Engineering University of Tehran Tehran Iran

Today, system identification plays a pivotal role in control science and offering a myriad of applications. This paper places its focus on the identification of actuator models within real-world delta robots for informing controller design. Two identification methods, namely NN-ARX and ARMAX, have been employed to extract the dynamic characteristics of the robot actuators, resulting in dynamic models of these integral components being derived. These dynamic models have been utilized in simulations for controller design, and due to the disparities in the identification models, distinct controllers have been realized. Subsequently, these controllers have been practically implemented on delta robots, and their performances have been subjected to a comprehensive comparative analysis. The results demonstrate that controllers integrating the identified actuator models outperformed those designed without the incorporation of the identification models. In practice, the implementation of controllers based on NN-ARX yielded the most favorable results among all the tested controllers. This research not only underscores the importance of accurate actuator models in control system design but also highlights the superior performance of neural network-based controllers in real-world robotic applications. In particular, the practical results of NN-ARX-based controllers were able to achieve significantly lower RMSE of 2.3562, 1.9531, and 2.1185 for the three motors, respectively, as opposed to the 4.1369, 3.0125, and 3.0363 achieved by the ARMAX-based controllers.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards the Improvement of the Cognitive Process of the Synthesized Speech of Mathematical Expression in MathML: An Eye-Tracking 2

Towards the Improvement of the Cognitive Process of the Synt...

引用

2nd International Conference on Interactive Media, Smart Systems and Emerging Technologies, IMET 2022

作者： Souza, Adriana Freitas, Diamantino Bahia Federal Institute of Education Science and Technology Bahia Brazil Doctoral Program in Digital Media Faculty of Engineering of the University of Porto Porto Portugal Faculty of Engineering of the University of Porto Speech Processing Laboratory Electrical and Computer Engineering Department Porto Portugal

ISBN: (数字)9781665470162

ISBN: (纸本)9781665470162

Being one essential part of the solutions we are developing to provide accessibility for blind persons, synthesized speech of mathematical content, although having evolved in naturalness in recent years, still keeps a characteristic of generating very long outputs, which makes it difficult for a person who uses a screen reader to memorize. Eye-gaze tracking has been useful for studying cognitive processes and student's effort in performing tasks therefore it seems attractive as a means to understand how people analyze, process, and break down extensive math expressions into smaller ones. This understanding can help to build a similar model of auditory rendering of MathML capable of avoiding cognitive overload. Therefore, we carried out an experiment to do a gaze-based analysis of reading and memorizing mathematical expressions. Our sample consisted of fourteen participants, and seven mathematical expressions were used in the experiment. The results showed that the computed complexity of the expressions and the average duration of eye-gaze fixations have a strong and significant relationship. Therefore, we conclude that the complexity variable must always be considered in the speech synthesis process of mathematical expressions. However, when considering why participants requested the repetition of an expression with not larger complexity during the memorization process, a tentative interpretation based on the number of MathML tree nodes and the computed complexity of the expressions was not enough to explain it, indicating that other factors need to be investigated. Although some answers to the research questions were not yet conclusive, we consider this research relevant because it points to directions for the work in order to minimize the cognitive processing and mental load of the synthesized speech rendering of mathematical expressions. © 2022 IEEE.

关键词： Eye tracking

来源：评论

学校读者我要写书评

暂无评论

Joint Optimization of Energy Consumption and Truck Transfer by Stack Allocation in Steel Warehouses

Joint Optimization of Energy Consumption and Truck Transfer ...

引用

2024 China Automation Congress, CAC 2024

作者： Wang, Hongwei Xu, Zhezhuang Wang, Jinlong Chen, Boyu Zhang, Qingdong Wu, Xiuren Xia, Yuxiong College of Electrical Engineering and Automation Fuzhou University Key Laboratory of Industrial Automation Control Technology and Information Processing Education Department of Fujian Province Fuzhou350000 China Sansteel Minguang Co. Ltd. Sanming365000 China Fujian Huading Intelligent Manufacturing Technology Co. Ltd. Fuzhou350000 China

ISBN: (纸本)9798350368604

Due to the continuous growth in steel market demand and the shift towards small batches and multiple varieties, efficient storage management has become a key factor in increasing the profitability of logistics parks. However, the current storage methods, due to the unreasonable allocation of stack positions, still result in energy waste during the dispatch phase and the need for trucks to pick up goods across multiple yards. To address these challenges, this paper proposes a comprehensive optimization scheme to reduce truck transfers and energy consumption in steel product dispatch. First, we constructed an optimization problem model that integrates the spatial layout of the logistics park and order data, aiming to maximize the correlation between steel products within the same yard and reduce the total energy consumption during the dispatch phase. Subsequently, a new algorithm called Enhanced Greedy and Tabu-Assisted Adaptive Large Neighborhood Search (EGTA-ALNS) is introduced. Experimental results demonstrate that the proposed algorithm outperforms existing ones in terms of solving speed and scale. It effectively optimizes energy consumption during steel dispatch and reduces the number of truck transfers. © 2024 IEEE.

关键词： Tabu search

来源：评论

学校读者我要写书评

暂无评论

Robust Feature Selection With Weight Cost Maximin Optimization

Robust Feature Selection With Weight Cost Maximin Optimizati...

引用

IEEE Workshop on Machine Learning for Signal processing

作者： Mohammad Amin Omidi Babak Seyfe Shahrokh Valaee Department of Electrical Engineering Information Theoretic Learning Systems Laboratory (ITLS) Shahed University Tehran Iran Department of Electrical and Computer Engineering University of Toronto Toronto Canada

Recently, applying data-independent random feature extraction methods has been promising for time-series classifications. However, a large portion of the features generated by these methods is redundant. To address this problem, we propose a robust feature selection method that applies a maximin optimization to a weight cost function that makes a trade-off between dimension reduction and preserving the classification accuracy. It can be shown that the weight cost is discrete midpoint convex with respect to the sparsity parameter, and at the same time is concave with respect to the regularization parameter. Based on these findings, we propose an efficient implementation for feature selection with maximin optimization. Our empirical results show that for large classification tasks with a small sample size per class, our feature selection method removes more redundancies than the state-of-the-art methods, while preserving the classification accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Decentralized Federated Graph Learning with Lightweight Zero Trust Architecture for Next-Generation Networking Security

引用

IEEE Journal on Selected Areas in Communications 2025年第6期43卷 1908-1922页

作者： Zhou, Xiaokang Liang, Wei Wang, Kevin I-Kai Yada, Katsutoshi Yang, Laurence T. Ma, Jianhua Jin, Qun Kansai University Faculty of Business Data Science Osaka565-0823 Japan RIKEN Center for Advanced Intelligence Project RIKEN Tokyo103-0027 Japan Hunan University of Technology and Business School of Computer Science Changsha410205 China Xiangjiang Laboratory Changsha410205 China The University of Auckland Department of Electrical Computer and Software Engineering Auckland1010 New Zealand St. Francis Xavier University Department of Computer Science AntigonishNSB2G 2W5 Canada Hosei University Faculty of Computer and Information Sciences Chiyoda-ku102-8160 Japan Waseda University Faculty of Human Sciences Tokorozawa359-1192 Japan

The rapid development and usage of digital technologies in modern intelligent systems and applications bring critical challenges on data security and privacy. It is essential to allow cross-organizational data sharing to achieve smart service provisioning, while preventing unauthorized access and data leak to ensure end users' efficient and secure collaborations. Federated Learning (FL) offers a promising pathway to enable innovative collaboration across multiple organizations. However, more stringent security policies are needed to ensure authenticity of participating entities, safeguard data during communication, and prevent malicious activities. In this paper, we propose a Decentralized Federated Graph Learning (FGL) with Lightweight Zero Trust Architecture (ZTA) model, named DFGL-LZTA, to provide context-aware security with dynamic defense policy update, while maintaining computational and communication efficiency in resource-constrained environments, for highly distributed and heterogeneous systems in next-generation networking. Specifically, with a re-designed lightweight ZTA, which leverages adaptive privacy preservation and reputation-based aggregation together to tackle multi-level security threats (e.g., data-level, model-level, and identity-level attacks), a Proximal Policy Optimization (PPO) based Deep Reinforcement Learning (DRL) agent is introduced to enable the real-time and adaptive security policy update and optimization based on contextual features. A hierarchical Graph Attention Network (GAT) mechanism is then improved and applied to facilitate the dynamic subgraph learning in local training with a layer-wise architecture, while a so-called sparse global aggregation scheme is developed to balance the communication efficiency and model robustness in a P2P manner. Experiments and evaluations conducted based on two open-source datasets and one synthetic dataset demonstrate the usefulness of our proposed model in terms of training performance, computa

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning-Based Model for Energy Efficiency Classification of an Unmanned Aerial Vehicle 1

引用

International Conference on Artificial Intelligence and Smart Environment, ICAISE 2022

作者： Awotunde, Joseph Bamidele Arowolo, Micheal Olaolu Imoize, Agbotiname Lucky Farhaoui, Yousef Adeniyi, Abidemi Emmanuel Department of Computer Science Faculty of Information and Communication Sciences University of Ilorin Kwara Ilorin240003 Nigeria Department of Computer Sciences Landmark University Omu-Aran Nigeria Department of Electrical and Electronics Engineering Faculty of Engineering University of Lagos Akoka Lagos100213 Nigeria STI Laboratory T-IDMS Faculty of Sciences and Techniques Moulay Ismail University of Meknès Errachidia Morocco Department of Computer Sciences Precious Cornerstone University Ibadan Nigeria

ISBN: (数字)9783031262548

ISBN: (纸本)9783031262531

One of the most promising technologies for next-generation wireless networks is unmanned aerial vehicles (UAVs). They make excellent prospects for a range of applications due to their accessibility and capacity for establishing line-of-sight interactions with users. Because of the enormous amount of data available, artificial intelligence is rapidly developing and succeeding tremendously. As a result, a sizeable segment of the academic community has started integrating intelligence into the core of UAV networks by using machine learning (ML) approaches to address a range of drone-related problems. ML-based framework is designed to provide solutions to the different issues that have been time invariant when UAVs are utilized for communication. UAV-based delivery systems, real-time multimedia streaming, and intelligent transportation systems are all examples of this. The problems with wifi and security are revealed by this study. ML-based solution techniques are created to address these problems, enabling real-time secure operation of UAVs while leveraging wireless system resources in a flexible manner. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Responding to News Sensitively in Stock Attention Networks via Prompt-Adaptive Trimodal Model

引用

IEEE Transactions on Neural Networks and Learning Systems 2025年第6期36卷 10099-10113页

作者： Haotian Liu Bowen Hu Yadong Zhou Yuxun Zhou Ministry of Education Key Laboratory for Intelligent Networks and Network Security Faculty of Electronic and Information Engineering Xi’an Jiaotong University Xi’an Shaanxi China Department of Electrical Engineering and Computer Sciences University of California at Berkeley Berkeley CA USA

Modern quantitative finance and portfolio-based investment hinge on multimedia news and historical price trends for stock movement prediction. However, prior studies overlook the long tail effect in the feature distribution of stocks, inevitably leading to biased attention and thus degrading the efficiency of utilizing news. To this end, we propose a prompt-adaptive trimodal model (PA-TMM) to overcome the biased stock attention networks and tail feature scarcity problem. In this model, sentiments automatically extracted from trimodal information serve as prompts reflecting the market’s collective mood for other entities, and the interactions among stocks are dynamically inferred for integrating both news- and price-induced movements. By leveraging the movement prompt adaptation (MPA) strategy, our model proactively adapts to the feature-imbalanced phenomenon and converges toward being responsive to the news sensitively. Extensive experiments conducted on real-world datasets consistently demonstrate not only the superiority of the proposed framework over various state-of-the-art baselines, but also its effectiveness, profitability, and robustness in Fintech. The code is accessible at https://***/lauht/PA-TMM .

关键词： Adaptation models Peer-to-peer computing Investment Heavily-tailed distribution Tail Stock markets Feature extraction Correlation Attention mechanisms Time series analysis

来源：评论

学校读者我要写书评

暂无评论

What limits limits?

引用

National Science Review 2021年第1期8卷 11-14页

作者： Yong-Chun Liu Kun Huang Yun-Feng Xiao Lan Yang Cheng-Wei Qiu State Key Laboratory of Low-Dimensional Quantum Physics Department of Physics Frontier Science Center for Quantum Information Tsinghua University Department of Optics and Optical Engineering University of Science and Technology of China State Key Laboratory for Mesoscopic Physics and Frontiers Science Center for Nano-optoelectronics School of Physics Peking University Department of Electrical and Systems Engineering Washington University Department of Electrical and Computer Engineering National University of Singapore

There are fundamental rules and principles setting the limits of physical systems. It triggers an interesting thought—can we break the limits under specific circumstances? A realistic system can only provide limited functionalities because its performance is physically constrained by some fundamental principles.‘Breaking the limit’, which usually implies that the capability of a system could be enhanced significantly,

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：