检索结果-内蒙古大学图书馆

Digital Twin-Assisted Knowledge Distillation Framework for Heterogeneous Federated Learning

China Communications 2023年第2期20卷 61-78页

作者： Xiucheng Wang Nan Cheng Longfei Ma Ruijin Sun Rong Chai Ning Lu School of Telecommunications Engineering Xidian UniversityXi’an 710071China Chongqing Key Laboratory of Mobile Communications Technology Chongqing University of Posts and TelecommunicationsChongqing 400065China Department of Electrical and Computer Engineering Queen’s UniversityKingston K7L 3N6OntarioCanada

In this paper,to deal with the heterogeneity in federated learning(FL)systems,a knowledge distillation(KD)driven training framework for FL is proposed,where each user can select its neural network model on demand and distill knowledge from a big teacher model using its own private *** overcome the challenge of train the big teacher model in resource limited user devices,the digital twin(DT)is exploit in the way that the teacher model can be trained at DT located in the server with enough computing ***,during model distillation,each user can update the parameters of its model at either the physical entity or the digital *** joint problem of model selection and training offloading and resource allocation for users is formulated as a mixed integer programming(MIP)*** solve the problem,Q-learning and optimization are jointly used,where Q-learning selects models for users and determines whether to train locally or on the server,and optimization is used to allocate resources for users based on the output of *** results show the proposed DT-assisted KD framework and joint optimization method can significantly improve the average accuracy of users while reducing the total delay.

关键词： federated learning digital twin knowledge distillation heterogeneity Q-learning convex optimization

来源：评论

学校读者我要写书评

暂无评论

Exploring advanced feature selection techniques: an application to dialectal Arabic data

引用

International Journal of Information Technology (Singapore) 2024年第7期16卷 4637-4649页

作者： Abdellah, Ait Elouli Ouahi, Hassan Cherrat, El Mehdi Bekkar, Abdellatif Department of Computer Science Laboratory of Innovation in Mathematics and Intelligent Systems Faculty of Applied Sciences Ibn Zohr University Ait Melloul Morocco Laboratory of Innovation in Mathematics and Intelligent SystemsFaculty of Applied Sciences Ibn ZohrUniversity Ait Melloul Morocco Laboratory of Systems Engineering and Information Technology National School of Applied Sciences Ibn Zohr University Agadir Morocco Department of Computer ScienceLIM LaboratoryFaculty of Sciences and Technics Hassan II University of Casablanca Mohammedia Casablanca Morocco

In the field of automated language processing, distinguishing between Moroccan Arabic (Darija) in multilingual contexts is a major challenge. This study addresses this challenge by exploiting feature selection techniques to improve the accuracy of tongue detection. Using a comprehensive methodology integrating various feature selection methods, including TF-idf, CBOW, Word2Vec for feature extraction, LASSO regression, decision trees for machine learning techniques, and statistical feature selection such as ANOVA, Pearson correlation coefficient, and Mutual information, alongside semantic techniques by developing our semantic encoders adapted to Arabic data, we strive to uncover the most important, relevant language features while attenuating the noise. As a result, we have obtained robust results by applying the famous XGBOOST, with conventional extraction methods and SVD as a dimensional reduction method with a very reasonable execution time. Our experimental results highlight the effectiveness of feature selection techniques to reinforce supervised learning tasks. This research not only advances the field of natural language processing but also highlights the central role of feature selection in deciphering complex linguistic landscapes. © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Comparative Analysis Dialect Identification Dimensionality Reduction Moroccan Dialect Arabic NLP Standard Arabic

来源：评论

学校读者我要写书评

暂无评论

Identification of greenhouse temperature system using time series based on the NARX model 3

Identification of greenhouse temperature system using time s...

引用

3rd IEEE International Conference on Electronics, Control, Optimization and computer Science, ICECOCS 2022

作者： Chaimae, Dada Hamidane, Hafsa Guerbaoui, Mohammed Ed-Dahhak, Abdelali Lachhab, Abdeslam Moulay Ismail University Computer Engineering and Intelligent Eletrical Systems Laboratory High School of Technology Meknes Morocco

ISBN: (数字)9781665457231

ISBN: (纸本)9781665457231

An agricultural greenhouse is a temperature-controlled habitat that has the benefit of maintaining a crop-specific climate or producing them independently of the seasons and protects against insects, illnesses, and inclement weather. Regarding the non-linearity of the system, it is necessary to take this into consideration, especially throughout the identification phase. This paper describes a novel technique for the identification phase. In this regard, This paper discusses a new strategy for identifying and predicting the internal temperature of an agricultural greenhouse located in Meknes, Morocco, using a neural network based on a nonlinear autoregressive with external input time series model. In the present study, two algorithms have been used in training. Although the Levenberg-Marquardt has shown better performance and the best accuracy. The comparison between the estimated and simulated data indicates that the NARX (Non-linear Auto-Regressive with external inputs) model is qualified to predict and identify the indoor temperature of the greenhouse with an accurate coefficient of determination equal to 0.998. © 2022 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Volumetric B1+ field homogenization in 7 Tesla brain MRI using metasurface scattering

arXiv

引用

arXiv 2024年

作者： Yoon, Gyoungsub Yu, Sunkyu Lee, Jongho Park, Namkyoo Photonic Systems Laboratory Department of Electrical and Computer Engineering Seoul National University Seoul08826 Korea Republic of Intelligent Wave Systems Laboratory Department of Electrical and Computer Engineering Seoul National University Seoul08826 Korea Republic of Laboratory for Imaging Science and Technology Department of Electrical and Computer Engineering Seoul National University Seoul Korea Republic of

Ultrahigh field magnetic resonance imaging (UHF MRI) has become an indispensable tool for human brain imaging, offering excellent diagnostic accuracy while avoiding the risks associated with invasive modalities. When the radiofrequency magnetic field of the UHF MRI encounters the multifaceted complexity of the brain—characterized by wavelength-scale, dissipative, and random heterogeneous materials—detrimental mesoscopic challenges such as B1+ field inhomogeneity and local heating arise. Here we develop the metasurface design inspired by scattering theory to achieve the volumetric field homogeneity in the UHF MRI. The method focuses on finding the scattering ansatz systematically and incorporates a pruning technique to achieve the minimum number of participating modes, which guarantees stable practical implementation. Using full-wave analysis of realistic human brain models under a 7 Tesla MRI, we demonstrate more than a twofold improvement in field homogeneity and suppressed local heating, achieving better performance than even the commercial 3 Tesla MRI. The result shows a noninvasive generalization of constant intensity waves in optics, offering a universal methodology applicable to higher Tesla MRI. © 2024, CC BY.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Hidden Markov Models:Inverse Filtering,Belief Estimation and Privacy Protection

引用

Journal of systems Science & Complexity 2021年第5期34卷 1801-1820页

作者： LOURENCO Ines MATTILA Robert ROJAS Cristian R. HU Xiaoming WAHLBERG Bo Division of Decision and Control Systems School of Electrical Engineering and Computer ScienceKTH Royal Institute of TechnologyStockholmSweden Division of Optimizations and Systems Theory School of Engineering SciencesKTH Royal Institute of TechnologyStockholmSweden

A hidden Markov model(HMM)comprises a state with Markovian dynamics that can only be observed via noisy *** paper considers three problems connected to HMMs,namely,inverse filtering,belief estimation from actions,and privacy enforcement in such a ***,the authors discuss how HMM parameters and sensor measurements can be reconstructed from posterior distributions of an HMM ***,the authors consider a rational decision-maker that forms a private belief(posterior distribution)on the state of the world by filtering private *** authors show how to estimate such posterior distributions from observed optimal actions taken by the *** the setting of adversarial systems,the authors finally show how the decision-maker can protect its private belief by confusing the adversary using slightly sub-optimal *** range from financial portfolio investments to life science decision systems.

关键词： Belief estimation counter-adversarial systems hidden Markov models inverse decision making inverse filtering

来源：评论

学校读者我要写书评

暂无评论

Defective Microstrip Structure Based Phase Shifter with Reduced Size for Phased Antenna Array Applications 12

Defective Microstrip Structure Based Phase Shifter with Redu...

引用

12th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing systems: Technology and Applications, IDAACS 2023

作者： Khan, Hajra Khan, Shahid Nasir, Jamal Ali Shah, Syed Ahson Dalarsson, Mariana Alibakhshikenari, Mohammad Comsats University Islamabad Department of Electrical and Computer Engineering Pakistan Hanyang University Applied Bioelectronics Laboratory Seoul Korea Republic of School of Electrical Engineering and Computer Science Kth Royal Institute of Technology Stockholm Sweden Universidad Carlos Iii de Madrid Department of Signal Theory and Communications Spain

ISBN: (纸本)9798350358056

In this work, we propose a small-size and low-cost phase shifter based on defective microstrip structure (DMS) technique, with a modified reconfigurable unit cell (MRDMS) for WLAN applications at 5.2 GHz. The phase shifter is made up of an MRDMS unit, created by etching slots on a simple microstrip line with an outline of three bridges. To further increase the phase shift, a T-shaped slot is introduced in the central bridge and PIN diodes on the edges of the outer bridges are used. By switching the diodes on and off, the MRDMS unit cell is capable of operating in a variety of different modes to give a phase shift of 37.71° at 5.2 GHz. Additionally, MRDMS unit cells are cascaded for higher phase shift as required. Cascaded two- and four-cell phase shifters were designed and simulated in HFSS and a parametric study on various parameters was conducted to show the detailed operating properties of the proposed phase shifter. Compared to previously reported research, the present study shows that two cascaded phase shifters introduce 75.08° phase shifts and 151.75°, respectively. To the best of our knowledge, this is the maximum phase shift obtained by a phase shifter based on MRDMS. © 2023 IEEE.

关键词： defected microstrip structure phase shifter reconfigurable microwave system

来源：评论

学校读者我要写书评

暂无评论

Purify Unlearnable Examples via Rate-Constrained Variational Autoencoders 41

Purify Unlearnable Examples via Rate-Constrained Variational...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Yu, Yi Wang, Yufei Xia, Song Yang, Wenhan Lu, Shijian Tan, Yap-Peng Kot, Alex C. Rapid-Rich Object Search Lab Interdisciplinary Graduate Programme Nanyang Technological University Singapore School of Electrical and Electronic Engineering Nanyang Technological University Singapore PengCheng Laboratory Shenzhen China School of Computer Science and Engineering Nanyang Technological University Singapore

Unlearnable examples (UEs) seek to maximize testing error by making subtle modifications to training examples that are correctly labeled. Defenses against these poisoning attacks can be categorized based on whether specific interventions are adopted during training. The first approach is training-time defense, such as adversarial training, which can mitigate poisoning effects but is computationally intensive. The other approach is pre-training purification, e.g., image short squeezing, which consists of several simple compressions but often encounters challenges in dealing with various UEs. Our work provides a novel disentanglement mechanism to build an efficient pre-training purification method. Firstly, we uncover rate-constrained variational autoencoders (VAEs), demonstrating a clear tendency to suppress the perturbations in UEs. We subsequently conduct a theoretical analysis for this phenomenon. Building upon these insights, we introduce a disentangle variational autoencoder (D-VAE), capable of disentangling the perturbations with learnable class-wise embeddings. Based on this network, a two-stage purification approach is naturally developed. The first stage focuses on roughly eliminating perturbations, while the second stage produces refined, poison-free results, ensuring effectiveness and robustness across various scenarios. Extensive experiments demonstrate the remarkable performance of our method across CIFAR-10, CIFAR-100, and a 100-class ImageNet-subset. Code is available at https://***/yuyi-sd/D-VAE. Copyright 2024 by the author(s)

关键词： Variational techniques

来源：评论

学校读者我要写书评

暂无评论

Entropic and Operational Characterizations of Dynamic Quantum Resources

引用

IEEE Transactions on Information Theory 2025年

作者： Ji, Kaiyuan Chitambar, Eric Cornell University School of Electrical and Computer Engineering IthacaNY14850 United States University of Illinois at Urbana-Champaign Coordinated Science Laboratory Department of Electrical and Computer Engineering UrbanaIL61801 United States

We offer new methods for characterizing general closed and convex quantum resource theories, including dynamic ones, based on entropic concepts and operational tasks. We propose a resource-theoretic generalization of the quantum conditional min-entropy, termed the free conditional min-entropy (FCME), in the sense that it quantifies an observer's "subjective"degree of uncertainty about a quantum system given that the observer's information processing is limited to free operations of the resource theory. Using this generalized concept, we provide a complete set of entropic conditions for free convertibility between quantum states or channels in any closed and convex quantum resource theory. We also derive an information-theoretic interpretation for the resource global robustness of a state or a channel in terms of a mutual-information-like quantity based on the FCME. Apart from this entropic approach, we characterize dynamic resources by also analyzing their performance in operational tasks. We construct operationally meaningful and complete sets of resource monotones with these tasks, which enable faithful tests of free convertibility between quantum channels. Finally, we show that every well-defined robustness-based measure of a channel can be interpreted as an operational advantage of the channel over free channels in a communication task. © 1963-2012 IEEE.

关键词： Quantum channel

来源：评论

学校读者我要写书评

暂无评论

A Cyber-Physical Smart Grid Testbed for Validation of GOOSE-Based Protection Strategies

A Cyber-Physical Smart Grid Testbed for Validation of GOOSE-...

引用

2022 IEEE Industry Applications Society Annual Meeting, IAS 2022

作者： Abdelrahman, Mahmoud S. Kharchouf, Ibtissam Alrashide, Abdulmueen Mohammed, Osama A. Florida International University Energy Systems Research Laboratory Department of Electrical and Computer Engineering MiamiFL33174 United States

ISBN: (数字)9781665478151

ISBN: (纸本)9781665478151

Although smart grid technologies bring valuable economic, social, and environmental benefits, testing the combination of heterogeneous and co-existing cyber-physical grid structure with legacy technologies presents many challenges. To overcome these challenges without adversely affecting the real-time environment, testbeds are required to explore, develop, evaluate, and validate security controls and protection algorithms in the power system. This paper presents an improved hardware/software design of the smart grid testbed at the Energy systems Research laboratory, Florida International University. The hardware/software-based system includes implementing protection and control strategies for power systems with industrial-grade commercial devices to represent the holistic real-time operation of smart power grid. By leveraging resources available at FIU's smart grid testbed, an in-depth experimental analysis is performed to demonstrate and verify the successful operation of the GOOSE publish-subscribe protocol towards the substation protection within the smart grid setup. © 2022 IEEE.

关键词： Smart power grids

来源：评论

学校读者我要写书评

暂无评论

Joint Waveform and Passive Beamforming Design for IRS-Aided ISAC via Deep Unfolding 16

Joint Waveform and Passive Beamforming Design for IRS-Aided ...

引用

16th International Conference on Wireless Communications and Signal Processing, WCSP 2024

作者： Zhang, Jifa Liu, Mingqian Tang, Jie Zhao, Nan Niyato, Dusit Wang, Xianbin School of Information and Communication Engineering Dalian University of Technology Dalian China Xidian University State Key Laboratory of Integrated Service Networks Xi'an China School of Electronic and Information Engineering South China University of Technology Guangzhou China School of Computer Science and Engineering Nanyang Technological University Singapore Western University Department of Electrical and Computer Engineering LondonONN6A 5B9 Canada

ISBN: (纸本)9798350390643

Integrated sensing and communication (ISAC) has become a promising technique to alleviate the spectrum congestion via sharing the same spectrum for communication and sensing. Nevertheless, many ISAC schemes encounter the challenges of high complexity. In this paper, we propose a dual-functional waveform design scheme for reconfigurable intelligent surface (RIS) aided ISAC based on deep unfolding learning. Specifically, the weighted sum of multi-user interference energy and waveform discrepancy is minimized via the joint waveform and phase-shift design. We first develop an alternating direction method of multipliers (ADMM) based iterative algorithm to handle the non-convex optimization problem. Then, we develop a deep unfolding neural network (NN), named ADMM-NET, which unfolds the proposed ADMM-based iterative algorithm to a layer-wise architecture. Simulation results verify the effectiveness of the proposed ADMM-NET. © 2024 IEEE.

关键词： Convex optimization

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：