检索结果-内蒙古大学图书馆

Wireless Federated Learning With Hybrid Local and Centralized Training: A Latency Minimization design

IEEE Journal on Selected Topics in Signal Processing 2023年第1期17卷 248-263页

作者： Huang, Ning Dai, Minghui Wu, Yuan Quek, Tony Q. S. Shen, Xuemin State Key Lab of Internet of Things for Smart City China University of Macau Department of Computer and Information Science China University of Macau State Key Laboratory of Internet of Things for Smart City The Department of Computer and Information Science China Zhuhai Um Science and Technology Research Institute Zhuhai519031 China Singapore University of Technology and Design Information Systems Technology and Design Pillar 487372 Singapore National Cheng Kung University Taiwan University of Waterloo Department of Electrical and Computer Engineering WaterlooONN2L 3G1 Canada

Wireless federated learning (FL) is a collaborative machine learning (ML) framework in which wireless client-devices independently train their ML models and send the locally trained models to the FL server for aggregation. In this paper, we consider the coexistence of privacy-sensitive client-devices and privacy-insensitive yet computing-resource constrained client-devices, and propose an FL framework with a hybrid centralized training and local training. Specifically, the privacy-sensitive client-devices perform local ML model training and send their local models to the FL server. Each privacy-insensitive client-device can have two options, i.e., (i) conducting a local training and then sending its local model to the FL server, and (ii) directly sending its local data to the FL server for the centralized training. The FL server, after collecting the data from the privacy-insensitive client-devices (which choose to upload the local data), conducts a centralized training with the received datasets. The global model is then generated by aggregating (i) the local models uploaded by the client-devices and (ii) the model trained by the FL server centrally. Focusing on this hybrid FL framework, we firstly analyze its convergence feature with respect to the client-devices' selections of local training or centralized training. We then formulate a joint optimization of client-devices' selections of the local training or centralized training, the FL training configuration (i.e., the number of the local iterations and the number of the global iterations), and the bandwidth allocations to the client-devices, with the objective of minimizing the overall latency for reaching the FL convergence. Despite the non-convexity of the joint optimization problem, we identify its layered structure and propose an efficient algorithm to solve it. Numerical results demonstrate the advantage of our proposed FL framework with the hybrid local and centralized training as well as our proposed alg

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

A New Mutimodel approach for modelling of fractional order interval transfer functions 20

A New Mutimodel approach for modelling of fractional order i...

引用

20th International Multi-Conference on systems, Signals and Devices, SSD 2023

作者： Talmoudi, Samia Ksouri, Moufida Lahmari Applied College Department of Computer Science University of Tabuk Tabuk Saudi Arabia University of Tunis El Manar National Engineering School of Tunis LR11ES20 Analysis Design and Control of Systems Laboratory Tunis1002 Tunisia

ISBN: (纸本)9798350332568

This paper is focused on uncertain fractional order systems. In this context, a new modelling approach of uncertain fractional order systems represented by an explicit fractional order interval transfer function is proposed. This approach is based, essentially, on multimodel approach. In fact, firstly, two new determination methods of models' library, inspired from the Kharitonov approach, are exposed. Then, we propose to compute the validity degree of each model of the obtained library, by optimizing a constrained least squares problem. The global model is, finally deduced by fusion of outputs of the different library' models. To prove its efficiency and its precision, the proposed approach is then compared to the approximation approach of Oustaloup through two simulation examples. © 2023 IEEE.

关键词： Transfer functions

来源：评论

学校读者我要写书评

暂无评论

3D Contour Generation based on Diffusion Probabilistic Models

3D Contour Generation based on Diffusion Probabilistic Model...

引用

International Conference on computer Supported Cooperative Work in design

作者： Yiqi Wu Xuan Huang Kelin Song Fazhi He Dejun Zhang The Hubei Key Laboratory of Intelligent Geo-Information Processing China University of Geosciences School of Computer Science Wuhan University Information Systems Technology And Design Pillar Singapore University of Technology and Design

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

The contours of objects effectively represent essential 3D information such as shapes and boundaries. Existing contour detection methods mostly rely on thresholding or neural networks to classify points as edge or non-edge points. However, these methods often lack generalization ability on datasets with different shapes, leading to issues such as missing contours and discontinuous distribution. To address this, we propose a 3D point cloud contour generation method based on the denoising diffusion probabilistic model (DDPM). Our method treats the complete point cloud as an explicit condition to guide the generation of contour from noise. Specifically, our method trains the DDPM to be a conditional generative network customized for contour generation tasks. In the network, we design the Conditional Feature Extraction (CFE) module that obtains multi-scale feature information, and the Conditional Feature Fusion (CFF) module embeds this information in the generation process to guide contour generation. The experimental results demonstrate the effectiveness of our method. The source code of our method is available at: https://***/djzgroup/ContourGeneration.

关键词： Point cloud compression Three-dimensional displays Shape Source coding Noise reduction Noise Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Visual Sensitivity Aware Rate Adaptation for Video Streaming via Deep Reinforcement Learning 23

Visual Sensitivity Aware Rate Adaptation for Video Streaming...

引用

23rd IEEE International Conference on High Performance Computing and Communications, 7th IEEE International Conference on Data Science and systems, 19th IEEE International Conference on Smart City and 7th IEEE International Conference on Dependability in Sensor, Cloud and Big Data systems and Applications, HPCC-DSS-SmartCity-DependSys 2021

作者： Dan, Meng Ye, Jin Jiang, Wenchao Shan, Yuanchao Guangxi Key Laboratory of Multi-media Communications and Network Technology Nanning530000 China School of Computer and Electronic Information Guangxi University Nanning530000 China Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore

ISBN: (纸本)9781665494571

Adaptive bitrate (ABR) technology is widely adopted in video streaming to improve quality of experience (QoE). However, existing methods ignore the inherent characteristic of Human Visual System (HVS), i.e., HVS has different sensitivity to the quality distortion of different video content. Therefore, video contents with high visual sensitivity have higher visual importance and need to be allocated more bitrate resources. In this paper, we propose a novel rate adaptive algorithm by incorporating newly-defined visual sensitivity model. More specifically, a set of relevant features are extracted from video content to establish a deep neural network model that accurately reflects the visual sensitivity. The network state, buffer occupancy and visual sensitivity are comprehensively considered under deep reinforcement learning framework to select appropriate bitrate for maximizing QoE. Experimental results show that the proposed algorithm can generate an ABR strategy consistent with visual sensitivity, and improves the perceptual video quality and user QoE by 14.2% and 16.3%, respectively. © 2021 IEEE.

关键词： Visualization Adaptation models Sensitivity Heuristic algorithms Bit rate Reinforcement learning Streaming media

来源：评论

学校读者我要写书评

暂无评论

Positive and unlabeled learning with controlled probability boundary fence 24

Positive and unlabeled learning with controlled probability ...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Changchun Li Yuanchao Dai Lei Feng Ximing Li Bing Wang Jihong Ouyang College of Computer Science and Technology and Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China Information Systems Technology and Design Pillar Singapore University of Technology and Design Singapore

Positive and Unlabeled (PU) learning refers to a special case of binary classification, and technically, it aims to induce a binary classifier from a few labeled positive training instances and loads of unlabeled instances. In this paper, we derive a theorem indicating that the probability boundary of the asymmetric disambiguation-free expected risk of PU learning is controlled by its asymmetric penalty, and we further empirically evaluated this theorem. Inspired by the theorem and its empirical evaluations, we propose an easy-to-implement two-stage PU learning method, namely Positive and Unlabeled Learning with Controlled Probability Boundary Fence (PUL-CPBF). In the first stage, we train a set of weak binary classifiers concerning different probability boundaries by minimizing the asymmetric disambiguation-free empirical risks with specific asymmetric penalty values. We can interpret these induced weak binary classifiers as a probability boundary fence. For each unlabeled instance, we can use the predictions to locate its class posterior probability and generate a stochastic label. In the second stage, we train a strong binary classifier over labeled positive training instances and all unlabeled instances with stochastic labels in a self-training manner. Extensive empirical results demonstrate that PUL-CPBF can achieve competitive performance compared with the existing PU learning baselines.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Application of Extreme Learning Machine for Shunt Faults Detection and Classification in Three-phase Transmission Line systems 3

Application of Extreme Learning Machine for Shunt Faults Det...

引用

3rd IEEE International Conference on Signal, Control and Communication, SCC 2023

作者： Assadi, Khaoula Slimane, Jihane Ben Salhi, Salah University of Tunis El Manar National Engineering School of Tunis LR11ES20 Analysis Design and Control of Systems Laboratory Tunis1002 Tunisia Northern Border University Faculty of Computing and InformationTechnology Department of Computer Sciences Rafha91911 Saudi Arabia

ISBN: (纸本)9798350326390

The electrical power transmission lines play a crucial role in maintaining a continuous electricity supply. However, the exposed environment of these lines increases the risks of faults occurrence, necessitating prompt detection, and classification, to eliminate them within a specified time. In light of this, the present study introduces a methodology for the detection and classification of faults in a three-phase transmission line system employing the Extreme Learning Machine (ELM). A 220 kV, 300 km three-phase transmission line system was simulated in MATLAB/Simulink software, where the current and voltage signals were generated under different fault conditions including fault types, fault inception time, and fault resistance. The fundamental components of these signals were used as inputs in the ELM model. Different shunt fault types, including line-to-ground, line-to-line, double-line-to-ground, triple-line, and triple-line-to-ground were applied for fault detection and classification framework. Furthermore, the optimum number of hidden neurons in the ELM model was investigated in this study. In terms of the Mean Squared Error (MSE) and correlation coefficient, four ELM variants based on Sine, Sigmoid, Radial Basis, and Triangular Basis transfer functions were assessed for each module. The outcome of these metrics indicates that the ELM with the sigmoid model demonstrated superior performance compared to the other ELM models. Based on statistical metrics MSE, Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE), and also the computational time, the efficiency of ELM-Sigmoid and state-of-the-art methods of Multi-Layer Perceptron Neural Network (MLPNN) and Radial Basis Function Neural Network (RBFNN) were compared and analyzed during training and testing phases. The results obtained revealed that the ELM-Sigmoid model outperforms the other models in the detection and classification of shunt faults with significant accuracy and fast computational speed. ©

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

How to design a R-D Model for UAV Video Transmission? 15

How to Design a R-D Model for UAV Video Transmission?

引用

15th IEEE International Conference on Wireless Communications and Signal Processing, WCSP 2023

作者： Yu, Zongyang Yang, Peng Cao, Xianbin Zheng, Dezhi Quek, Tony Q. S. Oliver Wu, Dapeng Beihang University School of Electronic Information Engineering Beijing China Peng Cheng Laboratory Department of Mathematics and Theories Shenzhen China Beijing Institute of Technology Advanced Research Institute of Multidisciplinary Sciences Beijing China Singapore University of Technology and Design Information Systems Technology and Design Singapore City University of Hong Kong Department of Computer Science Kowloon Hong Kong

ISBN: (纸本)9798350324662

Unmanned aerial vehicle (UAV) video transmission has been extensively applied in many crucial fields. However, the problem of designing a rate-distortion (R-D) model for UAV video transmission, which is essential for theoretical analysis of video coding and optimization of video transmission quality, is under-studied. The designed R-D model is desired to be simple, accurate, and generic owing to the limited capability of the UAV. Observing the key role of transformed residuals in the R-D model, this paper elaborately discusses the modeling of the transformed residual distribution and proposes an estimation algorithm to estimate the statistical parameter of the distribution. Specifically, considering the stringent requirements for low complexity and high generalization capability, we first design a linear parameter estimator by mining and analyzing UAV video statistical characteristics. Further, we develop a bias update scheme to improve the accuracy of the estimator. Test results on multiple real video sequences taken by UAVs show that the proposed estimation algorithm is more accurate than benchmarks. © 2023 IEEE.

关键词： expectation maximization algorithm R-D model rate control video coding Video transmission

来源：评论

学校读者我要写书评

暂无评论

Online Learning in Blockchain-based Energy Trading systems 24

Online Learning in Blockchain-based Energy Trading Systems

引用

2024 International Symposium on Theory, Algorithmic Foundations, and Protocol design for Mobile Networks and Mobile Computing, MobiHoc 2024

作者： Liu, Yunshu Cheung, Man Hon Huang, Jianwei Pillar of Engineering Systems and Design Singapore University of Technology and Design Singapore Singapore Department of Computer Science City University of Hong Kong Hong Kong School of Science and Engineering Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen Key Laboratory of Crowd Intelligence Empowered Low-Carbon Energy Network CSIJRI Joint Research Centre on Smart Energy Storage The Chinese University of HongKong Guangdong Shenzhen518172 China

ISBN: (纸本)9798400705212

In this paper, we consider a blockchain-based energy trading (BBET) system with the proof-of-stake (PoS) protocol. The system designer aims to minimize system cost by considering the prosumers’ strategic token allocation between blockchain staking and energy purchase for their applications. This is challenging as the system designer does not know prosumers’ private information of impatience levels towards different applications. To this end, we propose an online learning mechanism (OLM), which includes incentive mechanisms to guide both prosumers’ private information reporting and staking decisions in two phases. In the exploration phase, we design a randomized staking reward to encourage prosumers’ truthful reporting of their private information for the learning of impatience level distributions. Based on the threshold structure of the prosumers’ equilibrium staking strategies, in the exploitation phase, we propose a learning-error-based reward to minimize the system cost considering the finite-sample bias. By characterizing the optimal exploration duration, we prove that OLM achieves an asymptotic zero-regret against the complete information benchmark, with the regret bounded by O(3√lnT/T) when operating for T time slots. We implement the corresponding smart contract in Ethereum to demonstrate the feasibility of our approach. Experiment results show that our mechanism reduces regret by an average of 74% compared to the state-of-art mechanism. © 2024 Copyright held by the owner/author(s).

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Software Complex and Mathematical Models for Technological design of Ozone-safe Chladones Synthesis Processes

Software Complex and Mathematical Models for Technological D...

引用

International Conference on Control systems, Mathematical Modelling, Automation and Energy Efficiency (SUMMA)

作者： Tamara Balabekovna Chistyakova Inna Vasilievna Novozhilova Dmitriy Vsevolodovich Doctorov Anastasia Valerievna Egorova Olga Evgenievna Bezdudnaya Computer-Aided Design and Control Systems Department World-class Laboratory Saint-Petersburg State Institute of Technology Saint-Petersburg Russia Russian Research Center Applied Chemistry (GIPH) JSC Design Institute Saint-Petersburg Russia World-class Laboratory Saint-Petersburg State Institute of Technology Saint-Petersburg Russia Computer-Aided Design and Control Systems Department Saint-Petersburg State Institute of Technology Saint-Petersburg Russia

ISBN: (数字)9798331532178

ISBN: (纸本)9798331532185

The functional structure of the problem-oriented software complex for solving the problem of designing a technological scheme for the multi-product processes for the synthesis of ozone-safe chladones is presented in the article. The inclusion of a customizable relational database of chladone characteristics in the software complex allows selecting equipment (working volumes of reactors) to form a production flow chart based on specified criteria (productivity, energy consumption, output concentrations of the target and by-products, etc.). The mathematical models library is the basis of the software complex. Mathematical models allow performing verification calculations of various reactors for the synthesis of a wide range of chladones in accordance with the technical specification. The advantage of the software complex is the ability to analyze the effect of contact time and process temperature on the output concentrations of by-products and target products with different compositions of the initial reaction mixture. The use of the software complex allows increasing the efficiency of designing chladones synthesis processes by reducing the time spent on selecting the hardware design of processes that ensure high conversion of raw materials and the required selectivity of processes for the target component.

关键词： Productivity Relational databases Software Mathematical models Raw materials Libraries Hardware Energy efficiency Kinetic theory Inductors

来源：评论

学校读者我要写书评

暂无评论

Improving Generalization of Deep Neural Networks by Optimum Shifting

arXiv

引用

arXiv 2024年

作者： Zhou, Yuyan Li, Ye Feng, Lei Huang, Sheng-Jun MIIT Key Laboratory of Pattern Analysis and Machine Intelligence College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing211106 China Information Systems Technology and Design Pillar Singapore University of Technology and Design Singapore

Recent studies showed that the generalization of neural networks is correlated with the sharpness of the loss landscape, and flat minima suggests a better generalization ability than sharp minima. In this paper, we propose a novel method called optimum shifting, which changes the parameters of a neural network from a sharp minimum to a flatter one while maintaining the same training loss value. Our method is based on the observation that when the input and output of a neural network are fixed, the matrix multiplications within the network can be treated as systems of under-determined linear equations, enabling adjustment of parameters in the solution space, which can be simply accomplished by solving a constrained optimization problem. Furthermore, we introduce a practical stochastic optimum shifting technique utilizing the Neural Collapse theory to reduce computational costs and provide more degrees of freedom for optimum shifting. Extensive experiments (including classification and detection) with various deep neural network architectures on benchmark datasets demonstrate the effectiveness of our method. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep neural networks

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：