检索结果-内蒙古大学图书馆

A Client Selection Method Based on Loss Function Optimization for Federated Learning

computer Modeling in engineering & sciences 2023年第10期137卷 1047-1064页

作者： Yan Zeng Siyuan Teng Tian Xiang Jilin Zhang Yuankai Mu Yongjian Ren Jian Wan School of Computer Science and Technology Hangzhou Dianzi UniversityHangzhou310018China Key Laboratory of Complex System Modeling and Simulation Ministry of EducationHangzhou310018China Zhejiang Engineering Research Center of Data Security Governance Hangzhou310018China Intelligent Robotics Research Center Zhejiang LabHangzhou311100China HDU-ITMO Joint Institute Hangzhou Dianzi UniversityHangzhou310018China

Federated learning is a distributedmachine learningmethod that can solve the increasingly serious problemof data islands and user data privacy,as it allows training data to be kept locally and not shared with other *** trains a globalmodel by aggregating locally-computedmodels of clients rather than their ***,the divergence of local models caused by data heterogeneity of different clients may lead to slow convergence of the global *** this problem,we focus on the client selection with federated learning,which can affect the convergence performance of the global model with the selected local *** propose FedChoice,a client selection method based on loss function optimization,to select appropriate local models to improve the convergence of the global *** firstly sets selected probability for clients with the value of loss function,and the client with high loss will be set higher selected probability,which can make them more likely to participate in ***,it introduces a local control vector and a global control vector to predict the local gradient direction and global gradient direction,respectively,and calculates the gradient correction vector to correct the gradient direction to reduce the cumulative deviationof the local gradient causedby *** experiments to verify the validity of FedChoice on CIFAR-10,CINIC-10,MNIST,EMNITS,and FEMNIST datasets,and the results show that the convergence of FedChoice is significantly improved,compared with FedAvg,FedProx,and FedNova.

关键词： Federated learning model aggregation Non-IID

来源：评论

学校读者我要写书评

暂无评论

An automatic isotropic/anisotropic hybrid grid generation technique for viscous flow simulations based on an artificial neural network

引用

Chinese Journal of Aeronautics 2022年第4期35卷 102-117页

作者： Peng LU Nianhua WANG Xinghua CHANG Laiping ZHANG Yadong WU School of Information Engineering Southwest University of Science and TechnologyMianyang 621010China School of Intelligent Manufacturing Engineering Chongqing University of Arts and ScienceChongqing 402160China Stake Key Laboratory of Aerodynamics China Aerodynamics Research and Development CenterMianyang 621000China Unmanned Systems Research Center National Innovation Institute of Defense TechnologyBeijing 100071China School of Computer Science and Technology Sichuan University of Science&EngineeringYibin 644005China

Based on the author’s previous research, a novel hybrid grid generation technique is developed by introducing an Artificial Neural Network(ANN) approach for realistic viscous flow simulations. An initial hybrid grid over a typical geometry with anisotropic quadrilaterals in the boundary layer and isotropic triangles in the off-body region is generated by the classical mesh generation method to train two ANNs on how to predict the advancing direction of the new point and to control the grid size. After inputting the initial discretized fronts, the ANN-based Advancing Layer Method(ALM) is adopted to generate the anisotropic quadrilaterals in boundary layers. When the high aspect ratio of the anisotropic grid reaches a specified value, the ANN-based Advancing Front Method(AFM) is adopted to generate isotropic triangles in the off-body computational *** initial isotropic triangles are smoothed to further improve the grid quality. Three typical cases are tested and compared with experimental data to validate the effectiveness of grids generated by the ANN-based hybrid grid generation method. The experimental results show that the two ANNs can predict the advancing direction and the grid size very well, and improve the adaptability of the isotropic/anisotropic hybrid grid generation for viscous flow simulations.

关键词： Advancing front method Advancing layer method Anisotropic quadrilateral grid generation Artificial neural network Isotropic triangular grid generation Machine learning

来源：评论

学校读者我要写书评

暂无评论

Realization of indoor and outdoor localization and navigation for quadruped robots

Realization of indoor and outdoor localization and navigatio...

引用

2022 International Symposium on Biomimetic Intelligence and robotics, ISBIR 2022

作者： Chen, Xin Liu, Dayu Luo, Jiangtao Chen, Teng Zhang, Guoteng Rong, Xuewen Li, Yibin Center for Robotics School of Control Science and Engineering Shandong University China Shandong Youbaote Intelligent Robotics Co. Ltd Shandong China

The quadruped robot has the advantages of flexible movement and large load because of the bionic leg structure. In order to improve their intelligence and autonomy in the complex environment, we build a highly integrated sensing system with lidar and an inertial measurement unit (IMU) on a quadruped robot. After the robot completes the construction of the map, point clouds are aligned using Normal Distribution Transform(NDT) registration to realize the localization of the robot. In the experimental part, we quantitatively tested the accuracy of outdoor localization and also completed indoor-outdoor navigation experiments for the quadruped robot. The experimental results validate the effectiveness of the perception system. © 2022 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0) Peer-review under responsibility of the scientific committee of the Proceedings of International Symposium on Biomimetic Intelligence and robotics.

关键词： Navigation

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Operators Performance Tuning for Changeable Sized Input Data on Tensor Accelerate Hardware

引用

IEEE Transactions on computers 2025年第6期74卷 2101-2113页

作者： Mu, Pengyu Liu, Yi Wang, Rui Liu, Guoxiang An, Hangcheng Zhao, Qianhe Yang, Hailong Xie, Chenhao Luan, Zhongzhi Gong, Chunye Qian, Depei Beihang University School of Computer Science and Engineering Beijing100191 China Beihang University Hangzhou Innovation Institute Hangzhou310051 China Shanghai Artificial Intelligence Laboratory Shanghai200003 China National Supercomputer Center Tianjin300457 China

The operator library is the fundamental infrastructure of deep learning acceleration hardware. Automatically generating the library and tuning its performance is promising because the manual development by well-trained and skillful programmers is costly in terms of both time and money. Tensor hardware has the best computing efficiency for deep learning applications, but the operator library programs are hard to tune because the tensor hardware primitives have many limitations. Otherwise, the performance is difficult to be fully explored. The recent advancement in LLM exacerbates this problem because the size of input data is not fixed. Therefore, mapping the computing tasks of operators to tensor hardware units is a significant challenge when the shape of the input tensor is unknown before the runtime. We propose DSAT, a deep learning operator performance autotuning technique for changeable-sized input data on tensor hardware. To match the input tensor's undetermined shape, we choose a group of abstract computing units as the basic building blocks of operators for changeable-sized input tensor shapes. We design a group of programming tuning rules to construct a large exploration space of the variant implementation of the operator programs. Based on these rules, we construct an intermediate representation of computing and memory access to describe the computing process and use it to map the abstract computing units to tensor primitives. To speed up the tuning process, we narrow down the optimization space by predicting the actual hardware resource requirement and providing an optimized cost model for performance prediction. DSAT achieves performance comparable to the vendor's manually tuned operator libraries. Compared to state-of-the-art deep learning compilers, it improves the performance of inference by 13% on average and decreases the tuning time by an order of magnitude. © 1968-2012 IEEE.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

Nonlinear Model Predictive Control for Optimal Dose Administration in Radiotherapy 15th

Nonlinear Model Predictive Control for Optimal Dose Administ...

引用

15th Advanced Doctoral Conference on Computing, Electrical and Industrial Systems, DoCEIS 2024

作者： Araújo, João C. G. Guerreiro, Bruno J. Oliveira, Luis B. da Silva, Filipe Ferreira CTS-UNINOVA and LASI Department of Electrical and Computer Engineering NOVA School of Science and Technology Caparica2829-516 Portugal Institute for Systems and Robotics LARSyS Lisbon1049-001 Portugal CEFITEC Department of Physics NOVA School of Science and Technology Caparica2829-516 Portugal

ISBN: (纸本)9783031638503

This work discusses the nonlinear modeling of healthy and cancer cell population growth under the influence of radiotherapy, and proposes predictive control techniques to determine the optimal dose for tumor control, while sparing surrounding healthy tissue. Radiation effects are modelled by a linear-quadratic formalism, coupled with a novel population-specific delayed dose response. Numerical simulations of the open- and closed-loop system are conducted, and robustness against model uncertainty is studied. Results illustrate the controller’s performance when dealing with imperfect information and unexpected system behavior, and how it can be tuned to produce the desired treatment outcome. However, optimal operation is conditioned by a limited prediction horizon, as well as strict adherence to treatment schedules and dose restrictions. © IFIP International Federation for Information Processing 2024.

关键词： Nonlinear systems

来源：评论

学校读者我要写书评

暂无评论

Online Queue-Aware Service Migration and Resource Allocation in Mobile Edge Computing

引用

IEEE Transactions on Vehicular Technology 2025年第5期74卷 8063-8078页

作者： Du, An Jia, Jie Chen, Jian Wang, Xingwei Huang, Min Northeastern University School of Computer Science and Engineering The Engineering Research Center of Security Technology of Complex Network System Shenyang110819 China Northeastern University Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Shenyang110819 China Northeastern University College of Information Science and Engineering State Key Laboratory of Synthetical Automation for Process Industries Shenyang110819 China

Mobile edge computing (MEC) integrated with Network Functions Virtualization (NFV) helps run a wide range of services implemented by Virtual Network Functions (VNFs) deployed at MEC networks. This emerging paradigm offers flexible edge resource management for Internet Service Providers (ISPs) and improves service satisfaction of diverse applications. However, a critical challenge lies in processing extremely unpredictable and bursty traffic flow, especially in event-trigger sensing tasks. In this paper, we study queue-aware service migration and resource allocation in an MEC network, where different devices with different arrival patterns request different network services. To this end, we first formulate a novel long-term operation cost minimization problem subject to the stability of multiple queues by adopting a simultaneous migration scheme and determining resource allocation dynamically. To address the problem efficiently, we propose an online control framework to make decisions without any prior system *** first adopt the Lyapunov optimization technique to decompose the long-term optimization problem into multiper-slot subproblems. Then, we adopt a decoupled optimization algorithm based on the coordinate descent method and augmented Lagrangian method to solve the offline mixed integer non-linear programming (MINLP) subproblems. Extensive results reveal that the proposed online optimization framework can efficiently balance queue stability and cost consumption. © 1967-2012 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Semantic-Aware Pseudo-Labeling for Unsupervised Meta-Learning

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年第7期47卷 5475-5488页

作者： Ouyang, Tianran Dong, Xingping Ye, Mang Du, Bo Shao, Ling Shen, Jianbing Wuhan University School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan430072 China University of Chinese Academy of Sciences UCAS-Terminus AI Lab Beijing101408 China University of Macau State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science 314100 China

In unsupervised meta-learning, the clustering-based pseudo-labeling approach is an attractive framework, since it is model-agnostic, allowing it to synergize with supervised algorithms to learn from unlabeled data. However, the pseudo-labels suffer from clustering noise and semantic chaos problems, further impacting the effectiveness of meta-learning. In this paper, we analyze and optimize the pseudo-labeling process, including encoding and clustering, aiming to generate semantic-like pseudo-labels to narrow the gap between unsupervised and supervised meta-learning. First, during the encoding, we observe that the embedding space of existing methods lacks clustering-friendly properties, which is the primary reason for clustering noise. To address this issue, we minimize the inter-to-intra-class similarity ratio to generate clustering-friendly embedding features and validate our approach through comprehensive experiments. Then, during the clustering, we find that the semantic quality of pseudo-labels is not adequately controlled, resulting in semantic chaos of pseudo-labels. We propose a semantic-stability index to measure the semantic quality of pseudo-labels quantitatively. Based on this index, we propose the Semantic-aware Pseudo-label Reassignment mechanism to generate semantic-like pseudo-labels for all samples. Our approach is model-agnostic and can easily be integrated into existing supervised methods. To demonstrate its generalization ability, we integrate it into two representative algorithms: MAML and EP. The results on three main few-shot benchmarks clearly show that the proposed method achieves significant improvement compared to state-of-the-art models. Notably, our approach also outperforms the corresponding supervised method in three tasks. © 1979-2012 IEEE.

关键词： Latent semantic analysis

来源：评论

学校读者我要写书评

暂无评论

Ground-Glass Lung Nodules Recognition Based on CatBoost Feature Selection and Stacking Ensemble Learning

引用

Journal of Shanghai Jiaotong University (science) 2024年 1-10页

作者： Miao, Jun Chang, Yiru Chen, Chen Zhang, Maoxuan Liu, Yan Qi, Honggang Guo, Zhijun Xu, Qian School of Computer Science Beijing Information Science and Technology University Beijing100101 China Pathological Information Engineering Technology Center Jinan Supercomputing Technology Research Institute Jinan250100 China School of Computer Science and Technology University of the Chinese Academy of Sciences Beijing100049 China Department of Radiology Tianjin Kanghui Hospital Tianjin300385 China Department of Radiology Huabei Petroleum General Hospital Hebei Renqiu062550 China

Aimed at the issue of high feature dimensionality, excessive data redundancy, and low recognition accuracy of using single classifiers on ground-glass lung nodule recognition, a recognition method based on CatBoost feature selection and Stacking ensemble learning was proposed. First, the method uses a feature selection algorithm to filter important features and remove features with less impact, achieving the effect of data dimensionality reduction. Second, random forests classifier, decision trees, K-nearest neighbor classifier, and light gradient boosting machine were used as base classifiers, and support vector machine was used as meta classifier to fuse and construct the ensemble learning model. This measure increases the accuracy of the classification model while maintaining the diversity of the base classifiers. The experimental results show that the recognition accuracy of the proposed method reaches 94.375%. Compared to the random forest algorithm with the best performance among single classifiers, the accuracy of the proposed method is increased by 1.875%. Compared to the recent deep learning methods (ResNet+GBM+Attention and MVCSNet) on ground-glass pulmonary nodule recognition, the proposed method’s performance is also better or comparative. Experiments show that the proposed model can effectively select features and make recognition on ground-glass pulmonary nodules. © Shanghai Jiao Tong University 2024.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Process hyper-relation knowledge graph construction and application 7

Process hyper-relation knowledge graph construction and appl...

引用

2024 7th International Conference on Intelligent Manufacturing and Automation, IMA 2024

作者： Lv, Yang Wang, Peiyan Ji, Guiyang Wang, Libang School of Computer Science Shenyang Aerospace University Shenyang110134 China Liaoning Prof. Technology Innovation Center on Knowledge Engineering and Human-Computer Interaction Shenyang110134 China

A knowledge graph enables the structured representation of process knowledge. Traditional knowledge graphs typically represent process fact knowledge by depicting relations between entities. However, higher-order knowledge, such as causality, coupling, and rationale among process facts, should be addressed. The Process Hyper-relational knowledge graph (PHKG) was proposed to address these shortcomings. It comprises three layers: a concept layer representing process concept knowledge, an instance layer representing process fact knowledge, and a hyper-relationship layer representing higher-order knowledge linking process facts. Employing a semi-automatic construction method, a hyper-relation knowledge graph was created with 1, 602 entities, 2, 509 entity relationships, and 231 pairs of hyper-relationships. A process knowledge reasoning algorithm has also been developed to enable applications to reason about process knowledge. © Published under licence by IOP Publishing Ltd.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Detection of False Information in Digital Media Using Blockchain Technology 3

Detection of False Information in Digital Media Using Blockc...

引用

3rd Odisha International Conference on Electrical Power engineering, Communication and Computing Technology, ODICON 2024

作者： Kilaru, Aswini Prasad, L V Narasimha Ghantasala, G S Pradeep Ananthanagu, U. Kallam, Suresh Rajesh Sharma, R. Institute of Aeronautical Engineering Department of Cse Telangana Hyderabad India Alliance College of Engineering and Design Alliance University Department of Computer Science and Engineering Bengaluru India Center of Excellence in Immersive Technologies Alliance University Bengaluru India School of Computer Science and Engineering Jain Deemed to Be University Bengaluru India

ISBN: (纸本)9798350354379

The spreading of false information over the internet, highly impacts society and causes social and economic loss to the nation. One of the most important factors for the increase in the number of misleading information is that all the users of any particular digital platform usually do not verify the authenticity of the information. The principal impartial of this proposed work is to afford a solution to society to reduce the social and economic losses caused by spreading false information circulated digitally. Blockchain is a disseminated, decentralized network that conducts peer-to-peer transactions, meaning that it does not have a central entity to operate. Here we present a literature survey on various approaches towards this problem statement and investigate a Blockchain-based solution that focuses on all types of digital content by providing the end user to validate the information along with the evidence for data that was collected at each step. © 2024 IEEE.

关键词： Distributed ledger

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：