检索结果-内蒙古大学图书馆

GridFL: A 3D-Grid-based Federated Learning framework

JOURNAL OF NETWORK AND COMPUTER APPLICATIONS 2025年 236卷

作者： Wu, Jiagao Jiang, Yudong Fan, Zhouli Liu, Linfeng Nanjing Univ Posts & Telecommun Sch Comp Nanjing 210023 Peoples R China Jiangsu Key Lab Big Data Secur & Intelligent Proc Nanjing 210023 Peoples R China

Federated Learning (FL) is an emerging distributed machine learning framework that enables a large number of devices to train machine learning models collaboratively without sharing local data. Despite the extensive potential of FL, in practical scenarios, different characteristics of clients lead to the presence of different heterogeneity in resources, data distribution, and data quantity, which poses a challenge for the training of FL. To address this problem, in this paper, we first conduct an exhaustive experimental study on all three kinds of heterogeneity in FL and provide insights into the specific impact of heterogeneity on training performance. Subsequently, we propose GridFL, a 3D-grid-based FL framework, where the three kinds of heterogeneity are defined as three dimensions (i.e., dimensions of training speed, data distribution, and data quantity) independently, and all clients in FL training are assigned to corresponding cells of the 3D grid by a gridding algorithm based on K-means clustering. In addition, we propose a grid scheduling algorithm with a dynamic selection strategy, which can select an optimal subset of clients to participate in FL training per round by adopting different strategies for different dimensions and cells. The simulation experiments show that GridFL exhibits superior performance in heterogeneous environments and outperforms several related state-of-the-art FL algorithms. Thus, the effectiveness of the proposed algorithms and strategies in GridFL are verified.

关键词： Federated learning Heterogeneity Client selection optimization algorithm Distributed machine learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing electromagnetic tracking: a hybrid pose calculation algorithm and a novel transmitting coil calibration approach

引用

PHYSICA SCRIPTA 2025年第4期100卷 046001-046001页

作者： Wen, Shihan Feng, Yuke Lai, Jiacheng Shi, Jianqiao Yang, Rongqian South China Univ Technol Sch Elect & Informat Engn Guangzhou 510641 Peoples R China Guangdong Hong Kong Macao Joint Lab Millimeter Wav Guangdong Prov Key Lab Millimeter Wave & Terahertz Guangzhou 510641 Peoples R China South China Univ Technol Sch Microelect Guangzhou 510641 Peoples R China Guangzhou Aimooe Technol Co Ltd Guangzhou 510641 Peoples R China

Medical electromagnetic tracking technology offers significant benefits in puncture and interventional surgeries by effectively mitigating obstacles. Traditional optimization-based algorithms for pose estimation in electromagnetic localization often converge to local optima and exhibit slow iterative convergence, which limits their accuracy and efficiency. To address these issues, we propose an enhanced pose estimation algorithm that integrates advanced optimization techniques for receiver sensors. The algorithm successfully converged to the global optimal solution in all test cases and no local optimal solution problem occurred in certain volume, which enables rapid real-time tracking of multiple coils simultaneously, outperforming traditional methods. Furthermore, we have developed a novel calibration method for transmission coils that corrects manufacturing-induced errors in size, position, and orientation. These innovations achieved system positional accuracy of 2.64 mm and directional accuracy of 1.33 degrees within a tracking volume of 350 x 350 x 350 mm3.

关键词： electromagnetic tracking magnetic dipole model optimization algorithm system calibration

来源：评论

学校读者我要写书评

暂无评论

Prediction of compressive strength and porosity of vegetated concrete based on hybrid BP neural networks

引用

MATERIALS TODAY COMMUNICATIONS 2025年 44卷

作者： Li, Qiong Su, Rui Qiao, Hongxia Su, Li Wang, Penghui Gong, Linhan Lanzhou Univ Technol Sch Civil Engn Lanzhou Gansu Peoples R China Gansu Adv Civil Engn Mat Engn Res Ctr Lanzhou 730050 Gansu Peoples R China Shenzhen Univ Coll Civil & Transportat Engn Guangdong Prov Key Lab Durabil Marine Civil Engn Shenzhen 518060 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China

To quickly and accurately obtain the proportions of various raw materials for Vegetated Concrete (VC) based on performance requirements, this study employs a neural network model for forward performance prediction and reverse proportion design. A backpropagation neural network model with a topology of 13-19-2 was designed, and optimized using Ant Colony optimization (ACO), Genetic algorithm (GA), and Bat algorithm (BAT). The input layer includes VC mixing ratio parameters as the amount of aggregate, ceramic granules, pebbles, cement, fly ash, silica fume, nano-SiO2, Anhydrous fluorgypsum, water, water reducer, binder, air-entraining agent, and straw powder, and the output layer includes compressive strength and porosity. The model dataset comprises 182 data points, and a 7:1.5:1.5 data partitioning was used for model development and validation. Correlation analysis was conducted to determine the relationships between raw materials and the mechanical and permeability properties of VC, and a comparative analysis of VC performance evaluation indicators was performed. Principal component analysis(PCA) was adopted to compare the importance and overall scores of different mix proportions. The results showed that the highest correlation coefficients of nano-SiO2 admixture with compressive strength and porosity of vegetated concrete were 0.7 and -0.5, respectively. The ACO-BPNN model demonstrates the highest accuracy in predicting the relationship between the mix proportions, mechanical properties and water permeability of VC, with specific indicators as follows: T1: R2= 0.85, MAE= 0.18, MAPE= 0.02, and RMSE= 0.34;T2: R2= 0.97, MAE= 0.37, MAPE= 0.01, and RMSE= 0.79. Additionally, the 34th mix proportion exhibited the highest performance with a total score of 3.49. Therefore, the ACO-BPNN model can provide scientific guidance for the mix proportion design of VC.

关键词： Vegetated concrete Neural network model optimization algorithm Correlation analysis Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

HEMLAB algorithm Applied to the High-Lift Japan Aerospace Exploration Agency Standard Model

引用

JOURNAL OF AIRCRAFT 2025年第1期62卷 207-218页

作者： Sukas, Hulya Sahin, Mehmet Istanbul Tech Univ Fac Aeronaut & Astronaut TR-34469 Istanbul Turkiye

The high-lift Japan Aerospace Exploration Agency (JAXA) standard model (HL-JSM) has been numerically analyzed in order to further validate the HEMLAB code for realistic aircraft configurations. The numerical algorithm is based on highly efficient edge-based data structure for a vertex-based finite volume algorithm on hybrid meshes. The data pattern is arranged to meet the requirements of a vertex-based finite volume algorithm by considering data access patterns and cache efficiency. A fully implicit version of the numerical algorithm has also been implemented based on the Portable, Extensible Toolkit for Scientific Computation (PETSc) library in order to improve the robustness of the algorithm. The resulting algebraic equations, including the one-equation Spalart-Allmaras, are solved in a monolithic manner using the restricted additive Schwarz preconditioner combined with the flexible generalized minimal residual method [FGMRES(m)] Krylov subspace algorithm. The numerical method is also combined with the metric-based anisotropic mesh refinement library Python Adaptive Mesh Geometry Suite-INRIA (pyAMG) from National Institute for Research in Digital Science and Technology in order to improve the numerical accuracy. The numerical algorithm is initially applied to the two-dimensional L1T2 (National High Lift Programme) high-lift system, and then the calculations around the HL-JSM are carried out at relatively high angles of attack. The numerical results with the anisotropic mesh refinement library pyAMG indicate significant improvements in numerical accuracy.

关键词： algorithms and Data Structures optimization algorithm Aircraft Components and Structure Aerodynamic Force Unsteady Reynolds Averaged Navier Stokes Adaptive Mesh Refinement Computational Fluid Dynamics High Performance Computing Fluid Flow Properties

来源：评论

学校读者我要写书评

暂无评论

A dueling double deep Q network assisted cooperative dual-population coevolutionary algorithm for multi-objective combined economic and emission dispatch problems

引用

SWARM AND EVOLUTIONARY COMPUTATION 2025年 95卷

作者： Yu, Xiaobing Wang, Yuan Zhang, Wen Nanjing Univ Informat Sci & Technol Collaborat Innovat Ctr Forecast & Evaluat Meteorol Nanjing 210044 Peoples R China Nanjing Univ Informat Sci & Technol Sch Management Sci & Engn Res Inst Risk Governance & Emergency Decis Making Nanjing 210044 Peoples R China

With the increasing demand for electricity and the awareness of environmental protection, requirements for economic efficiency and controlling environmental impact of the power system are increasing. However, traditional power system scheduling usually focuses on ensuring the stability of the power supply, which neglects the optimization of cost and emissions. Therefore, combined economic and emission dispatch (CEED) problem is proposed to overcome this challenge. Due to nonlinear and nonconvex objective functions and narrow feasible regions, the optimization of multi-objective CEED problem encounters many difficulties. A dueling double deep Q network-assisted cooperative dual-population coevolutionary algorithm (D3QN-CDCA) is developed to solve multi-objective CEED problems. The proposed algorithm utilizes D3QN to select operators dynamically and adaptively for two populations of coevolutionary algorithm, thus enhancing its adaptability to different practical constrained multi-objective problems and satisfying search needs of different iteration stages. The introduction of D3QN is to overcome the inherent overestimation of DQN and improve the learning efficiency of the network. To comprehensively evaluate its performance, we tested D3QN-CDCA on benchmark function sets and applied it to CEED problems in comparison with other competitive algorithms. Results demonstrate that D3QN-CDCA outperforms existing methods with an average IGD+ ranking of 1.4286 and an average HV ranking of 1.321 in benchmark function sets. Meanwhile, the proposed algorithm achieves an average improvement of 23.86 % in 6unit, 23.12 % in 11-unit and 13.51 % in 14-unit CEED problems. The improvement in solution quality demonstrates the effectiveness of D3QN-CDCA in solving high-dimensional multi-objective optimization problems, particularly in CEED, highlighting its potential for real-world energy management applications.

关键词： Combined economic and emission dispatch Coevolutionary algorithm Deep Q learning optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Set-membership estimation for T-S fuzzy complex networks: a dynamic coding-decoding mechanism

引用

NONLINEAR DYNAMICS 2025年第13期113卷 17041-17056页

作者： Hu, Changzhen Ding, Sanbo Rong, Nannan Hebei Univ Technol Sch Artificial Intelligence Tianjin 300401 Peoples R China Hebei Univ Technol Control Engn Technol Res Ctr Hebei Prov Tianjin 300401 Peoples R China Tiangong Univ Sch Artificial Intelligence Tianjin 300387 Peoples R China

This paper explores the set-membership estimation (SME) of T-S fuzzy complex networks (TSFCNs) under unknown but bounded process and measurement noises. To facilitate digital transmission, a dynamic coding-decoding mechanism is integrated into each communication channel between nodes. It employs a dynamic auxiliary variable to adjust the coding interval. Meanwhile, under a directed communication topology, a fuzzy estimator is designed for each node. This estimator utilizes relative measurement outputs from the node itself and its neighbors to determine an ellipsoidal set that encapsulates the system state at each instant. Furthermore, two optimization problems are formulated to establish sufficient conditions for the desired estimators, ensuring that specified performance requirements are satisfied. Finally, numerical simulations are provided to validate the effectiveness of the SME method for TSFCNs.

关键词： T-S fuzzy complex networks Set-membership estimation Dynamic coding-decoding mechanism optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

optimization algorithmS AND POINT-TO-SET-MAPS

引用

MATHEMATICAL PROGRAMMING 1975年第3期8卷 308-331页

作者： HUARD, P ELECT FRANCE PARIS FRANCE

Two general nonlinear optimization algorithms generating a sequence of feasible solutions are described. The justifications for their convergence are based on the concept of point-to-set mapping continuity. These two algorithms cover many conventional feasible solution methods. The convergence results unify these apparently diverse approaches.

关键词： Mapping Continuity optimization algorithm Feasible Solution Mathematical Method Solution Method

来源：评论

学校读者我要写书评

暂无评论

Efficient and Robust Sparse Linear Discriminant Analysis for Data Classification

引用

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE 2025年第1期9卷 617-629页

作者： Liu, Jingjing Feng, Manlong Xiu, Xianchao Liu, Wanquan Zeng, Xiaoyang Shanghai Univ Sch Microelect Shanghai Key Lab Automobile Intelligent Network In Shanghai 200444 Peoples R China Shanghai Univ Sch Mechatron Engn & Automat Shanghai 200444 Peoples R China Sun Yat Sen Univ Sch Intelligent Syst Engn Guangzhou 528406 Peoples R China Fudan Univ Sch Microelect State Key Lab Integrated Chips & Syst Shanghai 201203 Peoples R China

Sparse linear discriminant analysis (LDA) is a popular machine learning method that improves the accuracy of data classification by introducing sparsity. However, its performance often degrades seriously when encountering noise. To address this issue, this paper proposes a new method called efficient and robust sparse linear discriminant analysis (ERSLDA). The core idea is to characterize the local pixel corruptions by integrating L-p-norm (0< p< 1), and to describe the global structured sparsity by enforcing L-2,L-p-norm (0< p< 1), thereby improving the ability of feature selection. Compared with existing L-1-norm and L-2,L-1-norm, the involved L-p-norm and L-2,L-p-norm can bring higher robustness and better accuracy. Moreover, an additional matrix with Frobenius norm is embedded to represent Gaussian noise, which further enhances the robustness in different scenarios. In algorithms, an iterative optimization scheme is developed based on the alternating direction method of multipliers (ADMM) to solve the proposed ERSLDA, and the resulting subproblems can be calculated efficiently. Extensive numerical comparisons are performed with nine state-of-the-art LDA-based methods on seven benchmark image datasets. The experimental results validate that the proposed method is efficient for data classification and robust to noise.

关键词： Data classification linear discriminant analysis (LDA) L-p-norm optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Structural Deformation Warning Method for Coal Mine Roadway Surrounding Rock Based on Evidential Reasoning

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Zhang, Zehui Liu, Hanfeng Xu, Xiaobin Xie, Zhemin Huo, Huining Chang, Leilei Tao, Zhigang Hangzhou Dianzi Univ China Austria Belt & Rd Joint Lab Artificial Intel Hangzhou 310018 Peoples R China China Univ Min & Technol Beijing State Key Lab Tunnel Engn Beijing 100083 Peoples R China

The structural deformation measuring of coal mine roadways is an effective method to prevent dynamic disasters and avoid loss of civilian life and property. Previous studies on structural deformation early warning, however, failed on multisource uncertain data integration, dynamic adaptability, and limiting the updating ability of models. To address the above issues, this article proposes a structural deformation warning method for coal mine roadway surrounding rock based on evidential reasoning. The evidential reasoning theory is used to construct the models for predicting the deformation value and evaluating the stability level of the surrounding rock through multiple-source data fusion. Moreover, the online optimization mechanism is proposed to improve the performance of the evidence reasoning (ER)-based models. The proposed deformation warning method is evaluated on real coal mine roadway surrounding rock data. Experiment results demonstrate that the proposed method model performs well in deformation prediction with the advantage of dynamic updating and the roadway surrounding stability evaluation.

关键词： Deformation Rocks optimization Monitoring Predictive models Cognition Reliability Linear programming Deformable models Coal mining Coal mine roadway surrounding rock deformation prediction early warning evidential reasoning optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

A CNN-Based Approach for Classical Music Recognition and Style Emotion Classification

引用

IEEE ACCESS 2025年 13卷 20647-20666页

作者： Shi, Yawen Henan Univ Sci & Technol Sch Art & Design Luoyang 471000 Henan Peoples R China

Music recognition refers to the process of automatically recognizing and classifying the musical content in audio signals using computer technology and algorithms. Music recognition technology can help people recognize information such as the music title, artist, musical style, rhythm, and the emotions conveyed by the music in the audio, thus enabling applications like automated music information retrieval and recommendation systems. Classical music, due to its vast quantity, diverse types, and time span covering several centuries, presents challenges that existing music recognition software and traditional music recognition algorithms cannot effectively address. In this study, The model based on convolutional neural networks (CNNs) is proposed, allowing people to recognize the classical music title, style, and emotions contained in a piece of music. The proposed model is particularly beneficial for individuals who are interested in classical music but lack extensive knowledge about it, as it provides essential information about the pieces. By extracting multidimensional features from classical music, the model can recognize the title, style, and emotions expressed. To improve the model's recognition accuracy, various noises are introduced to the dataset. Meanwhile, in this study, a novel loss function has been devised to more effectively assess the model's performance. For searching for optimal performance of the model, a novel optimization algorithm also be proposed to find optimal hyperparameters of loss function. The experiment results show average title recognition accuracy is 0.98, average style recognition accuracy is 0.89 and average emotion recognition accuracy is 0.93. These results adequately demonstrate that the proposal model significantly enhances the model's ability to accurately recognize the titles, styles, and emotions of classical music, achieving high recognition rates even in noisy environments.

关键词： Emotion recognition Accuracy Feature extraction Multiple signal classification Classification algorithms Noise Deep learning Recommender systems Proposals Heuristic algorithms CNN deep learning music recognition music retrieval optimization algorithm

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：