检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Shen, Yehui Zhang, Lei Li, Qingqiu Zhao, Xiongwei Wang, Yue Lu, Huimin Chen, Xieyuanli College of Intelligence Science and Technology National University of Defense Technology China Faculty of Robot Science and Engineering Northeastern University China School of Electronic and Information Engineering Harbin Institute of Technology Shenzhen China State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University China SIASUN Robot& Automation Co. Ltd China School of Computer Science Fudan University China

Visual place recognition (VPR) is crucial for robots to identify previously visited locations, playing an important role in autonomous navigation in both indoor and outdoor environments. However, most existing VPR datasets are limited to single-viewpoint scenarios, leading to reduced recognition accuracy, particularly in multi-directional driving or feature-sparse scenes. Moreover, obtaining additional data to mitigate these limitations is often expensive. This paper introduces a novel training paradigm to improve the performance of existing VPR networks by enhancing multi-view diversity within current datasets through uncertainty estimation and NeRF-based data augmentation. Specifically, we initially train NeRF using the existing VPR dataset. Then, our devised self-supervised uncertainty estimation network identifies places with high uncertainty. The poses of these uncertain places are input into NeRF to generate new synthetic observations for further training of VPR networks. Additionally, we propose an improved storage method for efficient organization of augmented and original training data. We conducted extensive experiments on three datasets and tested three different VPR backbone networks. The results demonstrate that our proposed training paradigm significantly improves VPR performance by fully utilizing existing data, outperforming other training approaches. We further validated the effectiveness of our approach on self-recorded indoor and outdoor datasets, consistently demonstrating superior results. Our dataset and code have been released at https://***/nubot-nudt/UGNA-VPR. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Theory of phase reduction for systems with higher-order interactions: a route to Kuramoto models on hypergraphs

arXiv

引用

arXiv 2025年

作者： León, Iván Muolo, Riccardo Hata, Shigefumi Nakao, Hiroya Department of Applied Mathematics and Computer Science Universidad de Cantabria Santander39005 Spain Department of Systems and Control Engineering Tokyo Institute of Technology Tokyo152-8552 Japan Graduate School of Science and Engineering Kagoshima University Kagoshima890-0065 Japan Research Center for Autonomous Systems Materialogy Institute of Innovative Research Tokyo Institute of Technology Yokohama226-8501 Japan

Phase reduction is a powerful technique in the study of nonlinear oscillatory systems. Under certain assumptions, it allows us to describe each multidimensional oscillator by a single phase variable, giving rise to simple phase models such as the Kuramoto model. Classically, the method has been applied in the case where the interactions are only pairwise (two-body). However, increasing evidence shows that interactions in real-world systems are not pairwise but higher-order, i.e., many-body. Although synchronization in higher-order systems has received much attention, analytical results are scarce because of the highly nonlinear nature of the framework. In this paper, we fill the gap by presenting a general theory of phase reduction for the case of higher-order interactions. We show that the higher-order topology is preserved in the phase reduced model at the first order and that only odd couplings have an effect on the dynamics when certain symmetries are present. Additionally, we show the power and ductility of the phase reduction approach by applying it to a population of Stuart-Landau oscillators with an all-to-all configuration and with a ring-like hypergraph topology;in both cases, only the analysis of the phase model can provide insights and analytical results. © 2025, CC BY-NC-ND.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

HaloFL: Efficient Heterogeneity-Aware Federated Learning Through Optimal Submodel Extraction and Dynamic Sparse Adjustment

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2025年

作者： Lian, Zirui Cao, Qianyue Liang, Chao Cao, Jing Zhu, Zongwei Yang, Zhi Ji, Cheng Li, Changlong Zhou, Xuehai School of Computer Science and Technology University of Science and Technology of China Hefei230026 China Suzhou Institute for Advanced Research University of Science and Technology of China Suzhou215123 China School of Software Engineering University of Science and Technology of China Hefei230026 China Xi'an Modern Control Technology Research Institute China Dfh satellite co. Ltd Cast China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China School of Computer Science and Technology East China Normal University Shanghai200063 China

Federated Learning (FL) is an advanced framework that enables collaborative training of machine learning models across edge devices. An effective strategy to enhance training efficiency is to allocate the optimal submodel based on each device's resource capabilities. However, system heterogeneity significantly increases the difficulty of allocating submodel parameter budgets appropriately for each device, leading to the straggler problem. Meanwhile, data heterogeneity complicates the selection of the optimal submodel structure for specific devices, thereby impacting training performance. Furthermore, the dynamic nature of edge environments, such as fluctuations in network communication and computational resources, exacerbates these challenges, making it even more difficult to precisely extract appropriately sized and structured submodels from the global model. To address the challenges in heterogeneous training environments, we propose an efficient FL framework, namely HaloFL. The framework dynamically adjusts the structure and parameter budget of submodels during training by evaluating three dimensions: model-wise performance, layer-wise performance, and unit-wise performance. First, we design a data-aware model unit importance evaluation method to determine the optimal submodel structure for different data distributions. Next, using this evaluation method, we analyze the importance of model layers and reallocate parameters from non-critical layers to critical layers within a fixed parameter budget, further optimizing the submodel structure. Finally, we introduce a resource-aware dual-UCB multi-armed bandit agent, which dynamically adjusts the total parameter budget of submodels according to changes in the training environment, allowing the framework to better adapt to the performance differences of heterogeneous devices. Experimental results demonstrate that HaloFL exhibits outstanding efficiency in various dynamic and heterogeneous scenarios, achieving up to a 14

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Transforming Healthcare Diagnostics With Tensorized Attention and Continual Learning on Multi-Modal Data

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Iqbal, Saeed Zhong, Xiaopin Khan, Muhammad Attique Shabaz, Mohammad Wu, Zongze AlHammadi, Dina Abdulaziz Liu, Weixiang Algamdi, Shabbab Ali Li, Yang Shenzhen University College of Mechatronics and Control Engineering Shenzhen518060 China Prince Mohammad Bin Fahd University Department of AI Alkhobar Saudi Arabia Model Institute of Engineering and Technology J and K Jammu India Princess Nourah bint Abdulrahman University College of Computer and Information Sciences Department of Information Systems Riyadh11671 Saudi Arabia Prince Sattam bin Abdulaziz University College of Computer Science and Engineering Department of Software Engineering Al Kharj Saudi Arabia Shihezi University College of Mechanical and Electrical Engineering Shihezi832003 China

Analyzing multi-modal medical data in the setting of uncertain healthcare situations continues to be a major topic in medical image analysis and healthcare big data. Traditional machine learning algorithms are severely hampered by inaccurate data fusion, a lack of adaptability to changing patient data, and challenges managing uncertainty. These difficulties are made worse by complicated medical images and diverse data sources, which results in less accurate diagnosis and worse-than-ideal healthcare choices. To tackle these urgent problems, this paper suggests two new approaches: Continual Learning using Progressive Neural Networks (PNNs) and Tensorized Attention Mechanism for Data Fusion. The Tensorized Attention Mechanism improves multi-modal data fusion by using dynamic, task-specific attention to improve feature alignment across modalities, and the PNNs framework uses continual learning, memory augmentation, and domain adaptation to ensure robust learning under data uncertainty. We test these methods on a variety of multi-modal datasets, such as MIMIC-IV, CheXpert, MOST, OAI, and Heart Murmur, which offer a comprehensive representation of medical data from clinical reports, chest X-rays, heart murmurs, and other heterogeneous data sources. Our experimental results show notable improvements in diagnostic performance, with notable results like a CFI of 0.10, a KR score of 90.4%, and an MMC score of 0.097, indicating superior generalization and robustness across domains. Healthcare AI applications could be revolutionized by the use of specialized losses, such as Conditional Variational Autoencoder (CVAE), Adversarial Contrastive Learning (ACL), Reciprocal Regularization, and domain adaptation losses, which are essential for preventing forgetting and guaranteeing learning stability across shifting data streams. © 1975-2011 IEEE.

关键词： Sensor data fusion

来源：评论

学校读者我要写书评

暂无评论

Spectral Clustering and Multi-Modal Stable Matching for Enhanced Management of Photovoltaic Stations and Virtual Power Plants

Spectral Clustering and Multi-Modal Stable Matching for Enha...

引用

International Conference on Green Energy and Applications (ICGEA)

作者： Yang Yang Boon Han Lim Yicheng Xu Yong Zhang Shenzhen Institute of Advanced Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Shenzhen China Lee Kong Chian Faculty of Engineering and Science Universiti Tunku Abdul Rahman Kajang Malaysia Faculty of Computer Science and Control Engineering Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen University of Advanced Technology Shenzhen China

ISBN: (数字)9798331530778

ISBN: (纸本)9798331530785

As renewable energy sources like photovoltaic (PV) stations expand, efficient management and operation are becoming increasingly important for maintaining grid stability and optimizing resource allocation. In this paper, we introduce a novel framework that integrates spectral clustering and multi-modal stable matching to enhance the coordination of PV stations and Virtual Power Plants (VPPs). We begin by applying spectral clustering to group PV stations based on geographic locations and key weather conditions. Our custom-built similarity matrix for PV stations, combined with our theoretical insights, suggests that using fewer eigenvectors in spectral clustering not only reduces computation time but also improves clustering accuracy. This method ensures that each cluster of PV stations shares similar environmental conditions, allowing for more effective collective management. In the second stage, we utilize multi-modal stable matching to assign these PV clusters to VPPs. Unlike traditional stable matching, the multi-modal approach considers multiple factors, such as energy demand, geographic proximity, and VPP capacity, resulting in a more balanced and stable allocation. We validate our approach through experiments on both synthetic and real-world PV station data. The results demonstrate that our framework leads to more accurate grouping of PV stations, facilitating more effective decision-making across multiple criteria. This also enhances work offloading when tasks become intensive on certain nodes. Our work presents a promising solution for managing large-scale renewable energy resources in future power systems, improving both efficiency and stability.

关键词： Photovoltaic systems Energy consumption Stability criteria Clustering algorithms Virtual power plants Power system stability Approximation algorithms Resource management Thermal stability Meteorology

来源：评论

学校读者我要写书评

暂无评论

Leader-Follower Formation Tracking control of Quadrotor UAVs Using Bearing Measurements

arXiv

引用

arXiv 2025年

作者： Doodeman, Sander Tang, Zhiqi Jacinto, Marcelo Cunha, Rita Silvestre, Carlos Department of Mechanical Engineering TU/e Eindhoven University of Technology Eindhoven Netherlands Division of Decision and Control Systems KTH Royal Institute of Technology Sweden Instituto Superior Técnico University of Lisbon Portugal Department of Electrical and Computer Engineering Faculty of Science and Technology University of Macau China

This work addresses the practical problem of distributed formation tracking control of a group of quadrotor vehicles in a relaxed sensing graph topology with a very limited sensor set, where only one leader vehicle can access the global position. Other vehicles in the formation are assumed to only have access to inter-agent bearing (direction) measurements and relative velocities with respect to their neighbor agents. A hierarchical control architecture is adopted for each quadrotor, combining a high-gain attitude inner-loop and an outer-loop bearing-based formation controller with collision avoidance augmentation. The proposed method enables a group of quadrotors to track arbitrary bearing persistently exciting desired formations, including time-varying shapes and rotational maneuvers, such that each quadrotor only requires relative measurements to at least one neighboring quadrotor. The effective performance of the control strategy is validated by numerical simulations in MATLAB and real-world experiments with three quadrotors. © 2025, CC BY-NC-ND.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

EK-Net++: Real-time scene text detection with expand kernel distance and Epoch Adaptive Weight

引用

Expert Systems with Applications 2025年 267卷

作者： Zhu, Boyuan Chen, Xi Tang, Quan Chen, C.L. Philip Liu, Fagui Computer Science and Engineering South China University of Technology Guangzhou510006 China Cyberspace Security Research Center Peng Cheng Laboratory Shenzhen518066 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100080 China

Recently, scene text detection has received significant attention due to its wide applications. Accurate detection in complex scenes of multiple scales, orientations, and curvature remains a challenge. Component-based methods have emerged as the dominant approach for offering a more flexible way to achieve superior performance. However, Component-based methods employ the Vatti clipping algorithm for multi-instance training to handle the difficulty of arbitrary-shaped text. Yet we identify several bias results from these approaches called the "shrinked kernel" leading to decreased accuracy. Additionally, almost all text detection methods fail to consider the characteristics of different datasets and directly assign fixed loss weights to multi-instances. To address these limitations, we propose a new approach named Expand Kernel Network (EK-Net++), which presents the expand kernel distance map to compensate for the previous deficiency and incorporates three-stage regression to complete integral instance detection. Furthermore, we design the Epoch Adaptive Weight algorithm which dynamically distinguishes the characteristics of different datasets. EK-Net++ not only achieves precise positioning of arbitrary-shaped text but also strikes a balance between performance and speed. Evaluation results show that EK-Net++ attains state-of-the-art or competitive performance compared to other advanced methods, e.g., F-measure of 86.72% at 35.42 FPS on ICDAR 2015, F-measure of 85.83% at 40.13 FPS on CTW1500. © 2024 Elsevier Ltd

关键词： Epoch Adaptive Weight Expand kernel distance Real-time Scene text detection

来源：评论

学校读者我要写书评

暂无评论

A Parallel Read-Write Circuit With Fast Amplitude-Adaptive Matching Scheme to Memristor Crossbar Array

引用

IEEE Transactions on Circuits and Systems I: Regular Papers 2025年

作者： Jiang, Ningye Jiang, Mingxuan Huang, Haoen Yang, Le Huang, Yi Zeng, Zhigang Huazhong University of Science and Technology School of Artificial Intelligence and Automation Key Laboratory of Image Information Processing and Intelligent Control Ministry of Education of China Wuhan430074 China Wuhan Institute of Technology School of Electrical and Information Engineering Wuhan430205 China University of Massachusetts Amherst Department of Electrical and Computer Engineering AmherstMA01003 United States

Memristor crossbar array (MCA) is a computing-in-memory (CIM) module for computational acceleration. However, conventional read-write (R-W) circuits for MCA rely heavily on external components and have shortcoming in long writing times. To address these issues, we propose a parallel R-W circuit with a fast amplitude-adaptive matching (AAM) scheme. The fast AAM scheme is designed to accelerate time of writing memristors in MCA by adaptively adjusting the writing voltage to match an optimal amplitude. The architecture of parallel R-W circuit are outlined with the implementation of R-W processes. The design principles of parallel R-W unit, fast AAM unit, and associated control logic are described for analyzing their functions within the circuit. By integrating the parallel R-W circuit with MCA, a computing block is leveraged in a neural network for classification tasks. The experimental results demonstrate that the neural network with multiple computing blocks maintains high accuracy across various datasets (over 80%). Furthermore, the proposed AAM scheme achieves an average 54% reduction in writing time compared to that one without AAM scheme. Compared to the pulse-width scheme, the parallel R-W circuit exhibits an average 3.05× speedup in adjusting a 5×5 MCA, and the speedup efficiency is higher as the increases of MCA size. © 2025 IEEE.

关键词： Memristors

来源：评论

学校读者我要写书评

暂无评论

KKL Observer Synthesis for Nonlinear Systems via Physics-Informed Learning

arXiv

引用

arXiv 2025年

作者： Niazi, M.B. Umar Cao, John Barreau, Matthieu Johansson, Karl Henrik Division of Decision and Control Systems Digital Futures KTH Royal Institute of Technology StockholmSE-100 44 Sweden Laboratory for Information and Decision Systems Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology CambridgeMA02139 United States Department of Electrical Engineering Stanford University StanfordCA94305 United States

This paper proposes a novel learning approach for designing Kazantzis-Kravaris/Luenberger (KKL) observers for autonomous nonlinear systems. The design of a KKL observer involves finding an injective map that transforms the system state into a higher-dimensional observer state, whose dynamics is linear and stable. The observer’s state is then mapped back to the original system coordinates via the inverse map to obtain the state estimate. However, finding this transformation and its inverse is quite challenging. We propose to sequentially approximate these maps by neural networks that are trained using physics-informed learning. We generate synthetic data for training by numerically solving the system and observer dynamics. Theoretical guarantees for the robustness of state estimation against approximation error and system uncertainties are provided. Additionally, a systematic method for optimizing observer performance through parameter selection is presented. The effectiveness of the proposed approach is demonstrated through numerical simulations on benchmark examples and its application to sensor fault detection and isolation in a network of Kuramoto oscillators using learned KKL observers. © 2025, CC BY.

关键词： State estimation

来源：评论

学校读者我要写书评

暂无评论

MRI Brain Tumor Classification Using Optimized APSO-LLRBFNN

MRI Brain Tumor Classification Using Optimized APSO-LLRBFNN

引用

Machine Learning and Autonomous Systems (ICMLAS), International Conference on

作者： Tiruveedula Gopi Krishna Nune Sreenivas M. Ajay Kumar Chandra Sekhar Reddy Davinder Sing Rathee Teklu Urgessa Department of Computer Science and Engineering College of Electrical Engineering and Computing Adama Science and Technology University Adama Ethiopia Department of Electrical and Electronics Engineering Andhra Loyala institute of Engineering and Technology Vijayawada India Department of Electrical Power and Control Engineering College of Electrical Engineering and Computing Adama Science and Technology University Adama Ethiopia Department of ECE College of Electrical Engineering and Computing Adama Science and Technology University Adama Ethiopia

ISBN: (数字)9798331505745

ISBN: (纸本)9798331505752

The research presents a new efficient machine learning method to classify brain tumors because this task remains vital in fighting the high incidence of brain cancers. The proposed approach unites all its operations including image segmentation with feature extraction and classification into a single processing system. This study uses Particle Swarm Optimization (PSO) and Adaptive PSO (APSO) methodologies to optimize Locally Linear Radial Basis Function Neural Network (LLRBFNN) resulting in PSO-LLRBFNN and APSO-LLRBFNN model implementations. The research examined the optimized APSO-LLRBFNN models against Support Vector Machines (SVM) and Least Mean Squares (LMS) based LLRBFNN classifier methods. Results from experiments show that APSO-LLRBFNN gives superior outcomes with 98.93% accuracy and takes 12.23 seconds for execution, which surpasses currently available methods.

关键词： Support vector machines Image segmentation Adaptation models Accuracy Magnetic resonance imaging Machine learning Feature extraction Brain modeling Data models Numerical models

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：