检索结果-内蒙古大学图书馆

Segmentation of CAD models using hybrid representation

虚拟现实与智能硬件(中英文) 2025年第2期7卷 188-202页

作者： Claude UWIMANA Shengdi ZHOU Limei YANG Zhuqing LI Norbelt MUTAGISHA Edouard NIYONGABO Bin ZHOU State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijing 100191China Peace-Bay Academy of Virtual Reality Shenyang 110004China China Aerospace Systems Engineering Corporation Beijing 100070China Department of Signal and Information Processing Beihang UniversityBeijing 100191China Department of Computer Science University of SherbrookeSherbrooke J1C0A1Canada

In this paper,we introduce an innovative method for computer-aided design(CAD)segmentation by concatenating meshes and CAD *** previous CAD segmentation methods have achieved impressive performance using single representations,such as meshes,CAD,and point ***,existing methods cannot effectively combine different three-dimensional model types for the direct conversion,alignment,and integrity maintenance of geometric and topological ***,we propose an integration approach that combines the geometric accuracy of CAD data with the flexibility of mesh representations,as well as introduce a unique hybrid representation that combines CAD and mesh models to enhance segmentation *** combine these two model types,our hybrid system utilizes advanced-neural-network techniques to convert CAD models into mesh *** complex CAD models,model segmentation is crucial for model retrieval and *** partial retrieval,it aims to segment a complex CAD model into several simple *** first component of our hybrid system involves advanced mesh-labeling algorithms that harness the digitization of CAD properties to mesh *** second component integrates labelled face features for CAD segmentation by leveraging the abundant multisemantic information embedded in CAD *** combination of mesh and CAD not only refines the accuracy of boundary delineation but also provides a comprehensive understanding of the underlying object *** study uses the Fusion 360 Gallery *** results indicate that our hybrid method can segment these models with higher accuracy than other methods that use single representations.

关键词： B-RepNet hybrid segmentation CAD models classification MeshCNN MeshCAD-Net

来源：评论

学校读者我要写书评

暂无评论

Advances in Robust Federated Learning: A Survey with Heterogeneity Considerations

引用

IEEE Transactions on Big Data 2025年第03期11卷 1548-1567页

作者： Chen, Chuan Liao, Tianchi Deng, Xiaojun Wu, Zihou Huang, Sheng Zheng, Zibin Sun Yat-sen University School of Computer Science and Engineering Guangzhou510006 China Guangdong Key Laboratory of Big Data Analysis and Processing China Sun Yat-sen University School of Software Engineering Zhuhai519000 China Sun Yat-sen University School of Systems Science and Engineering Guangzhou510006 China Zhuhai Key Laboratory of Trusted Large Language Models China

In the field of heterogeneous federated learning (FL), the key challenge is to efficiently and collaboratively train models across multiple clients with different data distributions, model structures, task objectives, computational capabilities, and communication resources. This diversity leads to significant heterogeneity, which increases the complexity of model training. In this paper, we first outline the basic concepts of heterogeneous FL and summarize the research challenges in FL in terms of five aspects: data, model, task, device and communication. In addition, we explore how existing state-of-the-art approaches cope with the heterogeneity of FL, and categorize and review these approaches at three different levels: data-level, model-level, and architecture-level. Subsequently, the paper extensively discusses privacy-preserving strategies in heterogeneous FL environments. Finally, the paper discusses current open issues and directions for future research, aiming to promote the further development of heterogeneous FL. © 2015 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Solving Overlapping Coalition Structure Generation in Task-Based Settings

引用

Journal of Artificial Intelligence Research 2025年 82卷 2125-2166页

作者： Zhang, Guofu Su, Zhaopin Song, Xiaoxiao Gao, Zixuan Li, Miqing Yao, Xin School of Computer Science and Information Engineering Hefei University of Technology Anhui Hefei China Intelligent Interconnected Systems Laboratory of Anhui Province Anhui Hefei China Anhui Province Key Laboratory of Industry Safety and Emergency Technology Anhui Hefei China CERCIA School of Computer Science University of Birmingham Birmingham United Kingdom School of Data Science Lingnan University Hong Kong

The overlapping coalition structure generation problem (OCSGP) is a challenging computational problem in multi-agent systems. It focuses on selecting possibly overlapping coalitions from a set of agents to maximize the social welfare of all coalitions while containing all agents. However, in practical applications, coalitions may be formed to selectively respond to tasks from a pool of potential tasks assigned to agents. Consequently, this study considers OCSGP in a task-based setting, where each agent has finite resources and can only respond to tasks of interest, and each coalition can only take on mutually disjoint subsets of tasks. Specifically, we first present a model of the task-based OCSGP and investigate its computational complexity. Our theoretical results demonstrate that this specific OCSGP remains intractable even under restrictive assumptions. Subsequently, we develop a generic evolutionary algorithm framework (EAF) to find an approximately optimal overlapping coalition structure (OCS) in time quartic polynomial in the size of the instance. Particularly, we devise a specific solution-repair based heuristic of cubic time complexity to generate a feasible OCS. Finally, we compare the proposed EAF with a task-oriented heuristic and a hybrid algorithm for OCSGP, and examine its applicability in the pursuit-evasion problem. The experimental results reveal that the proposed EAF exhibits superior performance in finding feasible OCSs and demonstrates flexible adaptability to problem size and resource status. ©2025 The Authors.

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

SUCP Analysis for Region-Centric UAV-Assisted MEC Networks 20th

SUCP Analysis for Region-Centric UAV-Assisted MEC Networks

引用

20th IFIP WG 10.3 International Conference on Network and Parallel Computing, NPC 2024

作者： Li, Yan Yi, Zhaozhi Long, Qingmin Luo, Lailong Guo, Deke School of Computer and Communication Engineering Changsha University of Science and Technology Changsha410004 China National Key Laboratory of Information Systems Engineering National University of Defense Technology Changsha410073 China

ISBN: (纸本)9789819628636

With the increase of computing-intensive and delay-sensitive applications, mobile edge computing (MEC) technology has sprung up. It effectively satisfies the needs of user equipment (UE) for real-time computing resources by placing servers at the edge of the network. However, traditional MEC infrastructures are constrained by their fixed locations and emergency mobility needs. Unmanned aerial vehicles (UAVs) offer an effective solution with low cost, high mobility, and flexible deployment capabilities. In this paper, we propose a region-centric UAV-assisted MEC model, where the whole network space is divided into a set of hexagonal cells of equal area, and all UAVs in the same cell jointly process UE offloading data. Assume all UAVs are assumed to be equipped with independent MEC servers, and both UAVs and terrestrial UE follow independent homogeneous Poisson point process (PPP) distributions. Using the stochastic geometry analysis framework, we derive the successful uplink communication probability (SUCP) of uplink transmission for users. Finally, we compare the simulation results with the theoretical values to verify the model’s accuracy and evaluate the influence of key performance parameters on the network performance. © IFIP International Federation for Information Processing 2025.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

YFLM: An Improved Levenberg-Marquardt Algorithm for Global Bundle Adjustment 41st

YFLM: An Improved Levenberg-Marquardt Algorithm for Global ...

引用

41st computer Graphics International Conference, CGI 2024

作者： Peng, Jiaxin Li, Tao Jiang, Qin Liu, Jie Wang, Ruibo Laboratory of Software Engineering for Complex Systems School of Computer Science National University of Defense Technology Hunan Changsha410073 China Parallel and Distributed Processing Laboratory School of Computer Science National University of Defense Technology Hunan Changsha410073 China

ISBN: (纸本)9783031820205

The conventional Levenberg-Marquardt (LM) algorithm is a state-of-the-art trust-region optimization method for solving bundle adjustment problems in the Structure-from-Motion community, which not only takes advantage of the fast convergence of the Gauss-Newton method, but also the stability of the gradient descent method when approaching optimal solutions. However, the damping ratio of LM is simply provided by trial-and-error, which causes slow convergence rate for large-scale problems. This paper proposes the Yamashita-Fukushima LM (YFLM) algorithm to reduce the time complexity for global bundle adjustment, where the damping factor is determined by Yamashita and Fukushima’s method. YFLM dynamically calculates a more reasonable and optimal damping ratio according to the newest reprojection error. The experimental results show that the YFLM algorithm outperforms the conventional LM algorithm for most public bundle adjustment datasets. Besides this, the convergence of the YFLM algorithm is also evaluated with different σ∈(0,2]. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Damping

来源：评论

学校读者我要写书评

暂无评论

Laser Scribed CNTs/PEEK/TPU Composites Film for High-performance Stretchable Electrodes

引用

IEEE Sensors Journal 2025年第10期25卷 16666-16674页

作者： Jiang, Caiyun Tang, Lei Hou, Jian Ding, Guqiao Sheng, Bin University of Shanghai for Science and Technology College of Optical Electrical and Computer Engineering Shanghai200093 China Engineering Research Center of Optical Instruments and System Shanghai Key Laboratory of Modern Optical Systems Shanghai200093 China Chinese Academy of Sciences State Key Laboratory of Materials for Integrated Circuits Shanghai Institute of Microsystem and Information Technology Shanghai200050 China

In this paper, an elastic composite material comprising carbon nanotubes (CNTs), polyether-ether-ketone (PEEK), and thermoplastic polyurethane (TPU) is presented, in which direct laser-induced graphitization was used to fabricate high-performance stretchable electrodes. The introduction of CNTs can enhance the conductivity and mechanical strength of the composites, thus improving the overall performance of the sensors. Flexible strain sensors with porous structures were prepared by appropriate encapsulation methods, which exhibited superior gauge factors of 72, 367, and 972 in the 0-30%, 30-44%, and 44-53% strain regions, respectively. Furthermore, it features a rapid response time (100 ms), excellent stability and durability, and is capable of detecting both large-scale human movement and monitoring of small physical signals. In addition, patterned laser-induced graphene interdigital electrodes (LIG-IDEs) were fabricated on composites using laser light. Highly sensitive humidity sensors were obtained using graphene oxide as the humidity-sensing material for respiratory monitoring and non-contact sensing. The thermoplastic properties of TPU allow the straight fiber to be thermoformed into highly stretchable helical electrode, which was of a helix index of 5 and with a high-quality factor (Q=130) at 1250% strain. In conclusion, the preparation of LIG on stretchable composite films by direct laser scribing shows a promising approach for large-scale fabrication of wearable devices. © 2001-2012 IEEE.

关键词： Humidity sensors

来源：评论

学校读者我要写书评

暂无评论

Visible-Infrared Person Re-identification with Real-world Label Noise

引用

IEEE Transactions on Circuits and systems for Video Technology 2025年第5期35卷 4857-4869页

作者： Zhang, Ruiheng Cao, Zhe Huang, Yan Yang, Shuo Xu, Lixin Xu, Min Beijing Institute of Technology State Key Laboratory of Electromechanical Dynamic Control School of Mechatronical Engineering Beijing100081 China Chinese Academy of Sciences New Laboratory of Pattern Recognition State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Beijing100190 China Harbin Institute of Technology School of Computer Science and Technology Harbin150001 China University of Technology Sydney School of Electrical and Data Engineering Faculty of Engineering and Information Technology UltimoNSW2007 Australia

In recent years, growing needs for advanced security and traffic management have significantly heightened the prominence of the visible-infrared person re-identification community (VI-ReID), garnering considerable attention. A critical challenge in VI-ReID is the performance degradation attributable to label noise, an issue that becomes even more pronounced in cross-modal scenarios due to an increased likelihood of data confusion. While previous methods have achieved notable successes, they often overlook the complexities of instance-dependent and real-world noise, creating a disconnect from the practical applications of person re-identification. To bridge this gap, our research analyzes the primary sources of label noise in real-world settings, which include a) instantiated identities, b) blurry infrared images, and c) annotators' errors. In response to these challenges, we develop a Robust Hybrid Loss function (RHL) that enables targeted recognition and retrieval optimization through a more fine-grained division of the noisy dataset. The proposed method categorises data into three sets: clean, obviously noisy, and indistinguishably noisy, with bespoke loss calculations for each category. The identification loss is structured to address the varied nature of these sets specifically. For the retrieval sub-task, we utilize an enhanced triplet loss, adept at handling noisy correspondences. Furthermore, to empirically validate our method, we have re-annotated a real-world dataset, SYSU-Real. Our experiments on SYSU-MM01 and RegDB, conducted under various noise ratios of random and instance-dependent label noise, demonstrate the generalized robustness and effectiveness of our proposed approach. © 1991-2012 IEEE.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

IoT-Enhanced Generative Al for Dynamic Train Control in Virtually Coupled Train Set systems

引用

IEEE Internet of Things Journal 2025年第10期12卷 13415-13427页

作者： Zhu, Li Ye, Zijie Wang, Hongwei Yu, Richard Tao, Tang State Key Laboratory of Advanced Rail Autonomous Operation Beijing Jiaotong University Beijing China Department of Electronics and Information Engineering Beijing Jiaotong University Beijing100044 China Department of Systems and Computer Eng. Carleton University OttawaON Canada

With the rapid development of the Internet of Things (IoT), train control systems have emerged as a successful application scenario. The Virtually Coupled Train Set (VCTS), as a new paradigm for train control, relies on more efficient vehicle-to-vehicle and vehicle-to-ground communication to achieve closer train spacing. This enhanced communication allows trains to capture more complex and detailed state information. However, traditional train control algorithms, limited by their data processing capabilities, often cannot fully utilize this additional information, leading to conservative control strategies to ensure safety and stability. Generative Artificial Intelligence (GAI), particularly generative diffusion models, has recently shown great potential in optimizing IoT scenarios by handling more complex environments. This paper proposes a GAI-based control algorithm framework that leverages diffusion models to optimize train trajectories. By integrating the extensive real-time data generated by IoT systems, the GAI-driven approach enhances decision-making processes, offering more precise and adaptive control strategies tailored to the demands of VCTS. This framework demonstrates the potential of combining IoT data with GAI to achieve higher control accuracy, ensuring safety and performance in dynamic and complex urban rail transit scenarios. Experimental results validate the effectiveness of the proposed method, highlighting its robustness and adaptability across various conditions. © 2025 IEEE. All rights reserved.

关键词： Adaptive control systems

来源：评论

学校读者我要写书评

暂无评论

Enhanced security framework for medical data embedding based on octonionic steganographic transforms and FPGA-accelerated integrity verification

引用

Alexandria engineering Journal 2025年 125卷 480-495页

作者： Tahiri, Mohamed Amine Karmouni, Ilham Mchichou, Ismail Bencherqui, Ahmed El Maloufy, Ahmed Karmouni, Hicham Moustabchir, Hassane Sayyouri, Mhamed Khafaga, Doaa Sami Aldakheel, Eman Abdullah Abouhawwash, Mohamed Engineering Systems and Applications Laboratory National School of Applied Sciences Sidi Mohamed Ben Abdellah University Fez Morocco Laboratory of Electronic Signals and Systems of Information Sidi Mohamed Ben Abdellah University Fez Morocco National School of Applied Sciences Cadi Ayyad University Marrakech Morocco Department of Computer Sciences College of Computer and Information Sciences Princess Nourah bint Abdulrahman University P.O.Box 84428 Riyadh11671 Saudi Arabia Department of Industrial and Systems Engineering King Fahd University of Petroleum and Minerals Dhahran31261 Saudi Arabia King Fahd University of Petroleum and Minerals Dhahran31261 Saudi Arabia

This study suggests a novel approach that combines steganography with innovative image and signal processing techniques to enhance the security and integrity of medical images. We employ octonions, which offer a rich and high-fidelity representation, to encode two medical images. Racah orthogonal polynomials (DORPs), which extract distinctive visual properties and are thus perfect for data concealment, are added to this method to improve it further. We created a verification method utilizing the SHA-256 hashing technique to guarantee data integrity. To identify any manipulation, this method computes the steganographic image's hash both before and after transmission. We used an FPGA-based technology to improve this process, which uses parallel processing to greatly speed up hash computations compared to conventional software techniques. Discrete wavelet decomposition (DWT), quaternion singular value decomposition (QSVD) of the cover picture, and the application of octonionic transforms to concealed images are the main components of our approach. Experimental results demonstrate high-fidelity image reconstruction, with PSNR values up to 40 dB, SSIM scores reaching 0.9900, and strong robustness against various attacks. In particular, the system achieves NC ≥ 0.98 even under geometric transformations such as rotation and scaling, thanks to an integrated geometric correction module based on the Arithmetic Optimization Algorithm (AOA). The FPGA implementation ensures low-latency integrity verification, making the framework suitable for embedded healthcare environments. The proposed solution shows strong potential for protecting sensitive diagnostic data in medical systems, combining mathematical rigor with hardware-level performance. © 2025

关键词： Wavelet decomposition

来源：评论

学校读者我要写书评

暂无评论

Robust Error State Sage-Husa Adaptive Kalman Filter for UWB Localization

引用

IEEE Sensors Journal 2025年第9期25卷 16034-16049页

作者： Juston, Marius Gupta, Soumil Mathur, Shrey Norris, William R. Nottage, Dustin Soylemezoglu, Ahmet University of Illinois Urbana-Champaign The Grainger College of Engineering Industrial and Enterprise Systems Engineering Department UrbanaIL61801 United States University of Illinois Urbana-Champaign The Grainger College of Engineering Electrical and Computer Engineering Department UrbanaIL61801 United States Construction Engineering Research Laboratory U.S. Army Corps of Engineers Engineering Research and Development Center ChampaignIL61822 United States

Given the sensors’ path and interference mitigation capabilities, ultra-wideband (UWB)-based positioning systems have demonstrated high accuracy and reliability. This work aims to improve the Sage-Husa fuzzy adaptive filter (SHFAF) proposed in previous works by modifying the motion model to a 3-D ground-based differential drive robot using IMU and wheel encoder kinematic fused control inputs. In addition to the changed motion model kinematics, this article improved the positive definite constraint on P and R during dynamic estimations, thus making the filter more robust to outliers. An improvement to the computation and derivation of the fuzzy logic system for the SHFAF based on the adaptive neuro-fuzzy inference system (ANFIS) structure was developed, and training the fuzzy system using gradient descent was applied to improve the system’s accuracy. Experimental validation was conducted using real-world data from a Clearpath Jackal robot equipped with Qorvo UWB sensors and static nodes. Regarding localization accuracy, the proposed velocity-based SHFAF (VelSHFAF) system outperformed the previous SHFAF implementation by approximately 30%–25% across two test courses, demonstrating its enhanced performance and reliability. © 2001-2012 IEEE.

关键词： Adaptive filters

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：