检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Tang, Xin Chen, Qian Weng, Wenjie Liao, Binhan Wang, Jiacheng Cao, Xianbin Li, Xiaohuan Guangxi University Key Laboratory of Intelligent Networking and Scenario System School of Information and Communication Guilin University of Electronic Technology Guilin541004 China The College of Computing and Data Science Nanyang Technological University 639798 Singapore School of Architecture and Transportation Engineering Guilin University of Electronic Technology Guilin541004 China National Engineering Laboratory for Comprehensive Transportation Big Data Application Technology Guangxi Nanning530001 China College of Computing and Data Science Nanyang Technological University 639798 Singapore School of Electronic and Information Engineering The Key Laboratory of Advanced Technology of Near Space Information System Ministry of Industry and Information Technology of China Beihang University Beijing100191 China

Unmanned Aerial Vehicles (UAVs) possess high mobility and flexible deployment capabilities, prompting the development of UAVs for various application scenarios within the Internet of Things (IoT). The unique capabilities of UAVs give rise to increasingly critical and complex tasks in uncertain and potentially harsh environments. The substantial amount of data generated from these applications necessitates processing and analysis through deep neural networks (DNNs). However, UAVs encounter challenges due to their limited computing resources when managing DNN models. This paper presents a joint approach that combines multiple-agent reinforcement learning (MARL) and generative diffusion models (GDM) for assigning DNN tasks to a UAV swarm, aimed at reducing latency from task capture to result output. To address these challenges, we first consider the task size of the target area to be inspected and the shortest flying path as optimization constraints, employing a greedy algorithm to resolve the subproblem with a focus on minimizing the UAV’s flying path and the overall system cost. In the second stage, we introduce a novel DNN task assignment algorithm, termed GDM-MADDPG, which utilizes the reverse denoising process of GDM to replace the actor network in multi-agent deep deterministic policy gradient (MADDPG). This approach generates specific DNN task assignment actions based on agents’ observations in a dynamic environment. Simulation results indicate that our algorithm performs favorably compared to benchmarks in terms of path planning, Age of Information (AoI), energy consumption, and task load balancing. Copyright © 2024, The Authors. All rights reserved.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Federated Graph Learning via Constructing and Sharing Feature Spaces for Cross-Domain IoT

引用

IEEE Internet of Things Journal 2025年

作者： Chen, Jiale Zhuo, Shengda He, Jinchun Qiu, Wangjie Zhang, Qinnan Xiong, Zehui Zheng, Zhiming Tang, Yin Chen, Min Wang, Changdong Huang, Shuqiang Jinan University College of Cyber Security Guangzhou China Beihang University Institute of Artificial Intelligence Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing Beijing100191 China Zhongguancun Laboratory Beijing China Singapore University of Technology and Design Information Systems Technology and Design 487372 Singapore Jinan University School of Management Guangzhou China South China University of Technology School of Computer Science and Engineering Guangzhou China Sun Yat-sen University School of Computer Guangzhou China Jinan University College of Cyber Security of Jinan University China Guangdong Key Laboratory of Data Security and Privacy Preserving Guangzhou China

The Internet of Things (IoT) collects large volumes of diverse data, with graph data as a critical component, and extensively utilizes Federated Graph Learning (FGL) to process this data while preserving data security. However, the graph data collected by different IoT institutions are relatively independent due to various factors (e.g., data collection methods, geographical locations), and data access is restricted to local environments due to privacy constraints, IoT institutions typically possess heterogeneous feature spaces. Aggregating under these conditions could potentially contaminate local graph representations. Unfortunately, most existing FGL methods tend to overlook this issue. To address this challenge, we propose Federated Graph Learning via Constructing and Sharing Features (FedCSF), a novel FGL framework designed to build a globally consistent feature space and share it among IoT institutions. To construct and extract the feature space, we employ an uniform feature initialization across IoT institutions and design an encoder to extract both global and local feature relationships, thereby facilitating effective collaboration across data from different IoT institutions. Furthermore, we introduce an independent adaptive aggregation strategy to eliminate the integration of harmful knowledge, ensuring that the contributions from each IoT institution are effectively integrated into the global model. We theoretically analyze the convergence of FedCSF. To validate the effectiveness of FedCSF, we conducted extensive experiments under various settings (i.e., cross-datasets, and cross-domains), demonstrating its significant advantages of FedCSF in terms of performance, convergence speed, and practical adaptability © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Stacking, Strain-Engineering Induced Altermagnetism, Multipiezo Effect, and Topological State in Two-Dimensional Materials

arXiv

引用

arXiv 2025年

作者： Xun, Wei Liu, Xin Zhang, Youdong Wu, Yin-Zhong Li, Ping Jiangsu Engineering Research Center for Design and Application of Intelligent Detection Equipment School of Electronic Engineering Jiangsu Vocational College of Electronics and Information Huaian223003 China School of Physical Science and Technology Suzhou University of Science and Technology Suzhou215009 China State Key Laboratory for Mechanical Behavior of Materials Center for Spintronics and Quantum System School of Materials Science and Engineering Xi’an Jiaotong University Shaanxi Xi’an710049 China State Key Laboratory for Surface Physics Department of Physics Fudan University Shanghai200433 China State Key Laboratory of Silicon and Advanced Semiconductor Materials Zhejiang University Hangzhou310027 China

Altermagnetism, as a newly identified form of unconventional antiferromagnetism, enables the removal of spin degeneracy in the absence of net magnetization that provides a platform for the low power consumption and ultra-fast device applications. However, the rare attention has been paid to the relationship between stacking, strain and altermagnet, multipiezo effect and topological state. Here, we propose a mechanism to realize the altermagnet, multipiezo effect, and topological state in two-dimensional materials by the stacking and strain engineering. Based on the analysis of symmetry, we find that the spin splitting feature related to the Ut, PTt, MzUt, or MzPTt symmetries in altermagnet multilayers. In addition, we find that the stacking engineering can effectively realize the transform from antiferromagnetism to altermagnetism and semiconductor to metal for the Jauns bilayer V2SeTeO. More interestingly, the strain not only induces an intriguing multipiezo effect, encompassing the piezovalley, piezomagnetism and piezoelectric, but also achieves the abundant topological phase. Our findings offer a generalized direction for manipulating the spin splitting, valley polarization, and topological states, promoting practical application of valleytronic and spintronic devices based on two-dimensional altermagnets. © 2025, CC BY.

关键词： Antiferromagnetism

来源：评论

学校读者我要写书评

暂无评论

TICNet: Three-Branch Real-Time Semantic Segmentation Network with Intensive Compensation of Railway Track Scenes

TICNet: Three-Branch Real-Time Semantic Segmentation Network...

引用

Machine Learning and Computer Application (ICMLCA), International Conference on

作者： Yiwen Bai Lu Yang Lei Zhang Yajing Song School of Transportation Science and Engineering Beihang University Beijing China Tianjin Key Laboratory for Advanced Mechanical System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education (Tianjin University of Technology) Tianjin China Traffic Control Technology Co. Ltd Beijing China

ISBN: (数字)9798331530334

ISBN: (纸本)9798331530341

With the rapid development of railway traffic system, real-time semantic segmentation plays a crucial role in railway track scene monitoring. However, most of the existing methods use lightweight convolution to reduce the computational complexity, which results in reduced accuracy. To solve this problem, this paper proposes a real-time semantic segmentation network called TICNet, which is specifically used for accurate segmentation of railway track scenes. TICNet uses a novel three-branch structure designed for efficient feature extraction and accurate segmentation. Results on the RailSem19 dataset show that TICNet has a segmentation accuracy of 62.36% mIoU with an inference speed of 81.2 FPS, which is significantly better than many existing methods.

关键词： Accuracy Convolution Semantic segmentation Semantics Focusing Machine learning Feature extraction Real-time systems Computational complexity Monitoring

来源：评论

学校读者我要写书评

暂无评论

design, Fabrication, and Characterization of Soft Robotic Claw Inspired by Parrot Feet for Grasping

SSRN

引用

SSRN 2024年

作者： Hao, Tianze Feng, Jingjing Ma, Yue Liu, Songtao Wang, Jutao Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin300384 China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of Technology School of Mechanical Engineering Tianjin300384 China Automation Equipment Company Limited Tianjin301701 China Tianjin University of Technology China

Soft pneumatic actuators (SPAs) have demonstrated the ability to generate contraction, expansion, and bending strokes in three-dimensional space during pressurization. Gripper composed of SPAs are expected to serve as end effectors to improve the adaptability and lightweight of mobile robots in complex environments. In this study, a soft robotic claw inspired by the zygodactyl structure of parrot feet is developed featuring pneu-net actuators with oblique air chambers. These chambers enable bending and twisting movements, ensuring effective contact with the cylindrical landing objects. Integration of a thin steel sheet as the strain limiting layer not only improves static stability, but also augments the output force by approximately 57%, significantly ameliorating the claw’s gripping strength. Comparative gripping tests on diverse everyday items, indicate that while soft claw with vertical chambers adeptly handle centrosymmetric objects, whose with oblique chambers excel at at securing objects with large diameters, making them particularly suitable for perching applications on unmanned aerial vehicles. Moreover, enhancing the actuators with a uniformly soft surface texture, approximately 1.8 mm in height, notably increases friction force, thereby improving grip and stability. Comprehensive static stability assessments on birch logs confirmed its effective gripping and perching capabilities. The proposed soft claw has certain application prospects in situations that require flexible operation and complex grasping tasks due to its lightweight, flexibility, and strong adaptability. © 2024, The Authors. All rights reserved.

关键词： Pneumatic actuators

来源：评论

学校读者我要写书评

暂无评论

Control of Residual Stress in 316l Stainless Steel Manufacturing by Pulsed-Wave Laser

SSRN

引用

SSRN 2023年

作者： Cheng, Manping Zou, Xi Yan, Zhou Liu, Wenyang Song, Lijun Research Institute of Auto Parts Technology Hunan Institute of Technology Hengyang421002 China Hunan University of Science and Technology Xiangtan411201 China School of Information Engineering Hubei University of Economics Wuhan430205 China State Key Laboratory of Advanced Design and Manufacturing for Vehicle Bodies Hunan University Changsha410082 China Hunan Provincial Key Laboratory of Intelligent Laser Manufacturing Hunan University Changsha410082 China

This paper mainly analyzes the typical thermodynamic response (thermal history, thermal strain and residual stress) in conventional continuous-wave laser (CW) during DED. The influence of process parameters (laser power and scanning speed) on the temperature gradient in heat affected zone, thermal strain and residual stress are studied, and the corresponding relationship are established. The results show that a reduction in residual stress can be obtained by decreasing temperature gradient. However, the method of reducing temperature gradient by changing process parameters leads to low forming quality and low density. A pulse-wave laser (PW) is proposed to actively control the residual stress of deposited sample. This laser mode can not only reduce the temperature gradient in the process of DED, but also in-situ release the thermal stress, and corresponding greatly reducing the residual stress. © 2023, The Authors. All rights reserved.

关键词： Residual stresses

来源：评论

学校读者我要写书评

暂无评论

design and Evaluation of a Novel Self-Adaptive Ankle Rehabilitation Exoskeleton with Elastic Modules

Design and Evaluation of a Novel Self-Adaptive Ankle Rehabil...

引用

International Conference on advanced Robotics and Mechatronics (ICARM)

作者： Meng Gao Junpeng Chen Mi Li Jian S. Dai Shenzhen Key Laboratory of Intelligent Robotics and Flexible Manufacturing Systems Southern University of Science and Technology Shenzhen China Centre for Robotics Research King's College London London United Kingdom Key Laboratory of Mechanism Theory and Equipment Design of the Ministry of Education Centre for Advanced Mechanisms and Robotics Tianjin University Tianjin China Chair Professor of Mechanisms and Robotics Centre for Robotics Research King's College London UK

This paper proposes a novel ankle rehabilitation exoskeleton based on the research of human gait cycle, aiming to assist patients with neurological injury to recover quickly. The mechanism consists of two frames equipped with ankle joints and toe joint. The lower limbs and musculature system are correlated to propose the model. Incorporating spring modules are provided on the instep, the bottom of toes and either sides of the ankles which cushions lower limbs and reduces energy consumption. Kinematics and stress analysis are conducted to verify the feasibility of the model. Besides, the simulation, which incorporates the elastic elements and springs, is presented. Finally, the modular facilitates could easy integration with other rehabilitation modules for a comprehensive system. Overall, this research provides theoretical and engineering technical support for developing lower limb rehabilitation robots with adaptive stability, diversified movement functions, and human-computer interaction safety and health under different conditions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Diff9D: Diffusion-Based Domain-Generalized Category-Level 9-DoF Object Pose Estimation

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年第7期47卷 5520-5537页

作者： Jian Liu Wei Sun Hui Yang Pengchao Deng Chongpei Liu Nicu Sebe Hossein Rahmani Ajmal Mian National Engineering Research Center for Robot Visual Perception and Control Technology College of Electrical and Information Engineering School of Robotics and the State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Hunan University Changsha China Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an China Department of Information Engineering and Computer Science University of Trento Trento Italy School of Computing and Communications Lancaster University Lancaster U.K. Department of Computer Science The University of Western Australia Crawley WA Australia

Nine-degrees-of-freedom (9-DoF) object pose and size estimation is crucial for enabling augmented reality and robotic manipulation. Category-level methods have received extensive research attention due to their potential for generalization to intra-class unknown objects. However, these methods require manual collection and labeling of large-scale real-world training data. To address this problem, we introduce a diffusion-based paradigm for domain-generalized category-level 9-DoF object pose estimation. Our motivation is to leverage the latent generalization ability of the diffusion model to address the domain generalization challenge in object pose estimation. This entails training the model exclusively on rendered synthetic data to achieve generalization to real-world scenes. We propose an effective diffusion model to redefine 9-DoF object pose estimation from a generative perspective. Our model does not require any 3D shape priors during training or inference. By employing the Denoising Diffusion Implicit Model, we demonstrate that the reverse diffusion process can be executed in as few as 3 steps, achieving near real-time performance. Finally, we design a robotic grasping system comprising both hardware and software components. Through comprehensive experiments on two benchmark datasets and the real-world robotic system, we show that our method achieves state-of-the-art domain generalization performance.

关键词： Shape Solid modeling Three-dimensional displays Pose estimation Training Robots Grasping Diffusion models Real-time systems Point cloud compression

来源：评论

学校读者我要写书评

暂无评论

Ultra-wideband MIMO Antenna design Based on EBG Structure

Ultra-wideband MIMO Antenna Design Based on EBG Structure

引用

Progress in Electromagnetic Research Symposium (PIERS)

作者： Zhipeng Chen Shijie Huang Zhongxiang Zhang Xianliang Wu Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Anhui University Heifei China Anhui Province Key Laboratory of Simulation and Design for Electronic Information System Hefei Normal University Heifei China

ISBN: (纸本)9781665409889

This paper proposes a low-coupling planar compact four-element ultra-wideband antenna based on the EBG structure for multiple-input multiple-output (MIMO) systems. The MIMO antenna is composed of four miniaturized monopole antenna elements based on the half-cut method and a periodic electromagnetic band gap (EBG) structure. The traditional mushroom-shaped EBG structure is cut into squares and a pair of harpoon-shaped microstrip lines are introduced. Structure to reduce its resonant frequency and increase the band gap width. By loading the improved EBG structure in the middle of the MIMO antenna, the electromagnetic coupling between the components is greatly reduced. In addition, the stop band characteristics in the WLAN band (5.725–5.825GHz) are realized by adding a U-shaped resonant stub to the right side of the feeder of the monopole antenna. The experimental results show that it has a good reflection coefficient in the passband bandwidth range of 2.90–11.7GHz, covering the 3.1–10.6GHz frequency band specified by UWB, the isolation between the components is greater than 15dB, and good envelope correlation. The coefficient ECC is <0.02, which proves that the antenna is a potential candidate for ultra-wideband applications.

关键词： Correlation Resonant frequency Bandwidth Metamaterials Ultra wideband antennas Reflection coefficient Passband

来源：评论

学校读者我要写书评

暂无评论

Time-Domain Transfer Path Analysis Based on Gaussian Process Latent Force Model and Least Squares

SSRN

引用

SSRN 2024年

作者： Zhu, Yu He, Zhicheng Zhou, Enlin L. Li, Eric Chen, Y.J. Gao, H. State Key Laboratory of Advanced Design and Manufacturing Technology for Vehicle Hunan University Changsha410082 China School of Computing Engineering & Digital Technologies Teesside University Middlesbrough United Kingdom Chinese Scholartree Ridge Laboratory China North Vehicle Research Institute Beijing100072 China Liuzhou Wuling New Energy Vehicle Co. Ltd. Guangxi Automobile Group Co. Ltd. Liuzhou545005 China

The appearance of Time-domain transfer path analysis (TPA) has provided an effective means for addressing the issues of noise, vibration, and harshness (NVH) in mechanical systems under transient conditions. However, two primary challenges exist with this approach. Firstly, computing the generalized inverse of the frequency response functions (FRFs) matrix from excitations to indicators is prone to numerical instabilities, leading to ill-conditioned problems. Secondly, the accuracy of time-domain information extracted from existing frequency-domain data is relatively low. These issues diminish the precision of classical time-domain TPA methods in time-domain loads identification and impulse response functions (IRFs) recognition, thereby affecting their accuracy. In this work, we propose a novel time-domain TPA method that integrates the gaussian process latent force model (GPLFM) with the least squares (LS). Initially, this method explores the GPLFM in fluid-structure interaction (FSI) system. Secondly, a genetic algorithm (GA) is utilized to determine optimal parameters of the indicators. Subsequently, the vibration IRFs are identified using the LS. Finally, the contribution of each path to the targets' vibration is calculated using linear convolution, while a Kalman filter without measurement updates predicts the noise contribution. Case studies have demonstrated that the proposed method achieved higher accuracy in time-domain loads identification under multiple loading conditions compared to traditional methods using deconvolution filters. Additionally, the accuracy of calculating the contributions surpasses that of traditional methods employing linear convolution. © 2024, The Authors. All rights reserved.

关键词： Genetic algorithms

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：