检索结果-内蒙古大学图书馆

SFedXL: Semi-Synchronous Federated Learning With Cross-Sharpness and Layer-Freezing

IEEE Internet of Things Journal 2025年第12期12卷 18692-18707页

作者： Zhao, Mingxiong Zhao, Shihao Feng, Chenyuan Yang, Howard H. Niyato, Dusit Quek, Tony Q. S. Yunnan University National Pilot School of Software Kunming650500 China Ministry of Education Engineering Research Center of Integration and Application of Digital Learning Technology Beijing100039 China Ministry of Education Engineering Research Center of Cyberspace Kunming650504 China Yunnan University of Finance and Economics Yunnan Key Laboratory of Service Computing Kunming650221 China EURECOM Sophia Antipolis06410 France Zhejiang University University of Illinois Urbana-Champaign Institute Zhejiang University Haining314400 China Nanyang Technological University School of Computer Science and Engineering 639798 Singapore Singapore University of Technology and Design Information Systems Technology and Design Pillar 487372 Singapore

Federated learning (FL) emerges as a potential solution for enabling multiple terminal devices to collaboratively accomplish computational tasks within an Unmanned Aerial Vehicle (UAV) swarm. However, traditional FL approaches, predicated on synchronous data aggregation, are not feasible for a UAV swarm owing to the inherently variable and dynamic nature of their communication networks compared with terrestrial systems. Furthermore, the data procured by UAVs is often highly heterogeneous, attributable to disparities in deployment environments and device attributes. Considering the distinct flight paths and unique operational conditions encountered by different UAVs, a considerable amount of data remains unlabeled. To tackle the challenges associated with asynchronous operations and the prevalence of unlabeled data, we introduce a novel framework termed Semi-synchronous FL with Cross-Sharpness and Layer-Freezing (SFedXL), tailored for a UAV swarm. In particular, we devise a cross-sharpness model training strategy aimed at optimizing the utilization of both labeled and unlabeled datasets. Additionally, we propose an innovative semi-synchronous model aggregation protocol, complemented by client-specific layer-freezing and client cluster scheduling, designed to expedite the training process. Our simulation results indicate that the proposed algorithm surpasses current FL methods in terms of object recognition accuracy and communication efficiency, albeit with a trade-off of increased local computation latency. © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Generational Genetic Mechanism of Space Mutagenesis in Rice Based on Multi-Omics

引用

Rice Science 2025年第3期32卷 400-425页

作者： ZENG Deyong CUI Jie YIN Yishu DAI Cuihong YU Wencheng ZHAO Haitian GUAN Shuanghong CHENG Dayou SUN Yeqing LU Weihong Department of Food Science and Engineering School of Medicine and Health Harbin Institute of Technology National and Local Joint Engineering Laboratory for Synthesis Transformation and Separation of Extreme Environmental NutrientsHarbin Institute of Technology The Intelligent Equipment Research Center for the Development of Special Medicine and Food Resources Chongqing Research Institute of Harbin Institute of Technology Environmental Systems Biology Institute Dalian Maritime University

Intergenerational inheritance of stress memory plays a crucial role in plant adaptation to environmental changes, particularly in the context of spaceflight, where plants may serve as a food source for humans on long-duration missions. However, the intergenerational genetic effects of spaceflightinduced stress memory in plants remain unclear. In this study, we assessed the cross-generational genetic effects of spaceflight stress memory using the rice mutant B10, identified during the SJ-10 return satellite mission. Our results showed that the oxidative stress effects induced by spaceflight persisted until the M5 generation in rice. We found that the rice genome remained unstable post-spaceflight, leading to alterations in genome methylation levels. Additionally, we observed significant changes in the methylation levels of transposons, suggesting their involvement in the intergenerational inheritance of spaceflightinduced stress memory. Furthermore, we identified thousands of differentially expressed genes(DEGs) and differentially alternatively spliced(DAS) genes induced by spaceflight stress memory across multiple rice generations. Notably, differentially methylated cytosines were more abundant in non-expressed genes than in DEGs or DAS genes. A substantial number of DEGs and DASs related to oxidative stress were identified, primarily involved in the generation and scavenging of reactive oxygen species. This study also presented report on the response of alternative splicing events in rice to spaceflight stress. Moreover, our findings revealed that genome methylation was associated with gene expression but not with DAS. In conclusion, our study provides comprehensive insights into the intergenerational inheritance of spaceflight-induced stress in rice and may contribute to uncovering novel mechanisms of oxidative stress-induced genomic instability and epigenetic regulation in plant stress inheritance.

关键词： DNA methylation intergenerational inheritance rice SJ-10 return satellite spaceflight stress memory

来源：评论

学校读者我要写书评

暂无评论

Durable Ag-Coated Micro-Crack Velcro Electrode for Hi-Fi Bioelectric Signals in Hairy Areas 38

Durable Ag-Coated Micro-Crack Velcro Electrode for Hi-Fi Bio...

引用

38th IEEE International Conference on Micro Electro Mechanical systems, MEMS 2025

作者： Guo, Jun Fu, Kang Zhang, Zimo Bai, Ruiyu Wang, Xuanqi Xue, Kai Chen, Huazhen Li, Le Hu, Huijing Wang, Minghao Chang, Honglong Ji, Bowen Northwestern Polytechnical University Unmanned System Research Institute China Northwestern Polytechnical University National Key Laboratory of Unmanned Aerial Vehicle Technology Integrated Research and Development Platform of Unmanned Aerial Vehicle Technology China Northwestern Polytechnical University Ministry of Education Key Laboratory of Micro/Nano Systems for Aerospace School of Mechanical Engineering China Northwestern Polytechnical University Institute of Medical Research China Hangzhou Dianzi University Moe Engineering Research Center of Smart Microsensors and Microsystems College of Electronics and Information China

ISBN: (纸本)9798331508890

This paper reports a conductive Velcro electrode with micro-cracks for the first time. The laser-induced micro-cracks increase the surface area of Velcro hooks and facilitate the adhesion of more silver particles. A cluster of Nylon-Ag hook are durable with repeated mechanical compression and multiple washing. After 100 times of compression, the plastic deformation is less than 23 μm ( © 2025 IEEE.

关键词： Hooks

来源：评论

学校读者我要写书评

暂无评论

MAKT: Multichannel Attention Networks based Knowledge Tracing with Representation Learning 11

MAKT: Multichannel Attention Networks based Knowledge Tracin...

引用

11th IEEE International Conference on Teaching, Assessment and Learning for engineering, TALE 2022

作者： Jiang, Xuyang Ouyang, Yuanxin Liu, Zhuang Rong, Wenge Xiong, Zhang Beihang University State Key Laboratory of Software Development Environment Beijing China Beihang University Engineering Research Center of Advanced Computer Application Technology Ministry of Education Beijing China

ISBN: (纸本)9781665491174

As an effective and emerging component of intelligent education, Knowledge Tracing(KT) achieves the combination of artificial intelligence and individualized learning, whose aim is to assess students' mastery of knowledge concepts and assist in developing learning plans. Several existing KT models either use concepts sequence as input and evaluate students' knowledge state or treat exercise as input to predict students' future performance. In this paper, we introduce a constraint factor to extract concepts' and exercises' relation matrix, design three methods in representation learning, and propose a Multichannel Attention Networks based KT model(MAKT). Specifically, we restrict the co-occurrence relationship within a time window to extract the relation matrix and then train their representations via graph generative learning, graph contrastive learning, and matrix decomposition, respectively. In MAKT, a sliding window is implemented by multichannel where input sequence is sequentially lagged in turn by one position and attention mechanism is applied. We conduct experiments on several benchmark datasets and demonstrate that MAKT with concepts' and exercises' representation trained by matrix decomposition outperforms state-of-the-art models. © 2022 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning-Based Explainable Recommendation over Knowledge Graphs with Negative Sampling 19

Reinforcement Learning-Based Explainable Recommendation over...

引用

2022 IEEE SmartWorld, 19th IEEE International Conference on Ubiquitous Intelligence and Computing, 2022 IEEE International Conference on Autonomous and Trusted Vehicles Conference, 22nd IEEE International Conference on Scalable Computing and Communications, 2022 IEEE International Conference on Digital Twin, 8th IEEE International Conference on Privacy Computing and 2022 IEEE International Conference on Metaverse, SmartWorld/UIC/ATC/ScalCom/DigitalTwin/PriComp/Metaverse 2022

作者： Zhang, Siyuan Ouyang, Yuanxin Liu, Zhuang Rong, Wenge Xiong, Zhang Beihang University State Key Laboratory of Software Development Environment Beijing China Beihang University Engineering Research Center of Advanced Computer Application Technology Ministry of Education Beijing China

ISBN: (纸本)9798350346558

Introducing knowledge graphs (KGs) into the recommender systems not only improves their performance but also enhances the interpretability. However, most KG-based recommendation methods have the problem of inefficiency and ex-post explanation, which reinforcement learning (RL) methods can solve properly. Most existing RL-based methods for explainable recommendations only consider positive rewards when designing the reward part of the RL environment, which is defective and misleads the policy of the RL agent. To address this problem, we propose Reinforced Knowledge Graph Reasoning with Reinforced Negative Sampling (RKGR-RNS) by introducing a negative sampling method into RL-based recommendation, which refines the reward mechanism to help optimize the agent's policy. And a judge module is proposed to improve the performance of the recommender system further. Experiments on three real datasets demonstrate that our method is better than the state-of-the-art baseline. © 2022 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Long-term and short-term plasticity independently mimicked in highly reliable Ru-doped Ge_(2)Sb_(2)Te_(5) electronic synapses

引用

InfoMat 2024年第8期6卷 85-96页

作者： Qiang Wang Yachuan Wang Yankun Wang Luyue Jiang Jinyan Zhao Zhitang Song Jinshun Bi Libo Zhao Zhuangde Jiang Jutta Schwarzkopf Shengli Wu Bin Zhang Wei Ren Sannian Song Gang Niu State Key Laboratory for Manufacturing Systems Engineering Electronic Materials Research LaboratoryKey Laboratory of the Ministry of Education&International Center for Dielectric ResearchSchool of Electronic Science and EngineeringXi'an Jiaotong UniversityXi'anthe People's Republic of China School of Integrated Circuits Peking UniversityBeijingthe People's Republic of China Beijing Microelectronics Technology Institute Beijingthe People's Republic of China National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual information and Applicationsand School of SoftwareXi'an Jiaotong UniversityXi'anthe People's Republic of China State Key Laboratory of Functional Materials for Informatics Shanghai Institute of Microsystem and Information TechnologyChinese Academy of SciencesShanghaithe People's Republic of China Key Laboratory of Microelectronics Device and Integrated Technology The Institute of Microelectronics of Chinese Academy of SciencesBeijingthe People's Republic of China University of Chinese Academy of Sciences Beijingthe People's Republic of China The State Key Laboratory for Manufacturing Systems Engineering&The International Joint Laboratory for Micro/Nano Manufacturing and Measurement Technology Xi'an Jiaotong UniversityXi'anthe People's Republic of China Leibniz-Institut für Kristallzüchtung Max-Born-Straße 2BerlinGermany Key Laboratory of Physical Electronics and Devices Ministry of EducationSchool of Electronic Science and EngineeringXi'an Jiaotong UniversityXi'anthe People's Republic of China The International Joint Laboratory for Micro/Nano Manufacturing and Measurement Technology Xi'an Jiaotong UniversityXi'anthe People's Republic of China

In order to fulfill the complex cognitive behaviors in neuromorphic systems with reduced peripheral circuits,the reliable electronic synapses mimicked by single device that achieves diverse long-term and short-term plasticity are *** change random access memory(PCRAM)is of great potential for artificial synapses,which faces,however,difficulty to realize short-term plasticity due to the long-lasting resistance *** work reports the ruthenium-doped Ge_(2)Sb_(2)Te_(5)(RuGST)based PCRAM,demonstrating a series of synaptic behaviors of short-term potentiation,pair-pulse facilitation,longterm depression,and short-term plasticity in the same single *** optimized RuGST electronic synapse with the high transformation temperature of hexagonal phase>380C,the outstanding endurance>108 cycles,the low resistance drift factor of 0.092,as well as the extremely high linearity with correlation coefficients of 0.999 and 0.976 in parts of potentiation and *** investigations also go insight to mechanisms of Ru doping according to thorough microstructure characterization,revealing that Ru dopant is able to enter GST lattices thus changing and stabilizing atomic arrangement of *** leads to the short-term plasticity realized by RuGST ***,the proposed RuGST electronic synapses performs a high accuracy of94.1%in a task of image recognition of CIFAR-100 database using ResNet *** work promotes the development of PCRAM platforms for large-scale neuromorphic systems.

关键词： electronic synapses neuromorphic computing PCRAM Ru-doped Ge_(2)Sb_(2)Te_(5)

来源：评论

学校读者我要写书评

暂无评论

Computational analysis of fluid-structure interaction in case of fish swimming in the vortex street

引用

Journal of Hydrodynamics 2021年第4期33卷 747-762页

作者： Lang Yan Xing-hua Chang Nian-hua Wang Run-yu Tian Lai-ping Zhang Wei Liu College of Aerospace Science and Engineering National University of Defense TechnologyChangsha410073China Unmanned Systems Research Center National Innovation Institute of Defense TechnologyBeijing100071China China Aerodynamics Research and Development Center State Key Laboratory of AerodynamicsMianyang621000China Hypervelocity Aerodynamics Institute China Aerodynamics Research and Development CenterMianyang621000China

The fluid-structure interaction (FSI) in case of fish swimming in the vortex street is investigated by numerical simulations. The vortex street is generated by a D-section cylinder. A 2-D fish model is placed on the downstream centerline of the bluff cylinder at a distance of 4 diameters away from the center of the cylinder. To simulate the fish body undulation and movement, the moving mesh is generated by a coupling approach based on the radial basis function and the overset grid technology. The Navier-Stokes equation in the arbitrary Lagrangian-Eulerian form is solved by coupling with the kinematics equation. Three cases are investigated: in a stationary position without deformation, a passive locomotion without deformation, and an active deformation based on the Kármán gait model. The results indicate that the fish body is acted by an alternating force and moment when it is located in the centerline of the vortex street. Furthermore, the fish could extract sufficient kinetic energy to overcome the drag under suitable conditions even when it keeps rigid and out of the suction zone. When the fish body undulates based on the Kármán gait model, the interaction is evidently shown between the fish body and the vortices. The theoretical analysis demonstrates that the lateral force and the moment acting on the fish body vary in a cosine formula, with the lateral translation and the body rotation as a result. This study focuses on the behavior of the fish body in the bluff cylinder wake and reproduces some phenomena observed in the experiments. Besides, the Kármán gait model is also theoretically analyzed, for the further exploration of the FSI mechanism in case of fish swimming.

关键词： Computational analysis fluid-structure interaction(FSI) Kármán gait vortex street passive locomotion fish swimming

来源：评论

学校读者我要写书评

暂无评论

Sleep Monitoring with Wearable Sensor Data in an eCoach Recommendation System: A Conceptual Study with Machine Learning Approach 7th

Sleep Monitoring with Wearable Sensor Data in an eCoach Reco...

引用

7th International Conference on Emerging Applications of Information Technology, EAIT 2022

作者： Chatterjee, Ayan Prinz, Andreas Pahari, Nibedita Das, Jishnu Riegler, Michael Alexander Department of Information Technology Center for eHealth University of Agder Kristiansand Norway Department of Software Engineering Knowit AS Oslo Norway Department of Library and Information Science University of Calcutta Calcutta India Department of Holistic Systems Simula Research Laboratory Oslo Norway

ISBN: (纸本)9789811951909

The collective effects of sleep loss and sleep disorders are correlated with many adverse health consequences, including increased risk of high blood pressure, obesity, diabetes, depressive state, and cardiovascular symptoms. research in eHealth can provide methods to enrich personal health care with information and communication technologies (ICTs). An eCoach system may allow people to manage a healthy lifestyle with extended health state monitoring (e.g., sleep) and tailored recommendation generation. Using supervised machine learning (ML) techniques, this study investigated the possibility of classifying sleep stages at night for adults on hourly and daily basis. The daily total sleep minutes and hourly total sleep minutes for defined sleeping period served as input for the classification models. We first used publicly available Fitbit dataset to build the initial classification models. Second, using the transfer learning approach, we re-used the top five best-performing models on a real dataset as collected from the MOX2-5 wearable medical-grade activity device. We found that support vector classifier (SVC) with "linear" kernel outdated other classifiers with a mean accuracy score of 99.92% for hourly sleep classification and a K-nearest neighbor (KNN) outpaced other classifiers with a mean accuracy score of 99.47% for daily sleep classification, for the public Fitbit datasets. Moreover, to determine the practical efficacy of the classifier models, we conceptualized to use the classifier models in an eCoach prototype system to attain tailored sleep goals (e.g., a weekly goal of 49–63 h of sleeping). © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Solar-powered miniature robot for on-site oil spill treatment under magnetic steering

引用

Science China(Technological Sciences) 2024年第7期67卷 2164-2175页

作者： WANG Ben CHEN YunRui WANG Yun JI FengTong LI HongYuan NIU ShiChao HAN ZhiWu ZHANG YaBin GUO ZhiGuang College of Chemistry and Environmental Engineering Shenzhen UniversityShenzhen 518060China State Key Laboratory of Featured Metal Materials and Life-cycle Safety for Composite Structures Ministry of Education Key Laboratory of New Processing Technology for Nonferrous Metals and Materialsand School of ResourcesEnvironment and MaterialsGuangxi UniversityNanning 530004China Key Laboratory for Bionic Engineering Ministry of Education Jilin UniversityChangchun 130022China Hubei Collaborative Innovation Centre for Advanced Organic Chemical Materials Ministry of Education Key Laboratory for the Green Preparation and Application of Functional MaterialsHubei UniversityWuhan 430062China Wellcome Trust/Cancer Research UK Gurdon Institute University of CambridgeCambridge CB21QNUK Department of Physiology Development and NeuroscienceUniversity of CambridgeCambridge CB21QNUK State Key Laboratory for Turbulence and Complex Systems Department of Mechanics and Engineering ScienceBeijing Innovation Center for Engineering Science and Advanced TechnologyCollege of EngineeringPeking UniversityBeijing 100871China

Walking on the water surface is an effective method for miniature robots to transport payloads with dramatically decreased interfacial drag. Current aquatic robots reported are generally actuated by a beam of focused light that can trigger asymmetrical deformation, enabling the directional movement through horizontal momentum transfer of photoinduced actuation force to the water. However, the operations are heavily dependent on manual manipulation of the focused light, making the long-term actuation and application of the aquatic robots in vast scenarios challenging. Herein, we developed a kind of water striderinspired robot that can autonomously manage the motion on the water surface under solar irradiation, with their direction steerable by a magnetic field. The motion of this bioinspired robot on the water surface was achieved by the use of a solar cell panel as a driving module to enable propulsive motion based on the conversion of light-electric-mechanical energies. The superhydrophobic design of its leg surfaces enables the aquatic robots with weight-bearing and drag-reducing abilities. With the assistance of magnetic navigation, the bioinspired robot can continuously and controllably locomote to the oily spill floating on the water body and collect them with high efficiency. For further demonstration, the treatment of oil spills in a campus pool with high efficiency has also been achieved. This on-site oil-spill treating strategy, taking advantage of a home-made bioinspired robot actuated by natural sunlight under magnetic steering, shows great potential applications in water-body remediation.

关键词： miniature robot superhydrophobic water strider interfacial friction magnetic actuation

来源：评论

学校读者我要写书评

暂无评论

Forming Circle Formations of Multi-agent systems Under Actuator Faults 5th

Forming Circle Formations of Multi-agent Systems Under Actu...

引用

5th Chinese Conference on Swarm Intelligence and Cooperative Control, CCSICC 2021

作者： Liu, Jiajun Ru, Xinfeng Xia, Weiguo Wang, Chen China National Aeronautical Radio Electronic Research Institute and National Key Laboratory of Science and Technology on Avionics System Integration Shanghai China Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education and School of Control Science and Engineering Dalian University of Technology Dalian China National Engineering Research Center of Software Engineering and the State Key Laboratory of Turbulence and Complex Systems Intelligent Biomimetic Design Lab College of Engineering Peking University Beijing China

ISBN: (纸本)9789811939976

A distributed fault-tolerant formation control law is designed in this paper for multi-agent systems under external disturbances and actuator faults including time-varying loss of effectiveness faults. The initial position of each agent is already on a circle and the control purpose is to form a desired formation on this circle. Based on this local information, a distributed adaptive formation control law is designed by employing the congelation of variables method to deal with time-varying actuator faults. Finally, a simulation example is given to verify the effectiveness of the adaptive fault-tolerant control design method. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Multi agent systems

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：