检索结果-内蒙古大学图书馆

Autonomous landing scene recognition based on transfer learning for drones

Journal of Systems engineering and Electronics 2023年第1期34卷 28-35页

作者： DU Hao WANG Wei WANG Xuerao WANG Yuanda School of Automation Southeast UniversityNanjing 210096China Autonomous Control Robot Laboratory Jiangsu Zhongke Institute of Applied Research on Intelligent Science and TechnologyChangzhou 213164China Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology Nanjing University of Information Science and TechnologyNanjing 210044China

In this paper, we study autonomous landing scene recognition with knowledge transfer for drones. Considering the difficulties in aerial remote sensing, especially that some scenes are extremely similar, or the same scene has different representations in different altitudes, we employ a deep convolutional neural network(CNN) based on knowledge transfer and fine-tuning to solve the problem. Then, LandingScenes-7 dataset is established and divided into seven classes. Moreover, there is still a novelty detection problem in the classifier, and we address this by excluding other landing scenes using the approach of thresholding in the prediction stage. We employ the transfer learning method based on ResNeXt-50 backbone with the adaptive momentum(ADAM) optimization algorithm. We also compare ResNet-50 backbone and the momentum stochastic gradient descent(SGD) optimizer. Experiment results show that ResNeXt-50 based on the ADAM optimization algorithm has better performance. With a pre-trained model and fine-tuning, it can achieve 97.845 0% top-1 accuracy on the LandingScenes-7dataset, paving the way for drones to autonomously learn landing scenes.

关键词： landing scene recognition convolutional neural network(CNN) transfer learning remote sensing image

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning in Motor Imagery Brain Computer Interface: A Review

引用

Journal of Shanghai Jiaotong university(Science) 2024年第1期29卷 37-59页

作者：李明爱许冬芹 Faculty of Information Technology Beijing University of TechnologyBeijing 100124China Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing 100124China Engineering Research Center of Digital Community Ministry of EducationBeijing 100124China

Transfer learning,as a new machine learning methodology,may solve problems in related but different domains by using existing knowledge,and it is often applied to transfer training data from another domain for model training in the case of insuficient training *** recent years,an increasing number of researchers who engage in brain-computer interface(BCI),have focused on using transfer learning to make most of the available electroencephalogram data from different subjects,effectively reducing the cost of expensive data acquisition and labeling as well as greatly improving the learning performance of the *** paper surveys the development of transfer learning and reviews the transfer learning approaches in *** addition,according to the"what to transfer"question in transfer learning,this review is organized into three contexts:instance-based transfer learning,parameter-based transfer learning,and feature-based transfer ***,the current transfer learning applications in BCI research are summarized in terms of the transfer learning methods,datasets,evaluation performance,*** the end of the paper,the questions to be solved in future research are put forward,laying the foundation for the popularization and in-depth research of transfer learning in BCI.

关键词： transfer learning brain-computer interface(BCI) electroencephalogram machine learning

来源：评论

学校读者我要写书评

暂无评论

Distributed robust matrix-scaled consensus control of perturbed multi-agent systems

引用

control Theory and technology 2024年第4期22卷 623-637页

作者： Bin Cheng Gang Li Kun An Chunhui Yu Department of Control Science and Engineering Tongji UniversityShanghai201804China Shanghai Research Institute for Intelligent Autonomous Systems Shanghai201210China The Key Laboratory of Road and Traffic Engineering of the Ministry of Education Tongji UniversityShanghai201804China Shanghai Sunshine Rehabilitation Center Shanghai201613China

Distributed matrix-scaled consensus is a kind of generalized cooperative control problem and has broad applications in the field of social network and *** paper addresses the robust distributed matrix-scaled consensus of perturbed multi-agent systems suffering from unknown *** discontinuous protocols are first proposed to drive agents to achieve cluster consensus and suppress the effect of *** protocols with time-varying gains obeying differential equations are also designed,which are completely distributed and rely on no global *** the boundary layer technique,smooth protocols are proposed to avoid the unexpected chattering effect due to discontinuous *** a cost,under the designed smooth protocols,the defined matrix-scaled consensus error tends to a residual set rather than zero,in which the residual bound is arbitrary small by choosing proper ***,distributed dynamic event-based matrix-scalar consensus controllers are also proposed to avoid continuous *** examples are provided to further verify the designed algorithms.

关键词： Matrix-scaled consensus Perturbed multi-agent systems Adaptive control Distributed control Event-triggered control

来源：评论

学校读者我要写书评

暂无评论

Efficient blocked symmetric compressed sparse column method for finite element analysis

引用

Frontiers of Mechanical engineering 2025年第1期20卷 87-104页

作者： Yingjun WANG Shijie LUO Jinyu GU Yuanfang ZHANG National Engineering Research Center of Novel Equipment for Polymer Processing The Key Laboratory of Polymer Processing Engineering of the Ministry of EducationGuangdong Provincial Key Laboratory of Technique and Equipment for Macromolecular Advanced ManufacturingSouth China University of TechnologyGuangzhou 510641China Shien-Ming Wu School of Intelligent Engineering South China University of TechnologyGuangzhou 511442China

In finite element analysis(FEA),optimizing the storage requirements of the global stiffness matrix and enhancing the computational efficiency of solving finite element equations are pivotal *** address these goals,we present a novel method for compressing the storage of the global stiffness matrix,aimed at minimizing memory consumption and enhancing FEA *** method leverages the block symmetry of the global stiffness matrix,hence named the blocked symmetric compressed sparse column(BSCSC)*** also detail the implementation scheme of the BSCSC method and the corresponding finite element equation solution *** approach optimizes only the global stiffness matrix index,thereby reducing memory requirements without compromising FEA computational *** then demonstrate the efficiency and memory savings of the BSCSC method in FEA using 2D and 3D cantilever beams as *** addition,we employ the BSCSC method to an engine connecting rod model to showcase its superiority in solving complex engineering ***,we extend the BSCSC method to isogeometric analysis and validate its scalability through two examples,achieving up to 66.13%memory reduction and up to 72.06%decrease in total computation time compared to the traditional compressed sparse column method.

关键词： finite element analysis global stiffness matrix blocked symmetric property memory reduction isogeometric analysis

来源：评论

学校读者我要写书评

暂无评论

Photographic Analysis and Optical Diagnosis of Kilowatt Microwave Plasma Torch with Air Carrier Gas

引用

Chemical research in Chinese Universities 2023年第6期39卷 1051-1057页

作者： YU Dengjie YU Bingwen ZHANG Xuchen HUANG Shiluo YING Yangwei YAN Yuwei JIN Yining JIN Wei Research Center for Analytical Instrumentation Institute of Cyber-Systems and ControlCollege of Control Science and EngineeringZhejiang UniversityHangzhou 310058P.R.China Research Center for Analytical Instruments and Intelligent Systems Huzhou Institute of Zhejiang UniversityHuzhou 313002P.R.China Faculty of Engineering University of Alberta116 St.and 85 Ave.EdmontonAlbertaCanada

The spatiotemporal motion characteristics of the kilowatt argon microwave plasma torch with the air carrier gas(kW-AC-ArMPT)and the behavior of the plasma filaments are investigated with a digital single-lens reflex(SLR)camera and a high-speed *** with the introduction of the air,both the volume of the central channel and the rotational frequency of the plasma filament are ***,the excitation temperature(Texc),rotational temperature(Trot),and density of electron number(ne)of the kW-AC-ArMPT are measured with optical *** is clearly shown that the introduction of air contributed to the rise of Trot and ne of the plasma,which is beneficial to improving the analytical performance of the *** the detection limits of some heavy metal elements are measured by kW-AC-ArMPT,which are in the ppb *** experimental results show that the kW-ArMPT has a high tolerance to air injection at least 1.0 L/min,which allows the direct extraction of air from the environment for analysis and therefore has the potential for online and in-situ detection of ambient air quality and industrial exhaust gases.

关键词： Air carrier gas Microwave plasma torch Photographic analysis Optical diagnosis

来源：评论

学校读者我要写书评

暂无评论

An Optimal control-Based Distributed Reinforcement Learning Framework for A Class of Non-Convex Objective Functionals of the Multi-Agent Network

引用

IEEE/CAA Journal of Automatica Sinica 2023年第11期10卷 2081-2093页

作者： Zhe Chen Ning Li Department of Automation Shanghai Jiao Tong UniversityShanghai 200240 Key Laboratory of System Control and Information Processing Ministry of Education of ChinaShanghai 200240 Shanghai Engineering Research Center of Intelligent Control and Management Shanghai 200240China Department of Automation Tsinghua UniversityBeijing 100084China IEEE

This paper studies a novel distributed optimization problem that aims to minimize the sum of the non-convex objective functionals of the multi-agent network under privacy protection, which means that the local objective of each agent is unknown to others. The above problem involves complexity simultaneously in the time and space aspects. Yet existing works about distributed optimization mainly consider privacy protection in the space aspect where the decision variable is a vector with finite dimensions. In contrast, when the time aspect is considered in this paper, the decision variable is a continuous function concerning time. Hence, the minimization of the overall functional belongs to the calculus of variations. Traditional works usually aim to seek the optimal decision function. Due to privacy protection and non-convexity, the Euler-Lagrange equation of the proposed problem is a complicated partial differential ***, we seek the optimal decision derivative function rather than the decision function. This manner can be regarded as seeking the control input for an optimal control problem, for which we propose a centralized reinforcement learning(RL) framework. In the space aspect, we further present a distributed reinforcement learning framework to deal with the impact of privacy protection. Finally, rigorous theoretical analysis and simulation validate the effectiveness of our framework.

关键词： Distributed optimization multi-agent optimal control reinforcement learning(RL)

来源：评论

学校读者我要写书评

暂无评论

Design of intelligent Backflow Prevention System 42

Design of Intelligent Backflow Prevention System

引用

42nd Chinese control Conference, CCC 2023

作者： Chen, Jiale Dong, Tao Wang, Shiyun Jiao, Guili Zhang, Rongrong Tian, Xincheng School of Control Science and Engineering Center for Robotics Engineering Research Center of Intelligent Unmanned System Ministry of Education Shandong University Jinan China Jinan China Shandong Tianyong Intelligent Technology Co. Ltd Jinan China Shandong Hydrology Center Jinan China

ISBN: (纸本)9789887581543

With the advent of the rainy season, the chances of urban flooding are increasing, to avoid the risk of flooding people and underground garages, this paper explains our reliance on video surveillance technology and 5G cloud data technology to collect the data of anti-backflow door equipment deployed in various parts of the city, and remote control and command in the management center, which can quickly give flood control measures and early warning to protect the personnel and property of underground garages, and reduced losses. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Remote control

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Learning for UAV Trajectory and Caching With Federated Cloud-Assisted Knowledge Distillation

引用

IEEE Transactions on Network and Service Management 2025年第3期22卷 2516-2533页

作者： Tietaa Maale, Gerald Arden Elorm Kuadey, Noble Arafat, Yeasin Thomas, Kwantwi Sun, Guolin Liu, Guisong Research Institute of Intelligent Computing University of Electronic Science and Technology of China School of Computer Science and Engineering National Key Laboratory of Intelligent Collaborative Computing Chengdu611731 China McCoy University College of Education Department of Mathematics and ICT Nadowli Ghana Research Institute of Intelligent Computing at the University of Electronic Science and Technology of China School of Computer Science and Engineering National Key Laboratory of Intelligent Collaborative Computing Chengdu611731 China Ho Technical University Department of Computer Science Ho Ghana University of Mines and Technology Department of Computer Science and Engineering Tarkwa Ghana Southwestern University of Finance and Economics Complex Laboratory of New Finance and Economics School of Computing and Artificial Intelligence Chengdu610074 China Ministry of Education Engineering Research Center of Intelligent Finance Chengdu610030 China

The proliferation of Internet of Things (IoT) technologies and ubiquitous connectivity has led to uncrewed aerial vehicles (UAVs) playing key role as edge servers, revolutionizing the wireless communications landscape by facilitating computing and caching resources closer to ground users (GUs). This advancement significantly alleviates core network loads, reduces latency, and guarantees content availability even in congested or remote areas. However, jointly optimizing UAV caching strategies and trajectories gives rise to a multi-task optimization (MTO) problem. This paper introduces a novel multi-task geo-temporal caching (MT-GTC) framework that addresses the interplay between UAV caching mechanisms and trajectory optimization in a cohesive manner. Leveraging a proposed multi-task learning (MTL) model for joint optimization of UAV caching and trajectory design, we develop a federated learning cloud-assisted knowledge distillation (FL-CAKD) scheme to preserve data privacy and adapt to data heterogeneity. FL-CAKD transfers knowledge from a cloud model orchestrator (CMO), which houses a large and sophisticated teacher model, to a lightweight on-device MTL student models using soft target distributions instead of large model parameters, significantly reducing communication costs. MT-GTC optimizes caching and trajectories to maximize cache hits and minimize latency. Evaluations on real-world mobility datasets demonstrate up to 95% cache hit rates and 21% lower delays compared to baselines. © 2004-2012 IEEE.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Distributed data-driven consensus control of multi-agent systems under switched uncertainties

引用

control Theory and technology 2023年第3期21卷 478-487页

作者： Wenjie Liu Yifei Li Gang Wang Jian Sun Jie Chen National Key Lab of Autonomous Intelligent Unmanned Systems Beijing Institute of TechnologyBeijing 100081China Beijing Institute of Technology Chongqing Innovation Center Chongqing 401120China Department of Control Science and Engineering Tongji UniversityShanghai 201804China

Cooperative control of multi-agent systems(MASs),particularly consensus control,has gained significant attention in the last two decades,thanks to the rapid and sustained development of distributed and networked *** this paper,we present some new results focused on consensus control of a set of unknown linear MASs(whose system matrices are unknown)under unknown switched uncertainties,with an emphasis on distributed data-driven *** proposed controller is end-to-end,designed by solving two data-based semi-definite programs(SDPs),which adjust to the changes of the uncertainty *** approach achieves asymptotic consensus of the MAS provided that the switching is slow enough and the uncertainty is *** illustrate the effectiveness of our proposed method through a numerical example.

关键词： Data-driven control Multi-agent systems Consensus-Switched uncertainties

来源：评论

学校读者我要写书评

暂无评论

Two-dimensional Microwave Through-wall Imaging Algorithm Based on Total Variational Compressive Sensing

Two-dimensional Microwave Through-wall Imaging Algorithm Bas...

引用

2024 Photonics and Electromagnetics research Symposium, PIERS 2024

作者： Zhou, C. Yang, C.X. Tong, M.S. Shanghai Normal University Shanghai Engineering Research Center of Intelligent Education and Bigdata 200234 China Tongji University Shanghai Institute of Intelligent Science and Technology 201203 China

ISBN: (纸本)9798350375909

Microwave imaging is a technique that uses information as a carrier. It enables non-contact acquisition of information from unknown targets, playing a pivotal role in various applications such as radar detection, medical imaging, and industrial inspection. However, practical applications often face challenges in meeting the requirements of traditional imaging algorithms due to limitations imposed by observation environments or economic constraints. Therefore, it is of great research value to explore how limited measurement data can be effectively utilized for reconstructing the target under test. Compressed sensing technology enables high-precision signal reconstruction with sampling frequencies lower than the Nyquist frequency, but its application scope is greatly restricted by the requirement for sparse target distribution measurements, particularly in non-uniform background imaging scenarios. In this study, we propose an inverse scattering method utilizing the total variation-based compressed sensing technique. And through-wall imaging scenes are chosen to validate the robustness of the algorithm. Firstly, by incorporating the gradient of the contrast function as a sparse prior, we reformulate the two-dimensional inverse scattering problem in a time-harmonic regime into an equivalent augmented Lagrange problem with the use of the first-order Born approximation. Subsequently, we construct a compressed sensing matrix. Then, we repeat the aforementioned steps and iteratively solve for the unknown total field and target to be reconstructed alternatively using the distorted Born iteration method framework until meeting certain convergence criteria. The proposed method effectively addresses the reconstruction problem of scattering targets with piecewise constant contrast, while remaining unaffected by non-uniform background. Numerical simulation results validate both the feasibility and efficiency of our proposed method. © 2024 IEEE.

关键词： Iterative methods

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：