检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Chen, Geng Liu, Si-Jie Sun, Yu-Jia Ji, Ge-Peng Wu, Ya-Feng Zhou, Tao Northwestern Polytechnical University Xi’an710072 China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering China Data Processing Center School of Power and Energy China Key Laboratory of System Control and Information Processing Ministry of Education Shanghai200240 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China School of Computer Science Inner Mongolia University Hohhot010021 China Artificial Intelligence Institute School of Computer Science Wuhan University Wuhan430072 China

Camouflaged object detection (COD) aims to identify the objects that conceal themselves in natural scenes. Accurate COD suffers from a number of challenges associated with low boundary contrast and the large variation of object appearances, e.g., object size and shape. To address these challenges, we propose a novel Context-aware Cross-level Fusion Network (C2F-Net), which fuses context-aware cross-level features for accurately identifying camouflaged objects. Specifically, we compute informative attention coefficients from multi-level features with our Attention-induced Cross-level Fusion Module (ACFM), which further integrates the features under the guidance of attention coefficients. We then propose a Dual-branch Global Context Module (DGCM) to refine the fused features for informative feature representations by exploiting rich global context information. Multiple ACFMs and DGCMs are integrated in a cascaded manner for generating a coarse prediction from high-level features. The coarse prediction acts as an attention map to refine the low-level features before passing them to our Camouflage Inference Module (CIM) to generate the final prediction. We perform extensive experiments on three widely used benchmark datasets and compare C2F-Net with state-of-the-art (SOTA) models. The results show that C2F-Net is an effective COD model and outperforms SOTA models remarkably. Further, an evaluation on polyp segmentation datasets demonstrates the promising potentials of our C2F-Net in COD downstream applications. Our code is publicly available at: https://***/Ben57882/C2FNet-TSCVT. Copyright © 2022, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

An active fault-tolerant control strategy of aircraft engines based on multi-model predictive control

引用

International Journal of Turbo and Jet Engines 2020年第0期

作者： Du, Xian Ma, Yan-Hua School of Control Science and Engineering Dalian University of Technology Dalian China Jiangsu Province Key Laboratory of Aerospace Power System Nanjing China School of Microelectronics Dalian University of Technology Dalian China DUT Artificial Intelligence Institute Dalian China

In order to mitigate or even eliminate the adverse effects caused by typical components faults of aircraft engines, an active fault-tolerant strategy based on multi-model predictive control is proposed, which consists of a pre-established multi-model library, a judgement module, and corresponding predictive controllers with smooth transition switching logic. Multiple dynamic nonlinear or linear models are firstly established by means of system identification methods, based on the component-level nonlinear engine model or historical data in faults cases. The judgement module is utilized to online compare the engine measured outputs with that of all models in the pattern library and select the best matched dynamic model on the basis of outputs error quadratic performance index, thus determining the most appropriate predictive controller for the next control sample period. When a certain fault occurs, the fault model in the library could be identified and fault-model based predictive controller is activated. Finally, two kinds of pre-considered high-pressure compressor and high-pressure turbine component-level faults are taken as an example to design the active fault-tolerant controller. Simulation results show that the judgement module owns the ability to sense the fault and gives smooth switching signal to the suitable predictive controller, verifying the effectiveness of the proposed technique. © 2020 Walter de Gruyter GmbH, Berlin/Boston 2020.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

On PID control for synchronization of complex dynamical network with delayed nodes

引用

Science China(Technological Sciences) 2019年第8期62卷 1412-1422页

作者： GU HaiBo Lv JinHu LIN ZongLi Key Laboratory of Systems and Control Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing 100190 China School of Mathematical Sciences University of Chinese Academy of Sciences Beijing 100049 China School of Automation Science and Electrical Engineering State Key Laboratory of Software Development Environment and Beijing Advanced Innovation Center for Big Data and Brain Machine Intelligence Beihang University Beijing 100083 China Charles L. Brown Department of Electrical and Computer Engineering University of Virginia Charlottesville VA 22904-4743 USA

Over the past two decades, synchronization, as an interesting collective behavior of complex dynamical networks, has been attracting much attention. To reveal and analyze the inherent mechanism of synchronization in complex dynamical networks with time delays in nodes, this paper attempts to use PD and PI control protocols to achieve synchronization. Based on a classical network model, we investigate the PD and PI control for synchronization of complex dynamical networks with delayed nodes and obtain some sufficient conditions. By using Lyapunov functions and appropriate state transformations, we prove that global synchronization can be achieved via the above control protocols. Finally, some simulation examples are illustrated to validate the effectiveness of the proposed theoretical results.

关键词： synchronization PID control complex dynamical network networked control system delayed node

来源：评论

学校读者我要写书评

暂无评论

A Quantifiable Muscle Fatigue Method Based on sEMG during Dynamic Contractions for Lower Limb Exoskeleton

A Quantifiable Muscle Fatigue Method Based on sEMG during Dy...

引用

IEEE International Conference on Real-time Computing and Robotics (RCAR)

作者： Shengcai Duan Can Wang Yuxiao Li Lufeng Zhang Ye Yuan Xinyu Wu Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology University of Chinese Academy of Sciences Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China The Chinese University of Hong Kong

ISBN: (数字)9781728172934

ISBN: (纸本)9781728172941

Advanced interactive methods between users and lower-limb exoskeletons are gradually drawing attention. Muscle fatigue is regarded as a significant contributory factor in muscle injuries and low work efficiency which is harmful to human-robot interactions. The detection and quantification of muscle fatigue during dynamic contractions remain as a challenging research. In this research, we introduce a novel method called Wavelet Packet Energy Entropy (WPEE) to quantify the muscle fatigue based on sEMG during dynamic contractions. Fatigue experiments and exoskeleton experiments are executed and three healthy subjects complete these experiments. sEMG signals from six muscles of arms are selected and analyzed. The results derived from fatigue experiments validate that the introduced method is better at quantifying the muscle fatigue compared with traditional method mean power frequency (MNF). WPEE is applied in exoskeleton experiments to investigate the arms' muscle fatigue under three conditions. The quantitative results detailly express the user's muscle fatigue condition and fatigue trends when the user is using an exoskeleton with crutches. Considering the muscle fatigue will contribute to ergonomic design and high-quality interactive control of exoskeleton.

关键词： Ergonomics Exoskeletons Muscles Fatigue Market research Wavelet packets Entropy

来源：评论

学校读者我要写书评

暂无评论

A DRL-based framework for self-balancing exoskeleton walking

A DRL-based framework for self-balancing exoskeleton walking

引用

IEEE International Conference on Real-time Computing and Robotics (RCAR)

作者： Yao Dong Yong He Xinyu Wu Guangju Gao Wei Feng A Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen College of Advanced Technology University of Chinese Academy of Sciences Shenzhen China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China

ISBN: (数字)9781728172934

ISBN: (纸本)9781728172941

Self-balancing exoskeleton is a robot that can be worn by paraplegic patients for walking without external support. The exoskeleton is similar to humanoid robot with two normal human feet, which cause inconvenience to existing control methods. These model-based methods require mathematical modeling and usually do not consider the impact of the controller like limits of position and torque. This paper proposes a deep reinforce learning (DRL) based training framework for self-balancing exoskeleton, for the purpose of learning a feasible walking policy which can generate walk pattern similar to the given reference motion for paraplegia with exoskeleton. The framework is based on policy gradient descent algorithm, and a way to simplify the model is proposed to speed up model training. The experimental results indicate that this training framework which fully considers the controller can acquire a feasible control policy for self-balancing exoskeleton.

关键词： Cows Robots Real-time systems Conferences

来源：评论

学校读者我要写书评

暂无评论

An Improved UAV Path Optimization Algorithm for Target Accurately and Quickly Localization

An Improved UAV Path Optimization Algorithm for Target Accur...

引用

International Conference on Informative and Cybernetics for Computational Social systems (ICCSS)

作者： Rui Liang Kai Wu Sheng Xu Tiantian Xu Xiaoyi Ma Lianyu Fu City West Power Supply Branch State Grid Tianjin Electric Power Company Tianjin China Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Shenzhen China Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology Shenzhen China State Grid Tianjin Information & Telecommunication Company Tianjin China

ISBN: (纸本)9781665402460

Angle-of-arrival (AOA) target localization using the unmanned aerial vehicle (UAV) has been widely applied in many practical applications. To localize an invasive target quickly and accurately, both the estimation and UAV path optimization algorithms are required. This paper focuses on developing a path optimization method to improve the target estimation performance. Firstly, the problem formulation of AOA target localization is introduced. Secondly, the classical pseudolinear Kalman filter (PLKF) and the gradient-based path optimization are presented. Thirdly, we analyze the problems that existed in the previous methods and propose an improved gradient-descent path optimization algorithm combined with a simple grid search method. Finally, the simulation examples verify the effectiveness of the proposed methods.

关键词： Location awareness Adaptation models Three-dimensional displays Target tracking Search methods Estimation Optimization methods

来源：评论

学校读者我要写书评

暂无评论

A multi-task learning convolutional neural network for object pose estimation

A multi-task learning convolutional neural network for objec...

引用

2019 IEEE International Conference on Robotics and Biomimetics, ROBIO 2019

作者： Wang, Yurui Jin, Shaokun Ou, Yongsheng Shenzhen Institutes of Advanced Technology CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Beijing China University of Chinese Academy of Sciences Beijing China Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China

ISBN: (纸本)9781728163215

Estimating 6D poses of objects from RGB images is very crucial for robots to interact with the surrounding environment and to cooperate with humans. It is a challenging problem due to the various shapes of objects, the occlusions among objects, as well as the complexity of the scene. In this study, we present a new multi-task convolutional neural network for 6D object pose estimation, which also learns the object region in the image to further improve the estimation result. A weighted loss computed from the training samples is adopted to guarantee that the components of the estimated pose are equally accurate. Additionally, we sythesize new virtual data based on the existing training data so as to overcome the possible adverse situation caused by insufficiency of training data. Experiments on the YCB-video dataset are undertaken to validate the effectiveness of the proposed method. © 2019 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Milestones in Autonomous Driving and Intelligent Vehicles Part I: control, Computing system Design, Communication, HD Map, Testing, and Human Behaviors

arXiv

引用

arXiv 2023年

作者： Chen, Long Li, Yuchen Huang, Chao Xing, Yang Tian, Daxin Li, Li Hu, Zhongxu Teng, Siyu Lv, Chen Wang, Jinjun Cao, Dongpu Zheng, Nanning Wang, Fei-Yue The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China Waytous Ltd. China BNU-HKBU United International College Zhuhai519087 China Hong Kong Baptist University Kowloon999077 Hong Kong The Department of Industrial and System Engineering Hong Kong Polytechnical University Hong Kong The School of Aerospace Transport and Manufacturing Cranfield University United Kingdom The School of Transportation Science and Engineering Beihang University China The Department of Automation Tsinghua University China The Department of Mechanical and Aerospace Engineering Nanyang Technological University Singapore The College of Artificial Intelligence Xi'an Jiaotong University China The School of Mechanical Engineering Tsinghua University China

Interest in autonomous driving (AD) and intelligent vehicles (IVs) is growing at a rapid pace due to the convenience, safety, and economic benefits. Although a number of surveys have reviewed research achievements in this field, they are still limited in specific tasks and lack systematic summaries and research directions in the future. Our work is divided into 3 independent articles and the first part is a Survey of Surveys (SoS) for total technologies of AD and IVs that involves the history, summarizes the milestones, and provides the perspectives, ethics, and future research directions. This is the second part (Part I for this technical survey) to review the development of control, computing system design, communication, High Definition map (HD map), testing, and human behaviors in IVs. In addition, the third part (Part II for this technical survey) is to review the perception and planning sections. The objective of this paper is to involve all the sections of AD, summarize the latest technical milestones, and guide abecedarians to quickly understand the development of AD and IVs. Combining the SoS and Part II, we anticipate that this work will bring novel and diverse insights to researchers and abecedarians, and serve as a bridge between past and future. Copyright © 2023, The Authors. All rights reserved.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Adsorption and Sensing Characteristics of Transition Metal (AU, Fe, Pt, Rh and Cu) Doped Ws2 on Dissolved Gases in Transformer Oil: A Dft Perspective

SSRN

引用

SSRN 2025年

作者： Jiang, Wenwen Zeng, Qingbin Zhang, Yiyi Wang, Guishan Sun, Kuoteng Xu, Min Chen, Dachang Jia, Pengfei School of Electrical Engineering Guangxi University Nanning China School of Artificial Intelligence Guangxi University Nanning China Guangxi Key Laboratory of Intelligent Control and Maintenance of Power Equipment Guangxi University Nanning China China Southern Power Grid Extra High Voltage Power Transmission Company Liuzhou Branch Liuzhou China College of Food Science and Bioengineering Xihua University Chengdu China School of Electrical and Electronic Engineering Wuhan Polytechnic University Wuhan China Guangxi Key Laboratory of Power System Optimization and Energy Technology China

In this work, the sensing characteristics of transition metal (Au, Pt, Fe, Rh, Cu) doped WS2 for faulty decomposition gases (CO, CH4, C2H2, C2H4) in oil-immersed transformers were studied using density functional theory (DFT). The analysis showed that pristine WS2 had limited adsorption capacity for these gases. After comparing two doping sites, the more stable TM-WS2 structure was selected. Adsorption structures were optimized, and interactions between the gas molecules and TM-WS2 were analyzed through binding energies, charge transfer, band gaps, and density of states. Results showed that doped WS2 exhibited enhanced gas adsorption compared to pristine WS2. Pt-WS2 showed excellent performance for CH4, Rh-WS2 for C2H4, and Cu-WS2 for C2H2, with short response times and high detection efficiency. This work provides insights into the design of gas-sensing materials based on TM-WS2 © 2025, The Authors. All rights reserved.

关键词： Chemical sensors

来源：评论

学校读者我要写书评

暂无评论

Maximal η-clique maintenance over uncertain graph streams

引用

Information Sciences 2025年 717卷

作者： Ma, Ziyi Wang, Liqing Yang, Jianye Zhou, Xu Li, Kenli Gao, Cuiyun School of Artificial Intelligence Hebei University of Technology Tianjin300401 China Chinacoal Beijing Coal Mining Machinery Co. Ltd. Beijing102400 China Guangxi Key Laboratory of Machine Vision and Intelligent Control Wuzhou University Wuzhou543002 China Department of New Networks PengCheng Laboratory Shenzhen518055 China Cyberspace Institute of Advanced Technology Guangzhou University Guangzhou510006 China College of Computer Science and Electronic Engineering Hunan University Changsha410082 China Shenzhen518055 China

Maximal clique enumeration is a critical task for analyzing graph data and has a wide range of applications, such as community detection, protein complex identification, and group recommendation. Although many efficient algorithms have been proposed, most of them are designed for static or deterministic graphs. However, in many real-life applications, graphs are often highly dynamic and nondeterministic. In this paper, we study the problem of maximal η-clique maintenance (shorted as MCM) over uncertain graph streams. Given an uncertain graph G and a probability threshold η, MCM reports all incremental η-cliques in G for each update edge of G. To the best of our knowledge, we are the first to systematically study this problem. We first develop a local pivot-based enumeration technique that utilizes the pivot priority of candidates to achieve effective pruning during the maximal η-clique enumeration procedure. Based on the technique, we propose a competitive baseline approach LPMCM, which finds newly generated maximal η-cliques and internal maximal η-cliques. Although LPMCM avoids repeated enumeration of the same maximal η-cliques, it still requires expensive costs in terms of η-clique maximality determination. To further enhance maintenance efficiency, we introduce an approach HLPMCM using the hash-based maximality determination technique and an improved internal maximal η-clique enumeration technique. Extensive experiments show that HLPMCM can achieve 1.1x-19.0x speedup over the competitors and consumes slightly more memory. © 2025 Elsevier Inc.

关键词： Maintenance

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：