检索结果-内蒙古大学图书馆

11th International Conference on Learning Representations, ICLR 2023

作者： Chen, Ziwei Li, Qiang Wang, Xiaofeng Yang, Wankou School of Automation Southeast University China Key Lab of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing China Y-tech Kuaishou Technology China Institute of Automation Chinese Academy of Sciences China

Human-centric perception targets for understanding human body pose, shape and ***-training the model on large-scale datasets and fine-tuning it on specific tasks has become a well-established paradigm in human-centric ***, self-supervised learning methods have re-investigated contrastive learning to achieve superior performance on various downstream *** handling human-centric perception, there still remains untapped potential since 3D human structure information is neglected during the task-agnostic *** this paper, we propose the Lifting Contrastive Learning (LiftedCL) to obtain 3D-aware human-centric representations which absorb 3D human structure *** particular, to induce the learning process, a set of 3D skeletons is randomly sampled by resorting to 3D human kinematic *** this set of generic 3D samples, 3D human structure information can be learned into 3D-aware representations through adversarial *** results demonstrate that LiftedCL outperforms state-of-the-art self-supervised methods on four human-centric downstream tasks, including 2D and 3D human pose estimation (0.4% mAP and 1.8 mm MPJPE improvement on COCO 2D pose estimation and Human3.6M 3D pose estimation), human shape recovery and human parsing. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Preparation of corrosion-resistant composite coating on AZ91D magnesium alloy through hydrothermal method

引用

MATERIALS AND CORROSION-WERKSTOFFE UND KORROSION 2024年第1期75卷 95-107页

作者： Chen, Shengli Zhu, Jiyuan Guilin Univ Technol Educ Dept Guangxi Zhuang Autonomous Reg Key Lab Adv Mfg & Automation Technol Guilin Peoples R China Guilin Univ Technol Coll Mech & Control Engn Guilin Guangxi Peoples R China Guilin Univ Technol Guilin 541006 Guangxi Peoples R China

The high corrosion susceptibility of magnesium alloy has become a practical problem which restricts its wide application in many fields. To improve its surface properties, a composite coating has been successfully prepared on the surface of AZ91D magnesium alloy using a one-step hydrothermal method. The coating surface possesses a dense structure in the form of scales and has an adhesion strength of 3B. The effect of different preparation conditions on the coating thickness and corrosion resistance is discussed. The coating heated at 180 & DEG;C for 2 h showed the best corrosion resistance in a 3.5 wt% sodium chloride solution, with a reduction in corrosion current density of 5 orders of magnitude compared to the bare sample. This solution significantly improved the corrosion resistance of the magnesium alloy and helped to further realize the application of magnesium alloys in corrosive environments.

关键词： corrosion-resistance hydrothermal method magnesium alloy metal protection

来源：评论

学校读者我要写书评

暂无评论

Camera distance helps 3D hand pose estimated from a single RGB image

引用

GRAPHICAL MODELS 2023年 127卷

作者： Cui, Yuan Li, Moran Gao, Yuan Gao, Changxin Wu, Fan Wen, Hao Li, Jiwei Sang, Nong Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automation Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China CloudWalk Technol Guangzhou Peoples R China Wuhan Univ Elect Informat Sch Wuhan Peoples R China

Most existing methods for RGB hand pose estimation use root-relative 3D coordinates for supervision. However, such supervision neglects the distance between the camera and the object (i.e., the hand). The camera distance is especially important under a perspective camera, which controls the depth-dependent scaling of the perspective projection. As a result, the same hand pose, with different camera distances can be projected into different 2D shapes by the same perspective camera. Neglecting such important information results in ambiguities in recovering 3D poses from 2D images. In this article, we propose a camera projection learning module (CPLM) that uses the scale factor contained in the camera distance to associate 3D hand pose with 2D UV coordinates, which facilities to further optimize the accuracy of the estimated hand joints. Specifically, following the previous work, we use a two-stage RGB-to-2D and 2D-to-3D method to estimate 3D hand pose and embed a graph convolutional network in the second stage to leverage the information contained in the complex non-Euclidean structure of 2D hand joints. Experimental results demonstrate that our proposed method surpasses state-of-the-art methods on the benchmark dataset RHD and obtains competitive results on the STB and D+O datasets.

关键词： Hourglass GCN Hand pose estimation Root-relative joints Coordinates attentions

来源：评论

学校读者我要写书评

暂无评论

Distributed model-free adaptive control for multi-agent systems with external disturbances and DoS attacks

引用

INFORMATION SCIENCES 2022年 613卷 309-323页

作者： Chen, Run-Ze Li, Yuan-Xin Hou, Zhong-Sheng Qingdao Univ Sch Automation Shandong Key Lab Ind Control Technol Qingdao 266071 Peoples R China Liaoning Univ Technol Dept Sci Jinzhou 121001 Peoples R China

This paper presents a distributed consensus control algorithm for nonlinear multi-agent systems (MASs) with external disturbances and denial-of-service (DoS) attacks. Modified dynamic linearization is proposed for the linear transformation of the MASs, and an extended discrete state observer (EDSO) improves their robustness. An attack compensation scheme eliminates the effects of DoS attacks. Based on the EDSO and the attack compensation scheme, a distributed model-free adaptive control (DMFAC) algorithm is developed to achieve consensus control in a boundary, and simulations verify its superiority in tracking time and tracking accuracy over other control algorithms. (c) 2022 Elsevier Inc. All rights reserved.

关键词： Distributed control Model -free adaptive control (MFAC) Denial -of -service (DoS) attacks Extended discrete state observer (EDSO)

来源：评论

学校读者我要写书评

暂无评论

A New Era of Intelligent Vehicles and Intelligent Transportation Systems: Digital Twins and Parallel Intelligence

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES

引用

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES 2023年第4期8卷 2619-2627页

作者： Wang, Ziran Lv, Chen Wang, Fei-Yue Purdue Univ Coll Engn W Lafayette IN 47907 USA Nanyang Technol Univ Sch Mech & Aerosp Engn Singapore 639798 Singapore Chinese Acad Sci Inst Automation State Key Lab Management & Control Complex Syst Beijing Peoples R China

By March 25, our transaction has received a total of 619 original submissions. Our current average number of submissions per day (SPD) rate is 7.37. Given this SPD, I would like to expand our editorial board to includ...

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multiplicative Attacks with Essential Stealthiness in Sensor and Actuator Loops against Cyber-Physical Systems

引用

SENSORS 2023年第4期23卷 1957页

作者： Chen, Jingzhao Liu, Bin Li, Tengfei Hu, Yong Wuhan Univ Sci & Technol Engn Res Ctr Met Automation & Measurement Technol Minist Educ Wuhan 430081 Peoples R China Wuhan Univ Sci & Technol Sch Informat Sci & Engn Wuhan 430081 Peoples R China Beijing Inst Control Engn Sci & Technol Space Intelligent Control Lab Beijing 100190 Peoples R China

Stealthy attacks in sensor and actuator loops are the research priorities in the security of cyber-physical systems. Existing attacks define the stealthiness conditions against the Chi-square or Kullback-Leibler divergence detectors and parameterize the attack model based on additive signals. Such conditions ignore the potential anomalies of the vulnerable outputs in the control layer, and the attack sequences need to be generated online, increasing the hardware and software costs. This paper investigates a type of multiplicative attack with essential stealthiness where the employed model is a novel form. The advantage is that the parameters can be designed in a constant form without having to be generated online. An essential stealthiness condition is proposed for the first time and complements the existing ones. Two sufficient conditions for the existence of constant attack matrices are given in the form of theorems, where two methods for decoupling the unknown variables are particularly considered. A quadruple-tank process, an experimental platform for attack and defense, is developed to verify the theoretical results. The experiments indicate that the proposed attack strategy can fulfill both the attack performance and stealthiness conditions.

关键词： cyber-physical systems cyber-attacks false data injection Kullback-Leibler divergence detector Chi-square detector

来源：评论

学校读者我要写书评

暂无评论

Modeling and identification of rate-dependent and asymmetric hysteresis of soft bending pneumatic actuator based on evolutionary firefly algorithm

引用

MECHANISM AND MACHINE THEORY 2023年 181卷

作者： Ru, Hongge Huang, Jian Chen, Wenbin Xiong, Caihua Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automation Key Lab Image Proc & Intelligent Control Educ Minist China Wuhan Hubei Peoples R China Huazhong Univ Sci & Technol Sch Mech Sci & Engn State Key Lab Digital Mfg Equipment & Technol Wuhan Hubei Peoples R China

Soft-bending pneumatic actuators (SBPA) have shown great potential in various applications owing to their intrinsic compliance. However, motion control is still challenging because of the complicated hysteresis of the elastic material and pneumatic system, which unlike the general hysteresis found in the rigid body mechanism, is rate-dependent and asymmetric. A precise hysteresis model is crucial for improving the performance of SBPA. This study proposed a rate-dependent modified generalized Prandtl-Ishlinskii (RMGPI) model for a vulcanized silicone rubber-based fast pneu-net soft bending pneumatic actuator (fp-SBPA) to describe complicated hysteresis characteristics. A visual feedback system obtained the bending angle in real time. With the increase in the number of operators, the identification of the proposed model parameters became more complicated and time-consuming;thus, an evolutionary firefly algorithm (EFA) was developed to improve identification efficiency. A series of experiments and comparison studies were conducted to verify the effectiveness of the proposed model and identification method.

关键词： Bending pneumatic muscle Rate-dependent and asymmetric hysteresis Prandtl-Ishlinskii (PI) model

来源：评论

学校读者我要写书评

暂无评论

Asynchronous sampled-data control for connected vehicles with heterogeneous delays

引用

ISA TRANSACTIONS 2024年 146卷 127-141页

作者： Wen, Shixi Guo, Ge Dalian Univ Sch Informat Engn Dalian 116622 Peoples R China Dalian Univ Key Lab Adv Design & Intelligent Comp Minist Educ Dalian 116622 Peoples R China Northeastern Univ State Key Lab Synthet Automation Proc Ind Shenyang 110004 Peoples R China Northeastern Univ Qinhuangdao Sch Control Engn Qinhuangdao 066004 Peoples R China

This study investigates an asynchronous sampled -data control problem of vehicular platoons, with heterogeneous sampling, subjected to actuator delays. Without a synchronized clock, a completely asynchronous sampled -data controller is designed for each follower, where the state of the ith follower itself and its neighboring vehicles are sampled at their own sampling time instants. The caused closed -loop tracking error dynamics for the entire platoon considering the effect of the nonuniform sampling time intervals, heterogeneous vehicle dynamics, inter -vehicle topology and heterogeneous time delays. To simplify the stability analysis and controller design, the tracking -error dynamics of the entire platoon are decomposed into individual subsystems with reduced -order dynamics. Based on Lyapunov stability theory, the optimal conditions are explored to design an asynchronous sampled -data controller to guarantee the desired stability performance. Moreover, the exact values for the maximum allowable sampling interval and time delay are calculated for each follower using the designed feedback controller gain. The proposed asynchronous sampled -data control method is extended to a vehicular platoon using an event -based sampling scheme. Numerical examples are used to verify the effectiveness of the proposed sampled -data control method.

关键词： Asynchronous sampled-data control Connected vehicles Heterogeneous time delays Undirected inter-vehicle communication topology String stability

来源：评论

学校读者我要写书评

暂无评论

PDE-based boundary event-triggered control of uncertain flexible manipulator with input nonlinearities

引用

NONLINEAR DYNAMICS 2023年第11期111卷 10229-10246页

作者： Xu, Bo Li, Yuan-Xin Ahn, Choon Ki Qingdao Univ Sch Automation Shandong Key Lab Ind Control Technol Qingdao 266071 Shandong Peoples R China Liaoning Univ Technol Coll Sci Jinzhou 121001 Peoples R China Korea Univ Sch Elect Engn Seoul 136701 South Korea

This study focuses on a novel event-triggered boundary control design of an uncertain flexible manipulator subject to input constraints and external disturbances. To this end, a novel boundary control law is developed based on the Lyapunov stability theory to suppress elastic deflection and regulate the manipulator to track the desired angular position. Moreover, to approximate the unknown functions and compensate for the effect of input constraints, the neural network technique is adopted with an arbitrarily adjustable approximating error. Simultaneously, the event-triggering mechanism is incorporated with a controller design to alleviate the communication load and the execution rate of the actuator. Lastly, numerical simulations are performed to demonstrate the effectiveness of the derived scheme.

关键词： Flexible manipulators Partial differential equations (PDE) Event-triggered control (ETC) External disturbances Input nonlinearities

来源：评论

学校读者我要写书评

暂无评论

MFANet: Multifaceted Feature Aggregation Network for Oil Stains Detection of High-Speed Trains

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2023年第11期24卷 12331-12344页

作者： Liu, Wei Lu, Xiaobo Wei, Yun Ran, Zhidan Southeast Univ Sch Automation Nanjing 210096 Peoples R China Minist Educ Key Lab Measurement & Control Complex Syst Engn Nanjing 210096 Peoples R China Beijing Mass Transit Railway Operat Corp Ltd Beijing 100044 Peoples R China

Oil is of great significance in the key components like the hydraulic damper of high-speed trains and its leaks suggest that some key components may malfunction, bringing potential danger to the safety of the train. It is indispensable to diagnose oil leakage timely and faults can be discovered by detecting oil stains to avoid possible accidents caused by the breakdown. But it is challenging to discover the oil stains due to their irregularity of shape and diversity of size in complex environments. To deal with these intractable problems, we propose the Multifaceted Feature Aggregation Network (MFANet) which is composed of Multifaceted Refinement Feature (MRF) module, Cross Layer Feature Attention (CLFA) module, and Cross Layer Feature Enhancement (CLFE) module. The MRF solves the limitation of the single convolution method's inability to catch changeable oil stains better and captures more expressive features. The CLFA and the CLFE obtain richer information and compensate for the shortcomings of insufficient information on single-layer features. Furthermore, we propose a loss function to guide the learning of our network in the case of the unbalanced dataset, which surpasses the useful Binary Cross-entropy loss. We conduct experiments based on four widely used backbone networks and achieve cutting-edge performance with fewer FLOPs and Parameters compared with many advanced methods. In addition, we perform our MFANet on several challenging saliency detection datasets, the rail surface defects detection dataset, and the COCO-Stuff segmentation dataset, which outperforms some progressive approaches and demonstrates powerful generalization capability and adaptation.

关键词： Oil stains MFANet saliency detection rail surface defects detection COCO-stuff segmentation

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：