检索结果-内蒙古大学图书馆

2019 Jiangsu Annual Conference on Automation, JACA 2019

作者： Han, Ling Wang, Xiangyu Li, Shihua Liu, Jiyu School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education China Aviation Key Laboratory of Science and Technology on Aircraft Control Facri Xian710065 China

This study studies the height and attitude tracking control problem of an unmanned helicopter system with disturbances. A composite controller based on the combination of harmonic disturbance observers and backstepping technique is proposed to achieve asymptotic tracking for height and attitude. Firstly, harmonic disturbance observers (HDOB) are designed to estimate the unknown disturbances affecting each channel. Then, a composite controller is proposed by integrating the backstepping control technique and the HDOB technique together to achieve the height and attitude tracking goal. Stability analysis of the closed-loop system is given. Finally, numerical simulations are presented to verify the efficiency of the proposed control scheme. © 2019 Institution of engineering and Technology. All rights reserved.

关键词： Backstepping

来源：评论

学校读者我要写书评

暂无评论

False Noise Attack Detection for differentially-private distributed control of microgrids

引用

Automatica 2025年 179卷

作者： Feng Ye Xianghui Cao Lin Cai Mo-Yuen Chow School of Automation Southeast University Nanjing 210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing 210096 China Department of Electrical and Computer Engineering University of Victoria Victoria BC V8W 3P6 Canada UM-SJTU Joint Institute Shanghai Jiao Tong University Shanghai 200240 China

Privacy preserving in distributed control is getting more attention, and differential privacy (DP) is the common tool to protect data privacy, in which additive noise is applied in the algorithm function. However, DP can be leveraged by false noise (FN) attacks because attack vectors can be disguised as artificial noise in DP. FN attacks are a concern as the stealth attacks are hard to detect. Moreover, DP in distributed control makes FN attack detection more difficult. Hence, detecting FN attacks in privacy-preserving distributed control is critical and challenging. In this paper, taking distributed energy management systems as the control object, we propose a novel peer-to-peer attack detection approach, named False Noise Attack Detection (FNAD). In FNAD, each device observes the power decisions of its neighbors based on the data from its two-hop neighbors, estimates the power decisions of its neighbors by a Kalman filter, and updates the detection index of each neighbor according to the residues of the Kalman filter at each iteration. The detection index is developed based on information entropy, without any prior knowledge of the FN attacks. If a device’s detection index is out of well-defined thresholds, its neighbors can perform a majority vote to decide whether it is malicious. We theoretically prove the detection effect of FNAD against three representative attacks in the literature and analyze the advantages of FNAD compared with the traditional methods. The effectiveness of FNAD is demonstrated by extensive simulations.

关键词： State estimation

来源：评论

学校读者我要写书评

暂无评论

Deep Rank-Consistent Pyramid Model for Enhanced Crowd Counting

arXiv

引用

arXiv 2022年

作者： Gao, Jiaqi Huang, Zhizhong Lei, Yiming Shan, Hongming Wang, James Z. Wang, Fei-Yue Zhang, Junping The Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai200433 China The Institute of Science and Technology for Brain-inspired Intelligence MOE Frontiers Center for Brain Science Fudan University Shanghai200433 China The Shanghai Center for Brain Science and Brain-Inspired Technology Shanghai201210 China The College of Information Sciences and Technology The Pennsylvania State University University ParkPA16802 United States The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China The Institute of Systems Engineering Macau University of Science and Technology China Qingdao Academy of Intelligent Industries Qingdao266109 China

Most conventional crowd counting methods utilize a fully-supervised learning framework to establish a mapping between scene images and crowd density maps. They usually rely on a large quantity of costly and time-intensive pixel-level annotations for training supervision. One way to mitigate the intensive labeling effort and improve counting accuracy is to leverage large amounts of unlabeled images. This is attributed to the inherent self-structural information and rank consistency within a single image, offering additional qualitative relation supervision during training. Contrary to earlier methods that utilized the rank relations at the original image level, we explore such rank-consistency relation within the latent feature spaces. This approach enables the incorporation of numerous pyramid partial orders, strengthening the model representation capability. A notable advantage is that it can also increase the utilization ratio of unlabeled samples. Specifically, we propose a Deep Rank-consistEnt pyrAmid Model (DREAM), which makes full use of rank consistency across coarse-to-fine pyramid features in latent spaces for enhanced crowd counting with massive unlabeled images. In addition, we have collected a new unlabeled crowd counting dataset, FUDAN-UCC, comprising 4,000 images for training purposes. Extensive experiments on four benchmark datasets, namely UCF-QNRF, ShanghaiTech PartA and PartB, and UCF-CC-50, show the effectiveness of our method compared with previous semi-supervised methods. The codes are available at https://***/bridgeqiqi/DREAM. Copyright © 2022, The Authors. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Distributed PV Identification Based on High-Precision Bus Data Analysis

Distributed PV Identification Based on High-Precision Bus Da...

引用

IEEE International Conference on Networking, Sensing and control

作者： Xincheng Shen Shaoxiong Huang Zhi Li Kaifeng Zhang Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing China Center State Grid Anhui Electric Power Co. Ltd. Hefei China

ISBN: (数字)9781728168555

ISBN: (纸本)9781728168562

With the rapid development of distributed photovoltaic (PV), it is necessary to study its low-cost output identification technology. In this paper, a low-cost PV output identification method is proposed by using feature extraction. This paper analyzes the high-precision bus data, and uses harmonic analysis, wavelet analysis and Ensemble Empirical Mode Decomposition (EEMD) to extract the operating features of PV output. Then this paper screens these extracted features with the correlation between features and PV output, the stability of the features at different times and the difference of features in different signals. The appropriate features are selected for PV output identification, and its identification accuracy is calculated. The experimental results show that with the method of the Ensemble Empirical Mode Decomposition, an appropriate operating feature can be extracted. This feature can identify the distributed PV output in small bus bar when the PV is working stably.

关键词： Photovoltaic systems Empirical mode decomposition Feature extraction Wavelet analysis Stability analysis Sensors Data mining

来源：评论

学校读者我要写书评

暂无评论

3D face landmarking with denoise auto-encoder networks 11

3D face landmarking with denoise auto-encoder networks

引用

11th International Conference on Digital Image Processing, ICDIP 2019

作者： Wang, Liang Gai, Shaoyan Guo, Shuai School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China Cardiff University CF103AT United Kingdom

ISBN: (数字)9781510630765

ISBN: (纸本)9781510630758

3D Facial landmarking plays an important role on 3D face recognition and face expression recognition. However, the most of methods underperform when faces have occluded region such as hair, glasses or finger. To solve this problem, a coarseto-fine method is proposed, containing several denoising auto-encoder networks (denoted as DANs). DANs not only can recover the lost information but improve the accuracy of landmarking. Tests based on Bosphorus dataset show a 100% of good landmarking under 6mm precision of mean error, which demonstrates that our algorithm achieves the state-of-theart performance. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Statistical tests

来源：评论

学校读者我要写书评

暂无评论

Single-shot fringe projection profilometry based on deep learning and computer graphics

arXiv

引用

arXiv 2021年

作者： Wang, Fanzhou Wang, Chenxing Guan, Qingze School of Automation Southeast University 2# Sipailou Xuanwu Nanjing210096 China Key laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing210096 China Department of Computer Science University College London Gower St Bloomsbury LondonWC1E 6BT United Kingdom

Multiple works have applied deep learning to fringe projection profilometry (FPP) in recent years. However, to obtain a large amount of data from actual systems for training is still a tricky problem, and moreover, the network design and optimization still worth exploring. In this paper, we introduce computer graphics to build virtual FPP systems in order to generate the desired datasets conveniently and simply. The way of constructing a virtual FPP system is described in detail firstly, and then some key factors to set the virtual FPP system much close to the reality are analyzed. With the aim of accurately estimating the depth image from only one fringe image, we also design a new loss function to enhance the quality of the overall and detailed information restored. And two representative networks, U-Net and pix2pix, are compared in multiple aspects. The real experiments prove the good accuracy and generalization of the network trained by the data from our virtual systems and the designed loss, implying the potential of our method for applications. Copyright © 2021, The Authors. All rights reserved.

关键词： Computer graphics

来源：评论

学校读者我要写书评

暂无评论

Data-free point cloud network for 3d face recognition

arXiv

引用

arXiv 2019年

作者： Zhang, Ziyu Da, Feipeng Yu, Yi School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering

Point clouds-based Networks have achieved great attention in 3D object classification, segmentation and indoor scene semantic parsing. In terms of face recognition, 3D face recognition method which directly consume point clouds as input is still under study. Two main factors account for this: One is how to get discriminative face representations from 3D point clouds using deep network;the other is the lack of large 3D training dataset. To address these problems, a data-free 3D face recognition method is proposed only using synthesized unreal data from statistical 3D Morphable Model to train a deep point cloud network. To ease the inconsistent distribution between model data and real faces, different point sampling methods are used in train and test phase. In this paper, we propose a curvatureaware point sampling(CPS) strategy replacing the original furthest point sampling(FPS) to hierarchically downsample feature-sensitive points which are crucial to pass and aggregate features deeply. A PointNet++ like Network is used to extract face features directly from point clouds. The experimental results show that the network trained on generated data generalizes well for real 3D faces. Fine tuning on a small part of FRGCv2.0 and Bosphorus, which include real faces in different poses and expressions, further improves recognition accuracy. Copyright © 2019, The Authors. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Joint angle measurement of manipulator and error compensation based on an IMU sensor

Joint angle measurement of manipulator and error compensatio...

引用

7th International Symposium on Test Automation and Instrumentation, ISTAI 2018

作者： Zhang, Tianlin Chen, Sheng Xu, Guozheng Wang, Chao Tan, Caiming School of Automation Nanjing University of Posts and Telecommunications Nanjing210023 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing210096 China

To detect the joint angle of the manipulator accurately, a measuring method based on an IMU sensor is proposed. The sensor's attitude angles and corresponding rotation matrix are obtained according to the data of three-axis gyroscope and three-axis accelerometer. During the installation, the sensor's Z-axis direction is kept along with the motor's rotation axis direction, so that the angle of the sensor rotating around its Z-axis, which is the rotation angle of the motor, can be calculated by comparing the rotation relationship between the sensor's initial position and the sensor's position after the motor rotating. The largest source of result error derives from the inconsistent between the sensor's Z-axis direction and the motor's rotation axis direction. Consequently, an installation's error compensation method is designed to correct the sensor's Z-axis to the motor's rotation axis by rotating the related motor. The experiments show that the method can measure the joint angle of the manipulator accurately and calibrate the installation error effectively. The measurement result errors are confined © 2019 Institution of engineering and Technology. All rights reserved.

关键词： Manipulators

来源：评论

学校读者我要写书评

暂无评论

Finite-time Consensus for Second-order Multi-agent systems Based on Embedded control

Finite-time Consensus for Second-order Multi-agent Systems B...

引用

Chinese Automation Congress (CAC)

作者： Quanwei Wu Xiangyu Wang Guodong Wang Chuanlin Zhang School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing People’s Republic of China College of Automation Engineering Shanghai University of Electric Power People’s Republic of China

ISBN: (数字)9781728176871

ISBN: (纸本)9781728176888

This paper studies the finite-time consensus problem for both leader-follower and leaderless second-order multi-agent systems. To solve the problem, a nonsmooth embedded control scheme is used, which is made up of two parts. In part one, for each case, based on nonsmooth control theory, a distributed virtual signal generator is designed. For the leaderless case, the outputs of the designed generator reach finite-time consensus and for the leader-follower case, virtual position and velocity signals of the designed generator track the leader's position and velocity in finite time. In part two, for each case, through embedding the generator into the feedback loop and taking its outputs (i.e., outputs for the leaderless case and virtual position and velocity signals for the leader-follower case) as the reference outputs for the agents (i.e., all the agents for the leaderless case and the followers for the leader-follower case), some tracking controllers are designed for the agents to track their reference outputs in finite time. Based on this scheme, some consensus algorithms are proposed. Under the proposed consensus algorithms, leaderless and leader-follower multi-agent systems achieve finite-time consensus. Numerical simulations verify the validity of the proposed consensus algorithms.

关键词： Consensus algorithm Signal generators Multi-agent systems Topology Consensus protocol Generators Automation

来源：评论

学校读者我要写书评

暂无评论

An Attention Convolutional Neural Network for Forest Fire Smoke Recognition

An Attention Convolutional Neural Network for Forest Fire Sm...

引用

International Conference on systems and Informatics (ICSAI)

作者： Dexiong Zhang Yichao Cao Guangming Zhang Xiaobo Lu Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing China

ISBN: (数字)9781728152561

ISBN: (纸本)9781728152578

In order to find forest fire in time and accurately, the identification of forest fire smoke based on computer vision has become an important research direction. In this paper, a convolutional neural network model based on the attention mechanism is designed for forest fire smoke recognition. By focusing on the regions with obvious discrimination in the image, more precise local features are extracted for fire smoke identification with the auxiliary of backbone network. The performance of network on the unbalanced forest fire dataset is improved by optimizing the cross-entropy loss function with weights. The experimental results show that attention convolutional neural network improves the accuracy of the model which reached 89.3% while reducing false positives and false negatives.

关键词： Forestry Feature extraction Training Convolutional neural networks Convolution Machine learning

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：