检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Jiang, Xia Zeng, Xianlin Sun, Jian Chen, Jie Key Laboratory of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology Beijing100081 China Beijing Institute of Technology Chongqing Innovation Center Chongqing401120 China Ministry of Education Beijing100081 China School of Electronic and Information Engineering Tongji University Shanghai200082 China

This paper develops distributed synchronous and asynchronous algorithms for the large-scale semi-definite programming with diagonal constraints, which has wide applications in combination optimization, image processing and community detection. The information of the semi-definite programming is allocated to multiple interconnected agents such that each agent aims to find a solution by communicating to its neighbors. Based on low-rank property of solutions and the Burer-Monteiro factorization, we transform the original problem into a distributed optimization problem over unit spheres to reduce variable dimensions and ensure positive semi-definiteness without involving semi-definite projections, which are computationally expensive. For the distributed optimization problem, we propose distributed synchronous and asynchronous algorithms, both of which reduce computational burden and storage space compared with existing centralized algorithms. Specifically, the distributed synchronous algorithm almost surely escapes strict saddle points and converges to the set of optimal solutions to the optimization problem. In addition, the proposed distributed asynchronous algorithm allows communication delays and converges to the set of critical points to the optimization problem under mild conditions. By applying proposed algorithms to image segmentation applications, we illustrate the efficiency and convergence performance of the two proposed algorithms. © 2021, CC BY.

关键词： optimization

来源：评论

学校读者我要写书评

暂无评论

Fault Diagnosis of Micro Grid Inverter Based on Wavelet Transform and Probabilistic Neural Network

Fault Diagnosis of Micro Grid Inverter Based on Wavelet Tran...

引用

第三十九届中国控制会议

作者： Xin Gong Nan Wang Yiqiong Zhang Shuai Yin Mingyang Wang Genping Wu School of Automation China University of Geosciences (Wuhan) Hubei Provincial Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan Second Ship Design and Research Institute

This paper focuses on the fault diagnosis of IGBT switch for microgrid three-phase inverters. Based on the analysis of all kinds of fault mechanisms, firstly, the fault simulation model of microgrid inverter is built on MATLAB/Simulink to simulate the fault state of inverter switch under various faults. The load-side three-phase current fault data is collected. Then, wavelet transform is used to extract feature parameters, and normalize the process in the form of energy to construct the fault feature vector. Finally, the genetic algorithm-based probability neural network(PNN) is used for classification. The experimental results show that the method that combining wavelet transform and PNN can diagnose the faults of microgrid inverter accurately and effectively.

关键词： Inverter Fault diagnosis Wavelet transform Genetic algorithm Probabilistic neural network

来源：评论

学校读者我要写书评

暂无评论

An Interpretability Analysis of Travel Decision Learning in Cyber-Physical-Social-systems

An Interpretability Analysis of Travel Decision Learning in ...

引用

Digital Twins and Parallel Intelligence (DTPI), IEEE International Conference on

作者： Miao Guo Peijun Ye Xudong Liu Sheng Liu Gang Xiong Liguo Zhang The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Faculty of Information and Technology Beijing University of Technology Beijing China The Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing China The Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing The Cloud Computing Center Chinese Academy of Sciences Beijing China

In the few decades, the rise of Internet and social media has fundamentally changed the management, control, and operation modes of modern engineering and social systems like defense, energy, critical health care and ... 详细信息

关键词： Deep learning Social networking (online) Scalability Perturbation methods Neurons Transportation Transforms

来源：评论

学校读者我要写书评

暂无评论

Distributed Event-Triggered Attitude Estimation Without Angular Velocity Measurements

引用

IEEE Transactions on control of Network systems 2025年

作者： Li, Shanshan Jin, Xin Li, Yichun Li, Fangfei Werner, Herbert Tang, Yang East China University of Science and Technology Key Laboratory of Smart Manufacturing in Energy Chemical Process Ministry of Education Shanghai200237 China Fudan University Research Institute of Intelligent Complex Systems Shanghai200433 China East China University of Science and Technology Department of Mathematics Shanghai200237 China Hamburg University of Technology Institute of Control Systems Hamburg21073 Germany

In this paper, a distributed event-triggered attitude estimation problem is considered for multiple rigid body systems on SO(3). The error in attitude estimation converges asymptotically to a common orientation among multiple rigid body systems, based on relative attitude measurements under undirected graphs. To eliminate the reliance on direct angular velocity measurements, a cascaded estimation scheme is proposed, employing indirected angular velocity estimation through a single vector measurement that is readily accessible using accelerometers or magnetometers. An event-triggered condition (ETC), grounded in clock variables, is proposed to reduce the communication and computation requirements associated with the attitude estimation. Subsequently, a rigorous convergence analysis of the attitude estimation errors is conducted, relying upon a stability criteria of invariant sets for cascade-connected systems. Furthermore, a self-triggered condition is developed to overcome the challenge of continuous monitoring throughout the event detection process. Ultimately, the efficacy of the proposed framework is validated through a numerical simulation encompassing multiple small satellites. © 2014 IEEE.

关键词： Velocity measurement

来源：评论

学校读者我要写书评

暂无评论

Joint Face Alignment and 3D Face Reconstruction with Efficient Convolution Neural Networks

Joint Face Alignment and 3D Face Reconstruction with Efficie...

引用

International Conference on Pattern Recognition

作者： Keqiang Li Huaiyu Wu Xiuqin Shang Zhen Shen Gang Xiong Xisong Dong Bin Hu Fei-Yue Wang School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China The Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing China The Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan China

3D face reconstruction from a single 2D facial image is a challenging and concerned problem. Recent methods based on CNN typically aim to learn parameters of 3D Morphable Model (3DMM) from 2D images to render face alignment and 3D face reconstruction. Most algorithms are designed for faces with small, medium yaw angles, which is extremely challenging to align faces in large poses. At the same time, they are not efficient usually. The main challenge is that it takes time to determine the parameters accurately. In order to address this challenge with the goal of improving performance, this paper proposes a novel and efficient end-to-end framework. We design an efficient and lightweight network model combined with Depthwise Separable Convolution and Muti-scale Representation, Lightweight Attention Mechanism, named Mobile-FRNet. Simultaneously, different loss functions are used to constrain and optimize 3DMM parameters and 3D vertices during training to improve the performance of the network. Meanwhile, extensive experiments on the challenging datasets show that our method significantly improves the accuracy of face alignment and 3D face reconstruction. Model parameters and complexity of our method are also improved greatly.

关键词： Training Solid modeling Three-dimensional displays Convolution Face recognition Neural networks complexity theory

来源：评论

学校读者我要写书评

暂无评论

Model-free Output Consensus control for Nonlinear Multi-agent systems with Random Disturbance

Model-free Output Consensus Control for Nonlinear Multi-agen...

引用

Industrial Cyber-Physical systems (ICPS)

作者： Yipu Sun Xin Chen Hao Fu School of Automation China University of Geosciences Wuhan P. R. China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China

ISBN: (数字)9781728163895

ISBN: (纸本)9781728163901

The model-free output consensus control problem for the nonlinear multi-agent systems (MASs) with random disturbance is considered. In order to avoid the difficulty of designing a consensus protocol when the dynamic model is unknown, this paper proposes an online learning method for a consensus protocol by Gaussian regression based two-phase iteration. First, output of the leader is estimated by an adaptive distributed observer. On this basis, measurable input/output data is used to solve the consensus control problem of model-free systems. A two-phase iteration for Gaussian-kernel based adaptive critic design (GK-ACD) is proposed to approximate optimal Q-function and optimal control policies, which can simultaneously approximate and update value functions and hyper-parameters. This avoids the problem of artificial selection of improper hyper-parameters may mislead the kernel-based regression. Finally, the simulation results show that, without knowledge of dynamics, the distributed policies achieves the output consensus control of nonlinear MASs, and proves the effectiveness of the method.

关键词： Observers Adaptation models Vehicle dynamics System dynamics Synchronization Nonlinear dynamical systems Multi-agent systems

来源：评论

学校读者我要写书评

暂无评论

A Low-Cost Enhanced Heterogeneous Barrier Construction Method for Multi-Target Intrusion Monitoring

引用

IEEE Sensors Journal 2025年

作者： Ye, Jing Xiong, Yonghua Dong, Haobin Yu, Anjun She, Jinhua China University of Geosciences School of Automation Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Ministry of Education Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan430074 China Jiangxi Ganyue Expressway Company Ltd Nanchang330200 China Tokyo University of Technology School of Engineering Tokyo192-0982 Japan

In multi-target intrusion monitoring, heterogeneous nodes may overlap due to different sensing ranges. Additionally, excessively long barriers will increase the cost of barriers and reduce the number of barriers. To address these issues, this article proposes a distributed method for constructing weighted heterogeneous barriers using depth-first search and learning automata (WHBDLA). It designs a dynamically weighted coverage graph based on the non-overlap rate and horizontal displacement. The proposed method considers multiple heterogeneous properties. It uses several intrusion targets to identify the boundaries of local sub-regions while avoiding the cost increase and quantity decrease caused by long barriers. WHBDLA combines the advantages of depth-first search and the reinforcement learning mechanism to adaptively construct heterogeneous barriers in sub-regions with unknown faults. The algorithm initially searches for potential barrier path nodes and then activates nodes with sufficient energy and high weights. Finally, it monitors and repairs the barriers. Comparative experiments and analyses indicate that the proposed method increases the number of barriers, reduces node costs, and decreases running time. © 2001-2012 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Fast Calibration of Agent-Based Model using Mean-Field Approach

Fast Calibration of Agent-Based Model using Mean-Field Appro...

引用

Digital Twins and Parallel Intelligence (DTPI), IEEE International Conference on

作者： Wanze Lu Gang Xiong Xudong Liu Sheng Liu Peijun Ye Liguo Zhang Faculty of Information and Technology Beijing University of Technology Beijing China The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China The Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing China The Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing The Cloud Computing Center Chinese Academy of Sciences Beijing China

Calibration of simulation system is an important step to establish a reliable simulation system. In this paper, based on the existing mean field calibration theory, a new fast calibration method for complex urban traffic system based on mean field method is discussed by establishing the relationship between the macroscopic observation quantity and the proxy microscopic parameters. This method makes use of the machine learning method, and reduces the dimension of the state vector in the discrete time period, so that the dimension of the macroscopic state transition matrix is lower, and then reduces the computational complexity of the system calibration. Finally, the calibration results of the simulation system were verified by SUMO traffic simulation software.

关键词： Visualization Computational modeling Microscopy Digital twin Machine learning Traffic control Reliability theory

来源：评论

学校读者我要写书评

暂无评论

Learning Multiple Network Embeddings for Social Influence Prediction ⁎

引用

IFAC-PapersOnLine 2020年第2期53卷 2868-2873页

作者： Feng Wang Jinhua She Yasuhiro Ohyama Min Wu School of Automation China University of Geosciences Wuhan 430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan 430074 China School of Engineering Tokyo University of Technology Tokyo 192-0982 Japan

How to effectively predict social influence is an essential issue in social network analysis. Almost all reported methods for social influence prediction are mainly concerned with estimating influence probabilities for each linking edge. However, all of this past work cannot accurately predict influence probabilities for all edges due to the problem of data sparsity. Unlike conventional approaches, this work focuses on exploring a cross problem for multiple network embeddings and social influence prediction. This study developed a new end-to-end approach, Multi-Influor, that learns multiple influence vectors for each user in social networks, instead of estimating influence probabilities for each edge. The multiple network embeddings consider multi-dimensional influence factors that incorporate pairwise node interactions, network structures, and global similarity comparisons. Moreover, this study solves the problem of influence evaluation caused by sparse observations. Extensive comparisons based on large-scale datasets indicate that the Multi-Influor approach outperforms several state-of-the-art baselines, and the experimental results demonstrate that the Multi-Influor approach is more practical on real-world social networks.

关键词： Multiple Network Embeddings Representation Learning Online Social Networks Neural Network Social Influence Prediction

来源：评论

学校读者我要写书评

暂无评论

Solving optimal power flow using cuckoo search algorithm with feedback control and local search mechanism

IAENG International Journal of Computer Science

引用

IAENG International Journal of Computer Science 2019年第2期46卷 321-331页

作者： Chen, Gonggui Yi, Xingting Zhang, Zhizhong Qiu, Shiyuan Key Laboratory of Network control and Intelligent Instrument Chongqing University of Posts and Telecommunications Ministry of Education Chongqing400065 China Key Laboratory of Complex Systems and Bionic Control Chongqing University of Posts and Telecommunications Chongqing400065 China Key Laboratory of Communication Network and Testing Technology Chongqing University of Posts and Telecommunications Chongqing400065 China Software Technology Co. Ltd Suzhou215000 China

Cuckoo search (CS) algorithm is a novel heuristic algorithm, which can effectively solve the optimization problem by simulating the brood parasitism of some cuckoo species and combining with Lévy flight mechanism. However, it has also been shown to have certain weaknesses, especially falling into local optimums. Therefore, a novel CS algorithm with feedback control and local search mechanism (FLCS) is proposed in this paper. In the FLCS, feedback control is introduced to enhance the efficiency of search process, and local search mechanism is guided by the global optimal solution for improving the poor local search ability of CS method. To verify the performance of our approach, 21 test functions of different types are first employed. Then, the FLCS has been performed on the IEEE 30-bus power flow test case for optimal power flow (OPF) problem with valve point effect. The results indicate that the proposed FLCS method clearly has better performance than CS in the solution accuracy and convergence speed. In addition, the comparison results show that FLCS performs better than other evolutionary methods from literature for different functions. © International Association of Engineers.

关键词： Feedback control

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：