检索结果-内蒙古大学图书馆

Finite-size scaling of geometric renormalization flows in complex networks

Physical Review E 2021年第3期104卷 034304-034304页

作者： Dan Chen Housheng Su Xiaofan Wang Gui-Jun Pan Guanrong Chen School of Artificial Intelligence and Automation Image Processing and Intelligent Control Key Laboratory of Education Ministry of China Huazhong University of Science and Technology Wuhan 430074 China Department of Automation Shanghai University Shanghai 200072 China Faculty of Physics and Electronic Science Hubei University Wuhan 430062 China Department of Electronic Engineering City University of Hong Kong 999077 Hong Kong

Some characteristics of complex networks need to be derived from global knowledge of the network topologies, which challenges the practice for studying many large-scale real-world networks. Recently, the geometric renormalization technique has provided a good approximation framework to significantly reduce the size and complexity of a network while retaining its “slow” degrees of freedom. However, due to the finite-size effect of real networks, excessive renormalization iterations will eventually cause these important “slow” degrees of freedom to be filtered out. In this paper, we systematically investigate the finite-size scaling of structural and dynamical observables in geometric renormalization flows of both synthetic and real evolutionary networks. Our results show that these observables can be well characterized by a certain scaling function. Specifically, we show that the critical exponent implied by the scaling function is independent of these observables but depends only on the structural properties of the network. To a certain extent, the results of this paper are of great significance for predicting the observable quantities of large-scale real systems and further suggest that the potential scale invariance of many real-world networks is often masked by finite-size effects.

关键词： Network structure Scale free & inhomogeneous networks Small-world networks Critical exponents Renormalization Renormalization group Self-organized criticality Self-similarity

来源：评论

学校读者我要写书评

暂无评论

Feature Enhanced Faster R-CNN for Object Detection 11

Feature Enhanced Faster R-CNN for Object Detection

引用

11th International Symposium on Multispectral image processing and Pattern Recognition (MIPPR) - Automatic Target Recognition and Navigation

作者： Jiang, Jun Hu, Zhongbing Huazhong Univ Sci & Technol Natl Key Lab Sci & Technol Multispectral Informat Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Minist Educ Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China

ISBN: (纸本)9781510636361

In recent years, deep convolutional neural networks (CNNs) have achieved great successes in object detection, however, feature extraction is still sensitive to scale variation. FPN is one of the majority strategies to deal with this problem. It uses a top-down pathway and lateral connection to combine high-level features with low-level features, and then generates robust features. However, in FPN, high-level features are still unable to capture the detail information, and this results in the inconsistent representations for the same objects with different scales. To solve this problem, we proposed a Feature Enhanced Module to get more robust features, which can help the networks to produce object localization with higher quality, i.e., without bells and whistles. The performance of the proposed method is shown by the experiments in which it achieves a 1.1 point AP50 gain and 2.3 point AP75 gain on the Pascal VOC dataset, comparing to the Faster R-CNN with FPN.

关键词： object detection feature fusion

来源：评论

学校读者我要写书评

暂无评论

Voltage control for Distribution Networks via Coordinated Regulation of Active and Reactive Power of DGs

引用

IEEE TRANSACTIONS ON SMART GRID 2020年第5期11卷 4017-4031页

作者： Hu, Xiong Liu, Zhi-Wei Wen, Guanghui Yu, Xinghuo Liu, Chen Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Minist Educ Wuhan 430074 Peoples R China Southeast Univ Sch Math Dept Syst Sci Nanjing 210096 Peoples R China RMIT Univ Sch Engn Melbourne Vic 3001 Australia

Fast-acting reactive power support from distributed generations (DGs) is a promising approach for tackling rapid voltage fluctuations in distribution networks. However, the voltage regulation range via reactive power of DGs alone is narrow especially in distribution networks with high resistance-reactance ratio. In this paper, a randomized algorithm is proposed to improve the voltage profile in distribution networks via coordinated regulation of the active and reactive power of DGs. To this end, first the variables of the proposed quadratically constrained quadratic programming problem on voltage control are partitioned into disjoint subsets, each of which corresponds to a unique low-dimensional subproblem. Second, these subsets are updated serially in a randomized manner via solving their corresponding subproblems, which overcomes the requirement for system-wide coordination among participating agents and guarantees an optimal solution. Compared with the existing algorithms, the proposed algorithm is resilient to network reconfigurations and achieves a wider voltage regulation range. The effectiveness and convergence performance of the proposed algorithm is validated by the case studies.

关键词： Reactive power Voltage control Distribution networks Regulation Partitioning algorithms Quadratic programming Convergence Voltage control distribution network coordinated regulation quadratically constrained quadratic programming randomized algorithm

来源：评论

学校读者我要写书评

暂无评论

Event-triggered impulsive control on quasi-synchronization of memristive neural networks with time-varying delays

引用

NEURAL NETWORKS 2019年 110卷 55-65页

作者： Zhou, Yufeng Zeng, Zhigang Huazhong Univ Sci & Technol Sch Automat Wuhan 430074 Hubei Peoples R China Educ Minist China Key Lab Image Proc & Intelligent Control Wuhan 430074 Hubei Peoples R China

This paper discusses the quasi-synchronization of memristive neural networks (MNNs) with time-varying delays via event-triggered impulsive and state feedback control approaches. The choice of different initial conditions may lead to the unexpected parameter mismatch in virtue of the state-dependent parameters of MNNs. Thus, the accurate synchronization error level and the exponential convergence rate are derived in view of the comparison principle of impulsive systems and the variable parameter formula. A co-design procedure that can be easily implemented is presented to make the synchronization error converge to a predetermined level. Then, no zeno-behavior is proved to exist in the controlled system with the proposed event-triggered condition. In addition, a self-triggered scheme is proposed to prevent continuous communication happening between the drive system and the response system. Finally, a numerical example is given to illustrate the availability of the proposed control scheme. (C) 2018 Elsevier Ltd. All rights reserved.

关键词： Event triggered Impulsive control Quasi-synchronization Memristive neural networks Time-varying delays

来源：评论

学校读者我要写书评

暂无评论

Weight-Variable Scattering Convolution Networks and Its Application in Electromagnetic Signal Classification

引用

IEEE ACCESS 2019年 7卷 175889-175896页

作者： Zhou, Huaji Mao, Licheng Zheng, Shilian Chen, Shichuan Yang, Lifeng Shen, Weiguo Yang, Xiaoniu Xidian Univ Sch Artificial Intelligence Minist Educ Key Lab Intelligent Percept & Image Understanding Xian 710071 Peoples R China Sci & Technol Commun Informat Secur Control Lab Jiaxing 314033 Peoples R China

Deep learning is an important support for the development of cognitive communication in the cognitive Internet of Things (IoT). Deep convolution neural networks have powerful functional expression and feature extraction capabilities. Mallat et al. proposed a convolutional network model with strict mathematical theory support and excellent feature extraction ability in 2012, i.e., wavelet scattering convolution networks, which is widely used in audio and image classification. In this paper, we improve the wavelet scattering convolution networks and propose construct weight-variable scattering convolution networks by combining the scattering network and the deep convolution neural network organically. We select a variety of wavelet filters for filtering operations and add 1*1 convolution layers to enable the features extracted by different types of wavelet filters to be combined optimally. In order to verify the effectiveness of the proposed network structure, we conduct experiments on classification of typical electromagnetic signals. The experimental results show that the signal classification accuracy obtained by the weight-variable scattering convolution networks is significantly better than that of the traditional wavelet scattering convolution network, and the computational complexity is greatly reduced while the classification accuracy is close to the deep convolution neural network.

关键词： Cognitive communication convolution neural networks scattering convolution networks wavelet electromagnetic signals classification

来源：评论

学校读者我要写书评

暂无评论

Multiple ψ-Type Stability of Cohen-Grossberg Neural Networks With Both Time-Varying Discrete Delays and Distributed Delays

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2019年第2期30卷 566-579页

作者： Zhang, Fanghai Zeng, Zhigang Huazhong Univ Sci & Technol Sch Automat Wuhan 430074 Hubei Peoples R China Minist China Key Lab Image Proc & Intelligent Control Educ Wuhan 430074 Hubei Peoples R China

In this paper, multiple psi-type stability of Cohen-Grossberg neural networks (CGNNs) with both timevarying discrete delays and distributed delays is investigated. By utilizing psi-type functions combined with a new psi-type integral inequality for treating distributed delay terms, some sufficient conditions are obtained to ensure that multiple equilibrium points are psi-type stable for CGNNs with discrete and distributed delays, where the distributed delays include bounded and unbounded delays. These conditions of CGNNs with different output functions are less restrictive. More specifically, the algebraic criteria of the generalized model are applicable to several well-known neural network models by taking special parameters, and multiple different output functions are introduced to replace some of the same output functions, which improves the diversity of output results for the design of neural networks. In addition, the estimation of relative convergence rate of psi-type stability is determined by the parameters of CGNNs and the selection of psi-type functions. As a result, the existing results on multistability and monostability can be improved and extended. Finally, some numerical simulations are presented to illustrate the effectiveness of the obtained results.

关键词： psi-type stability Cohen-Grossberg neural networks (CGNNs) distributed delays time-varying discrete delays

来源：评论

学校读者我要写书评

暂无评论

Prescribed Performance controller Design for DC Converter System With Constant Power Loads in DC Microgrid

引用

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS 2020年第11期50卷 4339-4348页

作者： Xu, Xingchen Liu, Qingshan Zhang, Chuanlin Zeng, Zhigang Huazhong Univ Sci & Technol Sch Automat Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Educ Minist China Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China Southeast Univ Sch Math Nanjing 210096 Peoples R China Southeast Univ Jiangsu Prov Key Lab Networked Collect Intelligen Nanjing 210096 Peoples R China Shanghai Univ Elect Power Coll Automat Engn Shanghai 200090 Peoples R China

In this paper, a composite prescribed performance control strategy is developed for stabilizing dc/dc boost converter feeding constant power loads. First, by employing the exact feedback linearization technique, the nonlinear uncertain dc converter system is first transformed into the Brunovsky's canonical form. Then, a nonlinear disturbance observer is utilized to evaluate the dynamic change of load power and the accuracy of output voltage regulated by feedforward compensation. Next, the prescribed performance controller is elaborately designed to ensure that the tracking error of output voltage is always within the margin of predefined error bounds. Based on the backstepping design approach, the composite nonlinear controller with prescribed performance is determined. Finally, the numerical simulation results are presented to demonstrate the tracking performance of the proposed controller.

关键词： Constant power load (CPL) dc converter system disturbance rejection prescribed performance control recursive design

来源：评论

学校读者我要写书评

暂无评论

Distributed Frequency controller for MT-HVDC Systems Via Adaptive Dynamic Programming

Distributed Frequency Controller for MT-HVDC Systems Via Ada...

引用

第32届中国控制与决策会议

作者： Zhongjie Hu Zhi-Wei Liu Xiong Hu Ming Chi College of Artificial Intelligence and Automation Huazhong University of Science and Technology the Key Laboratory of Image Processing and Intelligent Control Ministry of EducationHuazhong University of Science and Technology

The exact mathematical models of multi-terminal high-voltage direct current（MT-HVDC） systems are hard to be obtained in the practical application of HVDC *** overcome this challenge,a model-free distributed frequency controller for MT-HVDC systems is proposed based on Adaptive dynamic programming（ADP） in this ***,for each AC area,only the local and neighboring sampling data of frequency is required without the MT-HVDC system ***,the proposed controller is distributed which effectively balances the communication burden among the AC ***,the proposed controller makes the connected AC areas share their power reserves via HVDC grids to compensate load disturbances so that the necessary power reserves can be *** simulations carried out on a five-terminal HVDC system evaluate the performance of the proposed controller.

关键词： MT-HVDC system distributed frequency controller adaptive dynamic programming（ADP） neural network reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A large-scale group Success Likelihood Index Method to estimate human error probabilities in the railway driving process

引用

RELIABILITY ENGINEERING & SYSTEM SAFETY 2022年第0期228卷

作者： Zhou, Jian-Lan Yu, Ze-Tai Xiao, Ren-Bin Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Hubei Peoples R China Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Wuhan 430074 Hubei Peoples R China Shenzhen Huazhong Univ Sci & Technol Res Inst Shenzhen 518057 Peoples R China Univ Southern Calif Viterbi Sch Engn Dept Comp Sci Los Angeles CA 90089 USA

Success Likelihood Index Method (SLIM) is widely used to estimate human error probability. However, the traditional SLIM relies on a small number of experts, which may cause biases and undermine its effectiveness. To overcome this drawback, a large number of experts participate to provide fuzzy ratings and negotiate to reduce biases, which forms a large-scale group SLIM (LG-SLIM) problem. The LG-SLIM model is used to negotiate among experts to reach a unanimous agreement of the group. We improve the consensus model by constructing two mathematical programming models that provide the recommendations of both optimum preference adjustments and weight adjustment for the non-cooperative subgroup, which establishes an effective balance between the subjectivities and compromises of experts. Some typical human errors concerning target tasks are estimated in the railway driving process. To verify the proposed LG-SLIM model, the results obtained from it and individuals are compared with the simulation values from the Bayesian network respectively. The comparison shows that the results are consistent with the simulation results and conform to the experience and knowledge in railway driving. The LG-SLIM model is helpful to human error assessment when critical operations need enormous ex-perts to obtain reliable and accurate results.

关键词： Railway operation Success likelihood index method Human error assessment Large-scale group decision -making Consensus model Bayesian network

来源：评论

学校读者我要写书评

暂无评论

Fault detection and assessment for solid oxide fuel cell system gas supply unit based on novel principal component analysis

引用

JOURNAL OF POWER SOURCES 2019年 436卷 226864-000页

作者： Wu, Xiao-long Xu, Yuan-Wu Zhao, Dong-qi Li, Ze-hua Zhong, Xiao-bo Chen, Meng-ting Jiang, Jianhua Deng, Zhonghua Fu, Xiaowei Li, Xi Huazhong Univ Sci & Technol Educ Minist Image Proc & Intelligent Control Key Lab Sch Artificial Intelligence & Automat Wuhan 430074 Hubei Peoples R China Wuhan Univ Sci & Technol Prov Key Lab Intelligent Informat Proc & Realtime Coll Comp Sci & Technol Wuhan 430081 Hubei Peoples R China

After long-term running of solid oxide fuel cell system, the performance degradation of solid oxide fuel cell stack is caused by the fault of gas supply equipment. The more serious problem is that the stack performance does not match external load requirement. In order to guarantee the normal discharge of the stack, the fault detection of the system balance of plant components is a prerequisite for maintaining stack normal state, and is an important guarantee for increasing its operating cycle and remain useful lifetime. This paper proposes a novel statistical method based on principal component analysis and exponentially weighted moving average control chart for solid oxide fuel cell system gas supply fault detection. The gas supply fault is derived from the reformer and heat exchangers of the real system. The fault detection is carried out with collected data of real system and novel detection method. The results show that the novel method has higher efficiency and better effect than the traditional method under the system gas supply fault. Multi-times experimental data of real system is used to verify the robustness of the novel methods on-site fault detection.

关键词： Solid oxide fuel cells (SOFC) Fault detection Gas supplied fault System analysis Principal component analysis (PCA)

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：