检索结果-内蒙古大学图书馆

Adaptive Distributed State and Input Estimation Using Retrospective-Cost-Based Information Filter

学校读者我要写书评

暂无评论

Adaptive Distributed State and Input Estimation Using Retros...

第三十九届中国控制会议

作者： Hong Wang Liang Han Yuan Liang Xiwang Dong Qingdong Li Zhang Ren School of Automation Science and Electrical Engineering Science and Technology on Aircraft Control Laboratory Beihang University School of Sino-French Engineer Beihang University Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University

In this paper, the problem of distributed state and input estimation using sensor networks for linear system is investigated. First, the retrospective-cost-based information filter（RCIF） is proposed to estimate the state and input simultaneously, by combining the retrospective cost input estimator subsystem and information filter state estimator subsystem. Next, the retrospective-cost adaptive input estimator subsystem is formulated, which utilizes retrospective cost optimization and recursive minimum mean square estimation to drive the estimated input to approximate the actual input without prior information. Then,the consensus algorithm is used to extend the RCIF to distributed estimation, and to improve the convergence rate, the adaptive update law of consensus weights is presented. Finally, a simulation example is illustrated to validate the effectiveness and feasibility of the proposed algorithm.

关键词： Adaptive Distributed Estimation State estimation Input estimation Retrospective cost optimization Consensus

Distributed State Estimation for Heterogeneous Mobile Sensor Networks with Varying Nodes

学校读者我要写书评

暂无评论

Distributed State Estimation for Heterogeneous Mobile Sensor...

第三十九届中国控制会议

作者： Yingrong Yu Jie Ren Xiwang Dong Qingdong Li Science and Technology on Aircraft Control Laboratory School of Automation Science and Electrical Engineering Beihang University Beijing Aerospace System Engineering Research Institute Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University

On background of cooperative air combat, state estimation of aerial maneuvering target with multi-sensor cooperative reconnaissance is discussed in this paper. Multiple moving platforms equipped with different kinds of detectors construct heterogeneous mobile sensor networks. Graph theory is adopted to describe the communication topology of the networks. In consideration of detection range limit, the number of sensors participating in the detection changes over time. An interactive multiple model algorithm（IMM） is utilized for target motion modeling. The local observation information is processed by Cubature Information Filter（CIF）. A weighted average consensus-based state estimation method for heterogeneous mobile sensor networks with varying nodes is put forward to fuse information from different sensors and obtain a consistent and precise tracking result. Moreover, the stability analysis of proposed method is provided detailed. Finally, numerical simulation results are given to illustrate the effectiveness of the theoretical results.

关键词： Cubature Information Filter consensus theory distributed state estimation mobile sensor networks stochastic boundedness

Matrix Classifier On Dynamic Functional Connectivity For Mci Identification

学校读者我要写书评

暂无评论

Matrix Classifier On Dynamic Functional Connectivity For Mci...

IEEE International Conference on Image Processing

作者： Lei Zhou Liang Zhang Xiao Bai Jun Zhou School of Computer Science and Engineering Beijing Advanced Innovation Center for Big Data and Brain Computing State Key Laboratory of Software Development Environment Beihang University Beijing School of Information and Communication Technology Griffith University Nathan

ISBN: (数字)9781728163956

ISBN: (纸本)9781728163963

One of the most popular method for Alzheimer's disease (AD) diagnosis is exploring the brain functional connectivity (FC) from resting-state functional magnetic resonance imaging (RS-fMRI). To early prevent AD, it is crucial to distinguish AD and and its preclinical stage, mild cognitive impairment (MCI) and early MCI (eMCI). In many existing works, dynamic functional connectivity (dFC) which contains rich spatiotemporal information has been exploited for the MCI and eMCI identification. However, most of these dFC based methods only consider the correlation between discrete brain status while ignore the valuable spatiotemporal information contained in dFC. To overcome this limitation, we propose a matrix classifier based method on the dFC signal for MCI and eMCI identification. Specifically, we first represent the dFC correlations by matrix features which contain rich spatiotemporal information and then learn the support matrix machines (SMM) to classify AD and its preclinical stage. Experiments on 600 real people data provide by the Alzheimer's Disease Neuroimaging Initiative (ADNI) demonstrate that our proposed matrix classifier based method outperforms other FC and dFC based methods for both normal controls (NC)/MCI identification and NC/eMCI identification.

关键词： Feature extraction Correlation Dementia Microsoft Windows Spatiotemporal phenomena Training

Representation Learning of Graphs Using Graph Convolutional Multilayer Networks Based on Motifs

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Li, Xing Wei, Wei Feng, Xiangnan Liu, Xue Zheng, Zhiming School of Mathematical Science Beihang University Beijing China Key Laboratory of Mathematics Informatics Behavioral Semantics Ministry of Education China Peng Cheng Laboratory Shenzhen Guangdong China and Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China School of Mathematical Science Beihang University Beijing China Key Laboratory of Mathematics Informatics Behavioral Semantics Ministry of Education China and Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China

The graph structure is a commonly used data storage mode, and it turns out that the low-dimensional embedded representation of nodes in the graph is extremely useful in various typical tasks, such as node classification, link prediction, etc. However, most of the existing approaches start from the binary relationship (i.e., edges) in the graph and have not leveraged the higher order local structure (i.e., motifs) of the graph. Here, we propose mGCMN – a novel framework which utilizes node feature information and the higher order local structure of the graph to effectively generate node embeddings for previously unseen data. Through research we have found that different types of networks have different key motifs. And the advantages of our method over the baseline methods have been demonstrated in a large number of experiments on citation network and social network datasets. At the same time, a positive correlation between increase of the classification accuracy and the clustering coefficient is revealed. It is believed that using high order structural information can truly manifest the potential of the network, which will greatly improve the learning efficiency of the graph neural network and promote a brand-new learning mode establishment. Copyright © 2020, The Authors. All rights reserved.

关键词： Graph neural networks

Graph classification based on skeleton and component features

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Liu, Xue Wei, Wei Feng, Xiangnan Cao, Xiaobo Sun, Dan Beijing System Design Institute of Electro-Mechanic Engineering Beijing100854 China School of Mathematical Sciences Beihang University Beijing100191 China Key Laboratory of Mathematics Informatics and Behavioral Semantics Ministry of Education 100191 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China Peng Cheng Laboratory Shenzhen Guangdong518066 China

Most existing popular methods for learning graph embedding only consider fixed-order global structural features and lack structures hierarchical representation. To address this weakness, we propose a novel graph embedding algorithm named GraphCSC that realizes classification based on skeleton information using fixed-order structures learned in anonymous random walks manner, and component information using different size subgraphs. Two graphs are similar if their skeletons and components are both similar, thus in our model, we integrate both of them together into embeddings as graph homogeneity characterization. We demonstrate our model on different datasets in comparison with a comprehensive list of up-to-date state-of-the-art baselines, and experiments show that our work is superior in real-world graph classification tasks. © 2021, CC BY.

关键词： Musculoskeletal system

Distributed State Estimation for Nonlinear Networked System with Correlated Noises

学校读者我要写书评

暂无评论

Distributed State Estimation for Nonlinear Networked System ...

International Conference on Control, Automation, Robotics and Vision (ICARCV)

作者： Yuan Liang Sibo Hu Xiwang Dong Qingdong Li Zhang Ren School of Automation Science and Electrical Engineering Beihang University Beijing P. R. China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing P. R. China

ISBN: (数字)9781728177090

ISBN: (纸本)9781728177106

In this paper, the problem of distributed state estimation for nonlinear networked system with correlated noises is investigated. First, a distributed weighted consensus-based cubature information filtering algorithm is designed, of which the goal is to achieve accurate estimated states with the presence of correlated noises in a fully distributed fashion. Then based on the statistical linear approximation method, it is further proved that, the estimated states of the proposed filtering algorithm are consistent. Finally, the improved performance of the proposed filtering algorithm are confirmed by the numerical simulation.

关键词： Sensors Sensor fusion Noise measurement Sensor systems Wireless sensor networks State estimation Kalman filters

Graph entropy guided Node Embedding Dimension Selection for Graph Neural Networks

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Luo, Gongxu Li, Jianxin Su, Jianlin Peng, Hao Yang, Carl Sun, Lichao Yu, Philip S. He, Lifang Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University China School of Computer Science and Engineering Beihang University China Shenzhen Zhuiyi Technology Co. Ltd China Department of Computer Science Emory University United States Department of Computer Science and Engineering Lehigh University United States Department of Computer Science University of Illinois Chicago United States

Graph representation learning has achieved great success in many areas, including e-commerce, chemistry, biology, etc. However, the fundamental problem of choosing the appropriate dimension of node embedding for a given graph still remains unsolved. The commonly used strategies for Node Embedding Dimension Selection (NEDS) based on grid search or empirical knowledge suffer from heavy computation and poor model performance. In this paper, we revisit NEDS from the perspective of minimum entropy principle. Subsequently, we propose a novel Minimum Graph Entropy (MinGE) algorithm for NEDS with graph data. To be specific, MinGE considers both feature entropy and structure entropy on graphs, which are carefully designed according to the characteristics of the rich information in them. The feature entropy, which assumes the embeddings of adjacent nodes to be more similar, connects node features and link topology on graphs. The structure entropy takes the normalized degree as basic unit to further measure the higher-order structure of graphs. Based on them, we design MinGE to directly calculate the ideal node embedding dimension for any graph. Finally, comprehensive experiments with popular Graph Neural Networks (GNNs) on benchmark datasets demonstrate the effectiveness and generalizability of our proposed MinGE. Copyright © 2021, The Authors. All rights reserved.

关键词： Graph neural networks

Neural entropic estimation: A faster path to mutual information estimation

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Chan, Chung Al-Bashabsheh, Ali Huang, Hing Pang Lim, Michael Tam, Da Sun Handason Zhao, Chao Department of Computer Science City University of Hong Kong Big Data and Brain Computing Beihang University

We point out a limitation of the mutual information neural estimation (MINE) where the network fails to learn at the initial training phase, leading to slow convergence in the number of training iterations. To solve this problem, we propose a faster method called the mutual information neural entropic estimation (MI-NEE). Our solution first generalizes MINE to estimate the entropy using a custom reference distribution. The entropy estimate can then be used to estimate the mutual information. We argue that the seemingly redundant intermediate step of entropy estimation allows one to improve the convergence by an appropriate reference distribution. In particular, we show that MI-NEE reduces to MINE in the special case when the reference distribution is the product of marginal distributions, but faster convergence is possible by choosing the uniform distribution as the reference distribution instead. Compared to the product of marginals, the uniform distribution introduces more samples in low-density regions and fewer samples in high-density regions, which appear to lead to an overall larger gradient for faster convergence. Copyright © 2019, The Authors. All rights reserved.

关键词： Entropy

Recurrent interaction network for jointly extracting entities and classifying relations

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Sun, Kai Zhang, Richong Mensah, Samuel Mao, Yongyi Liu, Xudong Sklsde School of Computer Science and Engineering Beihang University Beijing China Beijing Advanced Institution on Big Data and Brain Computing Beihang University Beijing China School of Electrical Engineering and Computer Science University of Ottawa Ottawa Canada

Named entity recognition (NER) and Relation extraction (RE) are two fundamental tasks in natural language processing applications. In practice, these two tasks are often to be solved simultaneously. Traditional multi-Task learning models implicitly capture the correlations between NER and RE. However, there exist intrinsic connections between the output of NER and RE. In this study, we argue that an explicit interaction between the NER model and the RE model will better guide the training of both models. Based on the traditional multi-Task learning framework, we design an interactive feature encoding method to capture the intrinsic connections between NER and RE tasks. In addition, we propose a recurrent interaction network to progressively capture the correlation between the two models. Empirical studies on two real-world datasets confirm the superiority of the proposed model. Copyright © 2020, The Authors. All rights reserved.

关键词： Natural language processing systems