检索结果-内蒙古大学图书馆

第35届中国控制会议

作者： ZHANG Jianlei CHEN Zengqiang LIU Zhongxin ZHANG Chunyan Department of Automation College of Computer and Control EngineeringNankai University Tianjin Key Laboratory of Intelligent Robotics Computer and Control EngineeringNankai University

ISBN: (纸本)9781509009107

Cooperative behaviors lie at the basis of human societies,yet its evolutionary origin still remains a perplexing *** exists a large evolutionary game literature exploring effects of population structures on evolutionary outcomes,but in most cases structured population models only employ one game alone.A relevant question is covered in this study thus concerns the effect of game diversity occurring along the edges linking two players situated on the *** basic structure of our mechanism provides more than one type of games available for the *** our game setting,the game model is assumed as a fixed property of each edge and will remain unaltered through game *** preliminary initiatives,we only consider two typical games（Prisoner’s dilemma game and Snowdrift game）,and all possible mixtures between them controlled by a *** performed simulations and theoretical analysis help us observe the remarkable improvement on cooperation levels in suitable parameter regions when the population are simultaneously provided with more than one type of ***,network heterogeneity helps to bring into existence of cooperator clusters and thus favors the survival of cooperators.

关键词： Collective Cooperation Evolutionary Game Theory Heterogeneity

来源：评论

学校读者我要写书评

暂无评论

ConnNet: A long-range relation-aware pixel-connectivity network for salient segmentation

arXiv

引用

arXiv 2018年

作者： Kampffmeyer, Michael Dong, Nanqing Liang, Xiaodan Zhang, Yujia Xing, Eric P. Machine Learning Group UiT The Arctic University of Norway Tromsø9019 Norway Cornell University IthacaNY14850 United States Machine Learning Department Carnegie Mellon University PittsburghPA15213 United States Institute of Automation Chinese Academy of Sciences School of Computer and Control Engineering University of Chinese Academy of Sciences Beijing100190 China

Salient segmentation aims to segment out attention grabbing regions, a critical yet challenging task and the foundation of many high-level computer vision applications. It requires semantic-aware grouping of pixels into salient regions and benefits from the utilization of global multi-scale contexts to achieve good local reasoning. Previous works often address it as two-class segmentation problems utilizing complicated multi-step procedures including refinement networks and complex graphical models. We argue that semantic salient segmentation can instead be effectively resolved by reformulating it as a simple yet intuitive pixel-pair based connectivity prediction task. Following the intuition that salient objects can be naturally grouped via semanticaware connectivity between neighboring pixels, we propose a pure Connectivity Net (ConnNet). ConnNet predicts connectivity probabilities of each pixel with its neighboring pixels by leveraging multi-level cascade contexts embedded in the image and long-range pixel relations. We investigate our approach on two tasks, namely salient object segmentation and salient instancelevel segmentation, and illustrate that consistent improvements can be obtained by modeling these tasks as connectivity instead of binary segmentation tasks for a variety of network architectures. We achieve state-of-the-art performance, outperforming or being comparable to existing approaches while reducing inference time due to our less complex approach. Copyright © 2018, The Authors. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Breast Cancer Diagnosis Using an Unsupervised Feature Extraction Algorithm Based on Deep Learning

Breast Cancer Diagnosis Using an Unsupervised Feature Extrac...

引用

第37届中国控制会议

作者： Yawen Xiao Jun Wu Zongli Lin Xiaodong Zhao Department of Automation Shanghai Jiao Tong Universityand Key Laboratory of System Control and Information Processing of Ministry of Education The Center for Bioinformatics and Computational Biology Shanghai Key Laboratory of Regulatory Biologythe Institute of Biomedical Sciences and School of Life SciencesEast China Normal University Charles L.Brown Department of Electrical and Computer Engineering University of Virginia School of Biomedical Engineering Shanghai Jiao Tong University

Breast cancer is the most often detected cancer in women. At the same time, it is one of the most curable types of cancer if diagnosed early. With the development of the detection technology, a growing amount of clinical data and highdimensional features can be used for breast cancer diagnosis. The high-dimensional data contributes to advances in the diagnostic technology, but also incurs a large amount of computational redundancy. Thus, extracting important information and reducing the feature dimension is critical to effective prediction and an accurate treatment ***, the previous works for breast cancer diagnosis are mainly based on labeled data that is difficult to obtain. To address this issue, in this paper, we demonstrate a new scheme, which integrates a deep learning based unsupervised feature extraction algorithm, the stacked auto-encoders, with a support vector machine model（SAE-SVM）, for breast cancer diagnosis. The stacked auto-encoders with the greedy layerwise pre-training and an improved momentum update algorithm is applied to capture essential information and extract necessary features of the original data. Then, a support vector machine model is employed to classify the samples with new features into malignant or benign tumors. The proposed method was tested on the Wisconsin Diagnostic Breast Cancer data set. The performance is evaluated using various measures and compared with the previously published results. The comparison results show that the proposed SAE-SVM method improves the accuracy to 98.25% and outperforms the other methods. The deep learning based unsupervised feature extraction significantly improves the performance of classification and provides a promising approach to breast cancer diagnosis.

关键词： Deep learning auto-encoder feature extraction breast cancer diagnosis unlabeled data

来源：评论

学校读者我要写书评

暂无评论

Synchronized Cell-Balancing Charging of Supercapacitors

引用

IFAC-PapersOnLine 2017年第1期50卷 3338-3343页

作者： Li H. Peng J. He J. Huang Z. Pan J. School of Information Science and Engineering Central South University Changsha 410087 China Department of Computer Science University of Victoria Victoria V8P5C2 Canada Dept. of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Shanghai 200240 China

As a classical cell balancing solution in low-power supercapacitor applications, the switched resistor circuit is vulnerable to resistance deviation effects with existing cell balancing methods. In this paper, we propose a synchronized cell balancing method for switched resistor circuits based on the consensus theory and a cyber-physical approach, with the aim of synchronizing cell voltages before they are fully charged. It is shown that the proposed cell-balancing algorithm is robust to resistance deviation effects. Extensive simulations are provided to show the effectiveness of the proposed method. © 2017

关键词： Cell balancing Charging Consensus Cyber-physical systems Supercapacitors

来源：评论

学校读者我要写书评

暂无评论

Unknown input observer based on discrete-time nonlinear descriptor model for understanding sitting control

引用

IFAC-PapersOnLine 2017年第1期50卷 820-825页

作者： Blandeau M. Guerra T.M. Estrada-Manzo V. Pudlo P. Gabrielli F. Laboratory of Industrial and Human Automation control Mechanical engineering and Computer Science (LAMIH UMR CNRS 8201) Université de Valenciennes et du Hainaut-Cambrésis Valenciennes France Department of Electrical and Electronics Engineering Sonora Institute of Technology 5 de febrero 818 Sur CP Obregon Sonora 85000 Mexico

The present paper studies sitting control for persons with complete thoracic spinal cord injury by means of automatic control. The methodology begins by modeling sitting control, after a discretization of the nonlinear descriptor model is computed, then a Takagi-Sugeno model is obtained for further manipulations. The approach uses unknown input observers to estimate states and internal variable of the system. The design conditions are expressed as linear matrix inequalities, whose solvability depends on convex optimization techniques. Simulations are conducted to show the effectiveness of the proposed observer. © 2017

关键词： Discrete-Time systems Inverted pendulum Nonlinear descriptor systems Sitting movement Spinal Cord Injury Takagi-Sugeno models Unknown input observer

来源：评论

学校读者我要写书评

暂无评论

Reliable Code Generation and Test Environment demonstrated on a PI-controller Design

引用

IFAC-PapersOnLine 2016年第3期49卷 465-470页

作者： Schwarz, M.H. Sheng, H. Üstoglu, I. Chabaan, W. Börcsök, J. Safety Computer Technology University of Kassel Germany Control and Automation Engineering Department Yildiz Technical University Istanbul Turkey Computer Architecture and System Programming University of Kassel Germany

This paper focuses on the latest version of a tool developed within the department to guide developer through the various steps of requirements, test-procedures and documentations to finally download the derived algorithm on a safety programmable logic controller (PLC). Requirements on how to develop and how to test software are steadily increasing due to international standards, which have to be obeyed in industries in general, and in the process- and automation industries in particular. A simple model is derived to be used to develop a PI controller that has to pass several steps to be qualified for execution on a PLC. The paper explains the different steps and describes the various problems that might occur. © 2016

关键词： controllers Accident prevention Reliability Software testing Automated code generation automation industry International standards P i controller designs PI control Programmable Logic controller (PLC) Simple modeling Test Environment

来源：评论

学校读者我要写书评

暂无评论

Accuracy analysis for distributed weighted least-squares estimation in finite steps and loopy networks

arXiv

引用

arXiv 2018年

作者： Sui, Tianju Marelli, Damián Fu, Minyue Lu, Renquan Department of Control Science and Engineering Dalian University of Technology Liaoning China School of Automation Guandong University of Technology Guangzhou China French-Argentinean International Center for Information and Systems Sciences National Scientific and Technical Research Council Ocampo y Esmeralda Rosario2000 Argentina School of Electrical Engineering and Computer Science University of Newcastle University Drive CallaghanNSW2308 Australia

Distributed parameter estimation for large-scale systems is an active research problem. The goal is to derive a distributed algorithm in which each agent obtains a local estimate of its own subset of the global parameter vector, based on local measurements as well as information received from its neighbours. A recent algorithm has been proposed, which yields the optimal solution (i.e., the one that would be obtained using a centralized method) in finite time, provided the communication network forms an acyclic graph. If instead, the graph is cyclic, the only available alternative algorithm, which is based on iterative matrix inversion, achieving the optimal solution, does so asymptotically. However, it is also known that, in the cyclic case, the algorithm designed for acyclic graphs produces a solution which, although non optimal, is highly accurate. In this paper we do a theoretical study of the accuracy of this algorithm, in communication networks forming cyclic graphs. To this end, we provide bounds for the sub-optimality of the estimation error and the estimation error covariance, for a class of systems whose topological sparsity and signal-to-noise ratio satisfy certain condition. Our results show that, at each node, the accuracy improves exponentially with the so-called loop-free depth. Also, although the algorithm no longer converges in finite time in the case of cyclic graphs, simulation results show that the convergence is significantly faster than that of methods based on iterative matrix inversion. Our results suggest that, depending on the loop-free depth, the studied algorithm may be the preferred option even in applications with cyclic communication graphs. Copyright © 2018, The Authors. All rights reserved.

关键词： Optimal systems

来源：评论

学校读者我要写书评

暂无评论

Local open-loop manipulation of multi-agent networks

Local open-loop manipulation of multi-agent networks

引用

American control Conference

作者： Dinuka Sahabandu Rahul Dhal Jackeline Abad Torres Sandip Roy Department of Electrical Engineering and Computer Science Washington State University Market Research and Analysis EPIS Inc. Department of Automation and Industrial Control Escuela Politecnica Nacional

ISBN: (纸本)9781509045839

The energy required for manipulation of a double-integrator network model via local external actuation is examined. Some previous results on the controllability Gramian, which specifies the required energy, are briefly reviewed. Three new results are then developed. First, the energy required for manipulation along the synchronization manifold over an arbitrary horizon is characterized. Second, several scalar measures that give a global indication of a network's manipulability are analyzed. Based on these measures, we study design of the DIN to prevent or facilitate manipulation.

关键词： NETWORKING AGENT Energy sources maneuverability Network network model

来源：评论

学校读者我要写书评

暂无评论

Machine discovery of partial differential equations from spatiotemporal data

arXiv

引用

arXiv 2019年

作者： Yuan, Ye Li, Junlin Li, Liang Jiang, Frank Tang, Xiuchuan Zhang, Fumin Liu, Sheng Goncalves, Jorge Voss, Henning U. Li, Xiuting Kurths, Jürgen Ding, Han School of Artificial Intelligence and Automation State Key Laboratory of Digital Manufacturing Equipments and Technology Huazhong University of Science and Technology Wuhan430074 China School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan430074 China School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm11428 Sweden School of Mechanical Science and Engineering Huazhong University of Science and Technology Wuhan430074 China School of Electrical and Computer Engineering Georgia Institute of Technology Atlanta30332 United States School of Power and Mechanical Engineering Wuhan University Wuhan430074 China Department of Engineering University of Cambridge CambridgeCB2 1PZ United Kingdom Luxembourg Centre for Systems Biomedicine University of Luxembourg BelvauxL-4367 Luxembourg Citigroup Biomedical Imaging Center Weill Cornell Medical College New York10021 United States Research Domain IV - Transdisciplinary Concepts & Methods Potsdam Institute for Climate Impact Research Potsdam14473 Germany School of Mechanical Science and Engineering State Key Laboratory of Digital Manufacturing Equipments and Technology Huazhong University of Science and Technology Wuhan430074 China

The study presents a general framework for discovering underlying Partial Differential Equations (PDEs) using measured spatiotemporal data. The method, called Sparse Spatiotemporal System Discovery (S3d), decides which physical terms are necessary and which can be removed (because they are physically negligible in the sense that they do not affect the dynamics too much) from a pool of candidate functions. The method is built on the recent development of Sparse Bayesian Learning;which enforces the sparsity in the to-be-identified PDEs, and therefore can balance the model complexity and fitting error with theoretical guarantees. Without leveraging prior knowledge or assumptions in the discovery process, we use an automated approach to discover ten types of PDEs, including the famous Navier-Stokes and sine-Gordon equations, from simulation data alone. Moreover, we demonstrate our data-driven discovery process with the Complex Ginzburg-Landau Equation (CGLE) using data measured from a traveling-wave convection experiment. Our machine discovery approach presents solutions that has the potential to inspire, support and assist physicists for the establishment of physical laws from measured spatiotemporal data, especially in notorious fields that are often too complex to allow a straightforward establishment of physical law, such as biophysics, fluid dynamics, neuroscience or nonlinear optics. Copyright © 2019, The Authors. All rights reserved.

关键词： Nonlinear optics

来源：评论

学校读者我要写书评

暂无评论

Visual Navigation Method for Indoor Mobile Robot Based on Extended BoW Model

Visual Navigation Method for Indoor Mobile Robot Based on Ex...

引用

第十二届中国智能机器人大会

作者： Xianghui Li Xinde Li Mohammad Omar Khyam Chaomin Luo Yingzi Tan Key Laboratory of Measurement and Control of CSE (Ministry of Education) School of Automation Sout Department of Electrical and Computer Engineering Faculty of Engineering National University of Si Department of Electrical and Computer Engineering University of Detroit Mercy Michigan USA

This paper proposes a new navigation method for mobile robots based on an extended BoW (Bag of Words) model for general object recognition in indoor *** SIFT (Scale-invariant Feature Transform) detection algorithm with the GPU (Graphic Processing Unit) acceleration technology is used to describe feature vectors in this ***,in order to add some redundant image information,statistical information of the spatial relationships of all the feature points in an image,i.e.,relative distances and angles,is used to extend the feature vectors in the original BoW ***,the unsupervised SVM (Support Vector Machine) classifier is used to classify ***,in order to navigate conveniently in unknown and dynamic indoor environments,a type of human-robot interaction method based on a hand-drawn semantic map is *** experimental results show that this new navigation technology for indoor mobile robots is very robust and highly effective.

关键词： general object recognition Bag of Words model mobile robot visual navigation

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：