检索结果-内蒙古大学图书馆

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

An Error-Entropy Minimization Algorithm for Tracking control of Nonlinear Stochastic Systems with Non-Gaussian Variables

引用

IFAC-PapersOnLine 2017年第1期50卷 10407-10412页

作者： Liu Y. Wang A. Guo L. Wang H. State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang 110819 China Institute of Computer Sciences Anhui University Anhui China Science and Technology on Aircraft Control Laboratory Beihang University Beijing 100191 China Pacific Northwest National Laboratory 902 Battelle Blvd RichlandWA 99352 United States

This paper presents an error-entropy minimization tracking control algorithm for a class of dynamic stochastic systems. The system is represented by a set of time-varying discrete nonlinear equations with non-Gaussian stochastic input, where the statistical properties of stochastic input are unknown. By using Parzen windowing with Gaussian kernel to estimate the probability densities of errors, recursive algorithms are then proposed to design the controller such that the tracking error can be minimized. The performance of the error-entropy minimization is compared with the mean-square-error minimization in the simulation results. © 2017

关键词： information potential Minimum error entropy non-Gaussian variables probability density function stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Hierarchical P systems with randomized right-hand sides of rules 18th

Hierarchical P systems with randomized right-hand sides of r...

引用

18th International Conference on Membrane Computing, CMC 1018

作者： Alhazov, Artiom Freund, Rudolf Ivanov, Sergiu Institute of Mathematics and Computer Science Academy of Sciences of Moldova Academiei 5 Chişinău2028 Moldova Key Laboratory of Image Information Processing and Intelligent Control of Education Ministry of China School of Automation Huazhong University of Science and Technology Wuhan430074 China Faculty of Informatics TU Wien Favoritenstraße 9–11 Vienna1040 Austria LACL Université Paris Est – Créteil Val de Marne 61 av. Général de Gaulle Créteil94010 France TIMC-IMAG/DyCTiM Faculty of Medicine of Grenoble 5 avenue du Grand Sablon La Tronche38700 France

ISBN: (纸本)9783319733586

P systems are a model of hierarchically compartmentalized multiset rewriting. We introduce a novel kind of P systems in which rules are dynamically constructed in each step by non-deterministic pairing of left-hand and right-hand sides. We define three variants of right-hand side randomization and compare each of them with the power of conventional P systems. It turns out that all three variants enable non-cooperative P systems to generate exponential (and thus non-semi-linear) number languages. We also give a binary normal form for one of the variants of P systems with randomized rule right-hand sides. © 2018, Springer International Publishing AG.

关键词： Hierarchical systems

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

Traffic flow optimization with QoS constrained network admission control

引用

IFAC-PapersOnLine 2017年第1期50卷 5275-5280页

作者： Csikós A. Farhadi H. Kulcsár B. Charalambous T. Wymeersch H. Institute for Computer Science and Control Hungarian Academy of Sciences Budapest Hungary Department of Signals and Systems Chalmers University of Technology Gothenburg Sweden John A. Paulson School of Engineering and Applied Sciences Harvard University Cambridge MA United States Department of Electrical Engineering and Automation School of Electrical Engineering Aalto University Espoo Finland

The paper proposes a control design method in order to gate input flow to a protected urban vehicular network such that travel time Quality of Service (QoS) constraints are preserved within the network. In view of the network to be protected (also called the region), two types of queues are distinguished: external and internal. While external queues represent vehicles waiting to enter the protected network, an internal queue can be used to describe the network's aggregated behaviour. By controlling the number of vehicles entering the internal queue, the travel time within the network subject to the vehicular conservation law and the Network Fundamental Diagram (NFD) can be subsequently controlled. The admission controller can thus be interpreted as a mechanism which transforms the unknown arrival process governing the number of vehicles entering the network to a regulated process, such that prescribed QoS requirements on travel time in the network and upper bound on the external queue are satisfied. The admission control problem is formulated as a constrained convex optimization problem and a Model Predictive control (MPC) problem. A case study demonstrates the benefits of the admission control mechanisms proposed. © 2017

关键词： admission network fundamental diagram perimeter control Quality of Service Traffic control traffic flow travel time

来源：评论

学校读者我要写书评

暂无评论

Gaussian pedestrian proxemics model with social force for service robot navigation in dynamic environment 17th

引用

17th International Conference on Asia Simulation, AsiaSim 2017

作者： Chik, Sheng Fei Yeong, Che Fai Su, Eileen Lee Ming Lim, Thol Yong Duan, Feng Tan, Jeffrey Too Chuan Tan, Ping Hua Chin, Patrick Jun Hua Faculty of Electrical Engineering Universiti Teknologi Malaysia Johor Bahru Malaysia Centre for Artificial Intelligence and Robotics Universiti Teknologi Malaysia Johor Bahru Malaysia Malaysia Japan Institute of Technolgy Universiti Teknologi Malaysia Johor Bahru Malaysia Department of Automation College of Computer and Control Engineering Nankai University Tianjin China Institute of Industrial Science The University of Tokyo Tokyo Japan DF Automation and Robotics Sdn. Bhd Skudai Malaysia

ISBN: (纸本)9789811064623

Pedestrian motion behaves stochastically, causing difficulties in modelling the appropriate proxemics for effective and efficient service robot navigation. Intruding the pedestrian social space can affect the social acceptance of a service robot. In this paper, a new proxemics model, Social-Force Gaussian Pedestrian Proxemics Model is presented to model the pedestrian social space and to improve the service robot navigation in dynamic human environment. This model was simulated and validated in a pedestrian simulator with both low and high pedestrian density environments. Results showed that the proposed model (i) improved proxemics representation of pedestrians, (ii) enhanced the robot performance in respecting the social norm and (iii) increased the efficiency in achieving a given task. This paper also presents the methods for parameter selections for the model without the requirement of complex tuning. © Springer Nature Singapore Pte Ltd. 2017.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

An SNR-Adaptive Relaying Algorithm for Multi-Antenna Cooperative Networks

引用

China Communications 2017年第10期14卷 228-236页

作者： Shuangshuang Han Peng Zhang Feijin Shi Fei-Yue Wang The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of SciencesBeijing China Qingdao Academy of Intelligent Industries Qingdao Shandong Province China The School of Computer Engineering Weifang University Shandong P. R. China Communications Headquarters Ministry of Foreign Affairs of the People's Republic of China Beijing China Research Center of Computational Experiments and Parallel Systems The National University of Defense Technology Changsha China

Multiple-input multiple-output(MIMO) and cooperative communications have been attracted great attention for the improvements of communication capacity, power consumption, and transmission coverage. The conventional fixed relaying protocols, amplify-and-forward(AF) and decode-and-forward(DF), have their own advantages and disadvantages, i.e. AF performs better than DF for low signal-to-noise ratio(SNR) region, while the reverse is true for high SNR region. Therefore, this paper proposes an SNR-adaptive forward(SAF) relaying scheme obtaining the advantages of both AF and DF. Furthermore, the proposed SAF does not need to switch between AF and DF when SNR changes. The main idea is to adaptively derive the soft information at the cooperative relay nodes based on the information of the received signal and the SNR. Besides, based on the theoretical analysis and the simulation results, it is affirmed that the proposed SAF achieves superior performance than both AF and DF for all SNRs. Moreover, the performance gain would be improved with the increasing number of parallel cooperative relay nodes.

关键词： MIMO SNR SNR-adaptive forward multi-antenna

来源：评论

学校读者我要写书评

暂无评论

Iterative Learning control Applied to a Deformable Mirror

Iterative Learning Control Applied to a Deformable Mirror

引用

第36届中国控制会议

作者： Blazej Cichy Petr Augusta Krzysztof Galkowski Eric Rogers Institute of Control and Computation Engineering University of Zielona Góra Institute of Information Theory and Automation The Czech Academy of Sciences Department of Electronics and Computer Science University of Southampton

An unconditionally stable finite difference discretization motivated by the well-known Crank-Nicolson method is used to develop an iterative learning control design for systems whose dynamics are described by a fourth-order partial differential equation.A discrete in time and space model of a deformable rectangular mirror is derived in this setting and forms the basi s for the new design,where a model for the actuator dynamics is also included.A numerical case study is given to demonstrate the properties of the new design.

关键词： Crank-Nicolson Discretization Method Iterative Learning control Thin Plates

来源：评论

学校读者我要写书评

暂无评论

Multi-view hybrid embedding: A divide-and-conquer approach

arXiv

引用

arXiv 2018年

作者： Xu, Jiamiao Yu, Shujian You, Xinge Leng, Mengjun Jing, Xiao-Yuan Chen, C. L. Philip School of Electronic Information and Communications Huazhong University of Science and Technology Wuhan430074 China Department of Electrical and Computer Engineering University of Florida GainesvilleFL32611 United States Department of Computer Science University of Houston HoustonTX77204 United States State Key Laboratory of Software Engineering School of Computer Wuhan University China Department of Computer and Information Science Faculty of Science and Technology University of Macau Macau99999 China Dalian Maritime University Dalian116026 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100080 China

We present a novel cross-view classification algorithm where the gallery and probe data come from different views. A popular approach to tackle this problem is the multiview subspace learning (MvSL) that aims to learn a latent subspace shared by multi-view data. Despite promising results obtained on some applications, the performance of existing methods deteriorates dramatically when the multi-view data is sampled from nonlinear manifolds or suffers from heavy outliers. To circumvent this drawback, motivated by the Divideand-Conquer strategy, we propose Multi-view Hybrid Embedding (MvHE), a unique method of dividing the problem of cross-view classification into three subproblems and building one model for each subproblem. Specifically, the first model is designed to remove view discrepancy, whereas the second and third models attempt to discover the intrinsic nonlinear structure and to increase discriminability in intra-view and interview samples respectively. The kernel extension is conducted to further boost the representation power of MvHE. Extensive experiments are conducted on four benchmark datasets. Our methods demonstrate overwhelming advantages against the stateof-the-art MvSL based cross-view classification approaches in terms of classification accuracy and robustness. Copyright © 2018, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Acoustic Model Compression with Knowledge Transfer

Acoustic Model Compression with Knowledge Transfer

引用

第十四届全国人机语音通讯学术会议

作者： Jiangyan Yi Jianhua Tao Zhengqi Wen Ya Li Hao Ni National Laboratory of Pattern Recognition Institute of AutomationChinese Academy of Sciences School of Computer and Control Engineering University of Chinese Academy of Sciences CAS Center for Excellence in Brain Science and Intelligence Technology Institute of AutomationChinese Academy of Sciences

Mobile devices have limited computing power and limited ***,large deep neural network(DNN) based acoustic models are not well suited for application on mobile *** order to alleviate this problem,this paper proposes to compress acoustic models by using knowledge *** approach forces a large teacher model to transfer generalized knowledge to a small student *** student model is trained with a linear interpolation of hard probabilities and soft probabilities to learn generalized knowledge from the teacher *** hard probabilities are generated from a Gaussian mixture model hidden Markov model(GMM-HMM) *** soft probabilities are computed from a teacher model(DNN or RNN).Experiments on AMI corpus show that a small student model obtains 2.4%relative WER improvement over a large teacher model with almost 7.6 times compression ratio.

关键词： model compression knowledge transfer deep neural networks automatic speech recognition

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：