检索结果-内蒙古大学图书馆

2018 International Joint Conference on Neural Networks, IJCNN 2018

作者： Luo, Lincong Peng, Liang Wang, Chen Hou, Zengguang State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China

ISBN: (纸本)9781509060146

The rehabilitation training with active involvement and efforts of impaired subjects can enhance the outcome of rehabilitation therapies. To promote patients' voluntary engagement, a variety of assist as needed (AAN) controllers have been proposed for robot-aided therapy. However, patients' impairment level is not taken into account in the implementation of those control schemes. In this study, a novel AAN controller is developed for upper limb rehabilitation therapy. The control paradigm uses Gaussian radial basis function (RBF) network to learn the model of subjects' motor capability in workspace. The update of weight vectors of RBF network is based on a greedy strategy, which has the potential to promote subjects' voluntary engagement by providing task challenge for them. Considering the difference in the impairment degree of patients, the assistance and impedance level of robot control is regulated based on the task performance of patients. The results of experiments at four healthy subjects verify the feasibility and adaptability of the proposed AAN controller. © 2018 IEEE.

关键词： controllers

来源：评论

学校读者我要写书评

暂无评论

Behavioral management for Employees based on Blockchain and Smart Contracts

Behavioral Management for Employees based on Blockchain and ...

引用

2019 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2019

作者： Ni, Xiaochun Yuan, Yong Wang, Fei-Yue State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Qingdao Academy of Intelligent Industries Qingdao China Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing China Research Center of Military Computational Experiments and Parallel Systems National University of Defense Technology Changsha China

ISBN: (纸本)9781728128535

With the continuing innovation of information and network technologies, on the one hand, social media has gradually become a necessary tool for internal communication within the organization, resulting in great changes in the behavioral patterns of employees;on the other hand, emerging technologies such as blockchain and smart contracts have enlightened many outstanding issues in organizational management, such as opaque data, tamable information and incomplete execution. Responding to the impact of new media on organizational management model, combined with the emerging technologies - blockchain and smart contracts, this paper aims to explore the behavioral management model of employees for trusted data within virtual cyberspace. It is devoted to the description modeling of employees' behavior and the guidance of employees' behavior based on smart contracts. We also validate our proposed method in a real-world scenario, and the experimental results prove our analysis, as well as the effectiveness of our approach. This paper is a basic research in the new application field, and is expected to offer helpful guidance and reference for future research efforts and industrial applications. © 2019 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Review on Teacher's Online Practice in Community

Review on Teacher's Online Practice in Community

引用

2019 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2019

作者： Wang, Xinzhu Gong, Xiaoyan Liu, Xiwei Yan, Yan Zhang, Nan Luo, Jie State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Faculty of Education Beijing Normal University Beijing China Institute of Smart Education Qingdao Academy of Intelligent Industries Qingdao China Chinese Association of Automation Beijing China State Key Laboratory of Software Development Environment Beihang University Beijing100191 China

ISBN: (纸本)9781728128535

Teacher's Online Practice in Community (TOPIC) is an informal and practical online learning community that improves teachers' professional development. Domestic researches on TOPIC have begun to take shape. By sorting out relevant literature retrieved from China National Knowledge Infrastructure (CNKI), this article summarizes research topics such as knowledge management, teacher professional development, and community management and summarizes qualitative and quantitative research methods commonly used by domestic researches. This article finally puts forward some limitations of current researches in this field and forecasts the possible future research directions. © 2019 IEEE.

关键词： Knowledge management

来源：评论

学校读者我要写书评

暂无评论

Review on Development of Smart Education

Review on Development of Smart Education

引用

2019 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2019

作者： Shi, Wanruo Liu, Xiwei Gong, Xiaoyan Niu, Xiaojie Wang, Xinzhu Jing, Sifeng Lu, Hao Zhang, Nan Luo, Jie State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Faculty of Education Beijing Normal University Beijing China Institute of Smart Education Qingdao Academy of Intelligent Industries Qingdao China Chinese Association of Automation Beijing China State Key Laboratory of Software Development Environment Beihang University Beijing100191 China

ISBN: (纸本)9781728128535

Smart education is leading the development direction of Chinese education informatization and becoming a main theme of education development in the era of which technology changes education. There are seven main branches of smart education, namely Intelligent Tutoring System (ITS), smart campus, Big Data in Education (BDE), knowledge graph, educational robots, virtual teachers, and personalized education. Based on literature survey and market research, this paper gives a comprehensive overview of the research and application of smart education from above seven aspects and proposes its development based on the status of smart education development. © 2019 IEEE.

关键词： Intelligent vehicle highway systems

来源：评论

学校读者我要写书评

暂无评论

Exploring Optimal Revenue Models for DSPs in Real Time Bidding Advertising

Exploring Optimal Revenue Models for DSPs in Real Time Biddi...

引用

2019 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2019

作者： Qin, Rui Yuan, Yong Wang, Fei-Yue State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Qingdao Academy of Intelligent Industries Qingdao China Research Center of Military Computational Experiments and Parallel Systems National University of Defense Technology Changsha China Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781728128535

In RTB advertising, the AdExchange platform (AdX) can be regarded as a bridge connecting the supply side and demand side of advertising, and advertisers buy the ad impressions through the Demand-Side Platforms (DSPs). As such, there is a two-stage auction process for each ad impression, and the first stage is organized by the DSPs, while the second stage is organized by the AdX. In the two-stage auction process, two possible revenue models are available for DSPs, namely commission model and two-stage resale model. In this paper, we first compare the revenues of DSPs under the two models, and then explore the optimal revenue model for a DSP under the condition that the revenue model of other DSPs are given. We also unitize the computational experiments approach to evaluate our proposed method, and our results can help DSPs find their optimal revenue model in RTB advertising. © 2019 IEEE.

关键词： Marketing

来源：评论

学校读者我要写书评

暂无评论

Pillar in pillar: Multi-scale and dynamic feature extraction for 3D object detection in point clouds

arXiv

引用

arXiv 2019年

作者： Tian, Yonglin Huang, Lichao Li, Xuesong Li, Yuan Wang, Zilei Wang, Fei-Yue University of Science and Technology China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Horizon Robotics

Sparsity and varied density are two of the main obstacles for 3D detection networks with point clouds. In this paper, we present a multi-scale voxelization method and a decomposable dynamic convolution to solve them. We consider the misalignment problem between voxel representation with different scales and present a center-aligned voxelization strategy. Instead of separating points into individual groups, we use an overlapped partition mechanism to avoid the perception deficiency of edge points in each voxel. Based on this multi-scale voxelization, we are able to build an effective fusion network by one-iteration top-down forward. To handle the variation of density in point cloud data, we propose a decomposable dynamic convolutional layer that considers the shared and dynamic components when applying convolutional filters at different positions of feature maps. By modeling bases in the kernel space, the number of parameters for generating dynamic filters is greatly reduced. With a self-learning network, we can apply dynamic convolutions to input features and deal with the variation in the feature space. We conduct experiments with our PiPNet on KITTI dataset and achieve better results than other voxelization-based methods on 3D detection task. Copyright © 2019, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Research on Track and Positioning Estimation of Autonomous Vehicles Based on Multi-sensor Fusion

Research on Track and Positioning Estimation of Autonomous V...

引用

第六届国际仿生工程学术大会暨2019年自然启迪科技国际研讨会

作者： Haibin Huang Yun Pei Wuling Huang Yaxia Liu Beijing Institute of Fashion Technology Jilin University The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences

Path estimation of unmanned vehicles is relative positioning. Relative positioning mainly depends on internal somatosensory sensors such as odometers and gyroscopes. The current position of the unmanned vehicle is determined by the displacement of the unmanned vehicle relative to the initial position. Target tracking based on driverless vehicles. This paper proposes an iterative iteration of integration, that is, a linear distance of movement in a very short time instead of a section of the trajectory of the vehicle. At the same time, to solve the problem that a single sensor has its own limited amount of information. Multi-sensor information data combining odometer(ie track derivation) data with the number of attitudes of the vehicle through extended Kalman filter fusion, estimating optimal vehicle trajectory to achieve positioning. The algorithm is validated by a miniature version of a driverless vehicle experiment platform equipped with a ROS(Robot Operating System) robot operating system.

关键词： Unmanned Cycling kinematics model Multi-sensor information EKF ROS

来源：评论

学校读者我要写书评

暂无评论

Robust Graph Neural Networks Against Adversarial Attacks via Jointly Adversarial Training

引用

IFAC-PapersOnLine 2020年第5期53卷 420-425页

作者： Hu Tian Bowei Ye Xiaolong Zheng Desheng Dash Wu The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Department of Statistics University of Illinois in Urbana-Champaign Illinois USA School of Economics and Management University of Chinese Academy of Sciences Beijing 100190 China Stockholm Business School Stockholm University SE-106 91 Stockholm Sweden

Graph neural networks (GNNs) are powerful tools for analyzing graph-structured data. However, recent studies have shown that GNNs are vulnerable to small but intentional perturbations of input features and graph structures in the node classification task. Existing researches focus on enhancing the robustness of GNNs for a single type of perturbation such as graph structure perturbation or node feature perturbation. An ideal graph neural networks model should be able to resist the two kinds of perturbations. For this purpose, we propose a new adversarial training method for graph-structured data named Graph Jointly Adversarial Training (GJAT) which incorporates Graph Structure Adversarial Training (GSAT) and Graph Feature Adversarial Training (GFAT) two components and can resist perturbations from the topological structure and node attribute. Extensive experimental results demonstrate that our proposed method combining two kinds of adversarial training strategies can effectively improve the robustness of graph convolutional networks (GCNs) which is an important subset of GNNs.

关键词： Graph neural networks Robustness Adversarial Attack Adversarial Training Deep Learning

来源：评论

学校读者我要写书评

暂无评论

Social Manufacturing for High-end Apparel Customization

引用

IEEE/CAA Journal of Automatica Sinica 2018年第2期5卷 489-500页

作者： Xiuqin Shang Fei-Yue Wang Gang Xiong Timo R. Nyberg Yong Yuan Sheng Liu Chao Guo Sen Bao State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China School of Science at Aalto University Aalto FI-00076 Finland Qingdao Academy of Intelligent Industries Qingdao 266109 China IEEE

Social manufacturing(SM), a novel distributed,collaborative and intelligent manufacturing mode, is proposed and developed for high-end apparel customization. The main components of SM cloud are designed, and its research topics are summarized. Then, SM's key technologies are studied. 3D technologies for apparel customization, like 3D modeling, 3D fitting mirror and 3D customization, are developed to improve the customization precision and user experience. Information based collaborative management is realized to share, communicate,and handle the information efficiently among all groups and individuals of SM cloud. Suppliers' evaluation mechanism is designed to support the optimal decisions making. Next, SM cloud is constructed in five layers for high-end apparel *** using SM cloud based crowd-sourcing, social resources can be allocated rationally and utilized efficiently, consumer can customize the product in any processes like innovation, design,making, marketing and service, and traditional apparel enterprise can be upgraded into SM mode for keeping it competitive in the future customization markets.

关键词： Index Terms-Big data collaborative management social man-ufacturing cloud 3D apparel customization.

来源：评论

学校读者我要写书评

暂无评论

Grasp State Assessment of Deformable Objects Using Visual-Tactile Fusion Perception

arXiv

引用

arXiv 2020年

作者： Cui, Shaowei Wang, Rui Wei, Junhang Li, Fanrong Wang, Shuo State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Further Technology Universty of Chinese Academy of Sciences Beijing100190 China Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Shanghai200031 China

Humans can quickly determine the force required to grasp a deformable object to prevent its sliding or excessive deformation through vision and touch, which is still a challenging task for robots. To address this issue, we propose a novel 3D convolution-based visual-tactile fusion deep neural network (C3D-VTFN) to evaluate the grasp state of various deformable objects in this paper. Specifically, we divide the grasp states of deformable objects into three categories of sliding, appropriate and excessive. Also, a dataset for training and testing the proposed network is built by extensive grasping and lifting experiments with different widths and forces on 16 various deformable objects with a robotic arm equipped with a wrist camera and a tactile sensor. As a result, a classification accuracy as high as 99.97% is achieved. Furthermore, some delicate grasp experiments based on the proposed network are implemented in this paper. The experimental results demonstrate that the C3D-VTFN is accurate and efficient enough for grasp state assessment, which can be widely applied to automatic force control, adaptive grasping, and other visual-tactile spatiotemporal sequence learning problems. Copyright © 2020, The Authors. All rights reserved.

关键词： Deformation

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：