检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Wang, Xin Ishii, Hideaki Du, Linkang Cheng, Peng Chen, Jiming State Key Lab. of Industrial Control Technology Zhejiang University Hangzhou310027 China Dept. of Computer Science Tokyo Institute of Technology Yokohama226-8502 Japan

With the proliferation of training data, distributed machine learning (DML) is becoming more competent for large-scale learning tasks. However, privacy concerns have to be given priority in DML, since training data may contain sensitive information of users. In this paper, we propose a privacy-preserving ADMM-based DML framework with two novel features: First, we remove the assumption commonly made in the literature that the users trust the server collecting their data. Second, the framework provides heterogeneous privacy for users depending on data's sensitive levels and servers' trust degrees. The challenging issue is to keep the accumulation of privacy losses over ADMM iterations minimal. In the proposed framework, a local randomization approach, which is differentially private, is adopted to provide users with self-controlled privacy guarantee for the most sensitive information. Further, the ADMM algorithm is perturbed through a combined noise-adding method, which simultaneously preserves privacy for users' less sensitive information and strengthens the privacy protection of the most sensitive information. We provide detailed analyses on the performance of the trained model according to its generalization error. Finally, we conduct extensive experiments using real-world datasets to validate the theoretical results and evaluate the classification performance of the proposed framework. Copyright © 2019, The Authors. All rights reserved.

关键词： Random processes

来源：评论

学校读者我要写书评

暂无评论

Parameters adaption of Lebesgue sampling-based diagnosis and prognosis for Li-ion batteries

Parameters adaption of Lebesgue sampling-based diagnosis and...

引用

2015 Annual Conference of the Prognostics and Health Management Society, PHM 2015

作者： Yan, Wuzhao Dou, Wanchun Liu, Datong Peng, Yu Zhang, Bin Department of Electrical Engineering University of South Carolina ColumbiaSC29208 United States Department of Computer Science and Technology State Key Lab. for Novel Software Technology Nanjing University NanjingJiangsu210093 China Department of Automatic Test and Control Harbin Institute of Technology HarbinHeilongjiang150080 China

ISBN: (纸本)9781936263202

Traditional fault diagnosis and prognosis (FDP) approaches are based on Riemann sampling (RS), in which samples are taken and algorithms are executed in a periodic time interval. With the increase of system complexity, the real-time implementation of this Riemann sampling-based FDP (RS-FDP) becomes a bottleneck, especially for distributed applications. To overcome this problem, a Lebesgue sampling-based FDP (LS-FDP) is proposed. LS-FDP takes samples on the fault dimension axis and provides a need-based diagnostic philosophy in which the algorithm is executed only when necessary. In previous Lebesgue sampling-based FDP, the Lebesgue length is a constant. To accommodate the change of fault dynamics, it is desirable to execute FDP algorithm more frequently when the fault growth is fast while less frequently when fault growth is slow. This requires to change the Lebesgue length adaptively. The goal of this paper is to deliver an improved LS-FDP method with varying Lebesgue length, which enables the FDP to be executed according to needs. The design and implementation of varying Lebesgue length LS-FDP based on a particle filtering algorithm are illustrated with experimental results on Li-ion batteries to verify the performances of the proposed approach. The experimental results show that the new varying LS-FDP is accurate and time-efficient on long term prognosis and also keeps a closer monitoring on the fast increase of fault size. © 2015, Prognostics and Health Management Society. All rights reserved.

关键词： Real time control

来源：评论

学校读者我要写书评

暂无评论

Path Planning of Humanoid Arm Based on Deep Deterministic Policy Gradient

Path Planning of Humanoid Arm Based on Deep Deterministic Po...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Shuhuan Wen Jianhua Chen Shen Wang Hong Zhang Xueheng Hu department of Key Lab of Industrial Computer Control Engineering of Hebei Province Yanshan University Qinhuangdao China Department of Computing Science University of Alberta Edmonton Canada

ISBN: (纸本)9781728103785;9781728103778

The robot arm with multiple degrees of freedom and working in a 3D space needs to avoid obstacles during the grasping process by its end effector. Path planning to avoid obstacles is very important for accomplishing a grasping task. This paper proposes a new obstacle avoidance algorithm, based on an existing deep reinforcement learning framework called deep deterministic policy gradient (DDPG). Specifically, we propose to use DDPG to plan the trajectory of a robot arm to realize obstacle avoidance. The rewards are designed to overcome the difficulty in convergence of multiple rewards, especially when the rewards are antagonistic with respect to each other. Obstacle avoidance of the robot arm using DDPG is achieved by self-learning, and the convergence problem caused by the high dimension state input and multiple return values is solved. The simulation model of an arm of the Nao robot is built based on the MuJoCo simulation environment. The simulation demonstrates that the proposed algorithm successfully allows the robot arm to avoid obstacles.

关键词： Manipulators Neural networks Robot kinematics Planning Reinforcement learning Trajectory

来源：评论

学校读者我要写书评

暂无评论

Wireless MIMO switching with MMSE relaying 2012

Wireless MIMO switching with MMSE relaying

引用

2012 IEEE International Symposium on Information Theory, ISIT 2012

作者： Wang, Fanggang Liew, Soung Chang Guo, Dongning Institute of Network Coding Chinese Univ. of Hong Kong Hong Kong Hong Kong State Key Lab. of Rail Traffic Control and Safety EIE Beijing Jiaotong Univ. Beijing China Department of Electrical Engineering and Computer Science Northwestern Univ. Evanston IL United States

ISBN: (纸本)9781467325790

A wireless relay which forms a one-to-one mapping from the inputs (uplinks) to the outputs (downlinks) is called a multiple-input-multiple-output (MIMO) switch. The MIMO switch carries out precode-and-forward, where all users send their signals in the uplink and then the MIMO switch precodes the received vector signal for broadcasting in the downlink. Ideally, each user employs a receive filter to recover its desired signal from one other user with no or little interference from other users. We propose a joint design of the precoder and the receive filters to achieve the minimum-mean-square-error (MMSE), assuming full channel state information is availab.e at the relay. Our results indicate that the proposed MMSE relaying scheme outperforms the existing ZF/MMSE schemes. © 2012 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Robust Beamforming Based on Covariance Matrix Reconstruction and ADMM

Robust Beamforming Based on Covariance Matrix Reconstruction...

引用

2021 CIE International Conference on Radar, Radar 2021

作者： Gong, Pengcheng Wang, Zhaobin Xu, Kaiyan School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu611731 China School of Computer Science and Engineering Wuhan Institute of Technology Wuhan430205 China Hubei University of Technology Hubei Key Lab. for High-efficiency Utiliz. of Solar Ener. and Oper. Control of Energy Storage System Wuhan430068 China

ISBN: (纸本)9781665498142

Considering at the issue that the performance of the traditional beamforming algorithm will decrease sharply when the disturbance occurs at the disturbed position and the steering vector mismatch occurs, a new robust beamforming method based on covariance matrix reconstruction and Alternating Direction Method of Multipliers (ADMM) is proposed. Firstly, based on the maximum output power criterion of beamformers, an optimization model is designed to solve the optimal steering vector. Then, the covariance matrix is reconstructed by using the defined interference range to widen the nullity and enhance the anti-motion interference ability of the system. Then, for the quadratic inequality constraint problem of the steering vector, this paper uses ADMM to solve the model iteratively, and obtains the specific solution of the steering vector in each iteration. In addition, the complexity of the algorithm is also analyzed. The experimental results show that, compared with the existing beamforming algorithms, the proposed method Widen the width of zero notch in the interference area, improves the anti-interference performance of the beam, and can well correct the mismatched steering vector. © 2021 IEEE.

关键词： Alternating Direction Method of Multipliers Beamforming Covariance matrix reconstruction Null widening Quadratic constraint

来源：评论

学校读者我要写书评

暂无评论

Improved Lightweight YOLOv5 Based on GhostNet and Its Application in Target Board Detection for Ladle Nozzle Positioning

Improved Lightweight YOLOv5 Based on GhostNet and Its Applic...

引用

第43届中国控制会议

作者： Fengfei Si Yiming Fang Hao Ju Dongliang Zhao Jingliang Xin Key Lab of Industrial Computer Control Engineering of Hebei Province Yanshan University Engineering Research Center of the Education Ministry for Intelligent Control System and Intelligent Equipment Yanshan University Tangshan Branch HBIS Company Limited

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

The detection of the target board of ladle nozzle positioning is the basis of automatic loading and unloading of ladle nozzle by ladle robot in continuous casting. Due to the complex situation of high temperature, dust, backlight and so on, the target board of ladle nozzle positioning is prone to false detection or low detection accuracy, and it is difficult to take into account the contradiction between rapidity and detection accuracy. Therefore, this paper proposes an improved lightweight algorithm GVP-YOLOv5(YOLOv5 with GhostNet, VoVGSCSP and Pruning), which takes into account both detection accuracy and rapidity, to detect the target board for ladle nozzle positioning. Firstly, Ghost module is used to improve the backbone network of YOLOv5 as the backbone feature extraction network to reduce the number of parameters and calculation of the backbone. Then in the neck, the GSConv module is used to design a thin neck structure, which can ensure the multi-scale feature fusion capability and further reduce the complexity of the network. Finally, the model pruning technology is used to prune the whole model, and the channels with small scaling factor are removed to compress the model to the greatest extent, so as to meet the requirements of industrial field application deployment. The experimental results show that the lightweight GVP-YOLOv5 algorithm proposed in this paper can complete the real-time detection of the target board in complex industrial scenarios. Compared with the original YOLOv5s algorithm, the number of parameters in the model is reduced by 82.6%, and the size of the model is significantly reduced to 19.4%. At the same time, the detection accuracy is maintained at more than 95% on mAP@50:95 and the detection speed is effectively improved.

关键词： Target board detection Ladle nozzle positioning YOLOv5 lightweight GhostNet thin neck structure channel pruning

来源：评论

学校读者我要写书评

暂无评论

DexRepNet: Learning Dexterous Robotic Grasping Network with Geometric and Spatial Hand-Object Representations

DexRepNet: Learning Dexterous Robotic Grasping Network with ...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Qingtao Liu Yu Cui Qi Ye Zhengnan Sun Haoming Li Gaofeng Li Lin Shao Jiming Chen College of Control Science and Engineering Zhejiang University Hangzhou China Key Lab of CS&AUS Zhejiang Province College of Control Science and Engineering and the State Key Laboratory of Industrial Control Technology Zhejiang University Department of Computer Science National University of Singapore Singapore

Robotic dexterous grasping is a challenging problem due to the high degree of freedom (DoF) and complex contacts of multi-fingered robotic hands. Existing deep re-inforcement learning (DRL) based methods leverage human demonstrations to reduce sample complexity due to the high dimensional action space with dexterous grasping. However, less attention has been paid to hand-object interaction representations for high-level generalization. In this paper, we propose a novel geometric and spatial hand-object interaction representation, named DexRep, to capture object surface features and the spatial relations between hands and objects during grasping. DexRep comprises Occupancy Feature for rough shapes within sensing range by moving hands, Surface Feature for changing hand-object surface distances, and LocalGeo Feature for local geometric surface features most related to potential contacts. Based on the new representation, we propose a dexterous deep reinforcement learning method DexRepNet to learn a generalizable grasping policy. Experimental results show that our method outperforms baselines using existing representations for robotic grasping dramatically both in grasp success rate and convergence speed. It achieves a 93% grasping success rate on seen objects and higher than 80% grasping success rates on diverse objects of unseen categories in both simulation and real-world experiments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Feasibility of Using Discriminate Pricing Schemes for Energy Trading in Smart Grid

Feasibility of Using Discriminate Pricing Schemes for Energy...

引用

IEEE Global Communications Conference

作者： Wayes Tushar Chau Yuen Bo Chai David B. Smith H. Vincent Poor Singapore University of Technology and Design State Key Lab. of Industrial Control Technology Zhejiang University NICTA Canberra ACT School of Engineering and Applied Science Princeton University

ISBN: (纸本)9781479935130

This paper investigates the feasibility of using a discriminate pricing scheme to offset the inconvenience that is experienced by an energy user (EU) in trading its energy with an energy controller in smart grid. The main objective is to encourage EUs with small distributed energy resources (DERs), or with high sensitivity to their inconvenience, to take part in the energy trading via providing incentive to them with relatively higher payment at the same time as reducing the total cost to the energy controller. The proposed scheme is modeled through a two-stage Stackelberg game that describes the energy trading between a shared facility authority (SFA) and EUs in a smart community. A suitable cost function is proposed for the SFA to leverage the generation of discriminate pricing according to the inconvenience experienced by each EU. It is shown that the game has a unique sub-game perfect equilibrium (SPE), under the certain condition at which the SFA's total cost is minimized, and that each EU receives its best utility according to its associated inconvenience for the given price. A backward induction technique is used to derive a closed form expression for the price function at SPE, and thus the dependency of price on an EU's different decision parameters is explained for the studied system. Numerical examples are provided to show the beneficial properties of the proposed scheme.

关键词： Smart grid Discriminate pricing Distributed energy resources Game theory Energy management

来源：评论

学校读者我要写书评

暂无评论

Dynamic Multi-Objective Optimization Algorithm for Classification of Decision Variables Based on Objective Monotonicity

SSRN

引用

SSRN 2023年

作者： Wei, Lixin Yang, Qingshuai Guo, Zeyin Institute of Electrical Engineering Yanshan University Hebei Qinhuangdao066004 China Key Lab of Industrial Computer Control Engineering of Hebei Province Yanshan University Hebei Qinhuangdao066004 China

Dynamic multi-objective optimization problems (DMOPs) are prevalent in daily life, and the aim of dealing with DMOPs is to track the moving Pareto Front(PF) and find a series of Pareto Sets (PS) at different moments. Strategies based on decision variable classification improve the performance of multi-objective evolutionary algorithms. However, it has been a challenge to ensure fast and accurate classification. In this study, a decision variable classification method based on objective monotonicity(CDMO) is proposed to reduce the negative effects of inaccurate classification. In addition, a multi-step convergence prediction method and a diversity maintenance strategy are proposed to improve the algorithm performance. The effectiveness of the CDMO algorithm is verified by comparing it with three state-of-the-art DMOEAs on 16 benchmark test problems. The experimental results show that the CDMO algorithm is able to obtain high-quality populations with good convergence and distributivity in a dynamic environment. © 2023, The Authors. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Sliding Mode control for Robot Based on Passivity Theory

Fuzzy Sliding Mode Control for Robot Based on Passivity Theo...

引用

International Symposium on Computational Intelligence and Design, ISCID

作者： Xiuling Liu Zhanfang Feng Hongrui Wang Yudong Feng Department of Electronic and Informational Engineering Hebei University Baoding Hebei China Key Lab of Industrial Computer Control Engineering of Hebei Province Yanshan University슠 Qinhuangdao Hebei China

A novel control strategy based on passivity theory was proposed with special attention to trajectory tracking and robust control of rigid robot. In this paper, robot model was divided into nominal model and uncertainty part. Based on the backstepping approach, feedback passivity was used to design controller for the nominal model. A variable structure concentrated compensation controller was adopted to the uncertainty part. Using fuzzy rules, a fuzzy system based on nominal model controller and sliding mode variable structure controller was built to eliminate chattering effectively. Simulation results show that the scheme can achieve tracking effect with high speed, as well as enhance the robustness of the system under the condition of existing model error and external disturbance, and the global stability can be also guaranteed.

关键词： Fuzzy control Sliding mode control Robots Uncertainty Fuzzy systems Robust stability Trajectory Robust control Backstepping Feedback

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：