检索结果-内蒙古大学图书馆

∊-k anonymization and adversarial training of graph neural networks for privacy preservation in social networks

Electronic Commerce Research and Applications 2021年 50卷 101105-101105页

作者： Tian, Hu Zheng, Xiaolong Zhang, Xingwei Zeng, Daniel Dajun The State of Key Laboratory of Management and Control for Complex System Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

With the explosive growth of social networks, privacy preservation as a social good has been one common concern. Graph neural networks (GNNs) have been utilized by social network service providers to improve business service. However, traditional anonymization techniques of social networks cannot satisfy the desired privacy preservation of node attribute and graph structure and introduce information disturbance from the anonymization, leading to the performance degradation of GNNs in social network analysis. To protect sensitive user data and persist GNNs’ performance in social network analysis, we propose a two-stage privacy-preserving method of graph neural networks in the social network domain. During the first stage, we design a novel ∊-k anonymization method that can achieve ∊-local differential privacy (∊-LDP) and k-degree anonymity by incorporating the classical LDP and k-degree anonymization (k-DA) while retaining as much network community information as possible. At the second stage, we develop an adversarial training mechanism for GNNs to resist the disturbance from ∊-k anonymization and retain as much task performance as possible on anonymous social network data. Comprehensive experiments on several real-world social network datasets demonstrate the effectiveness of the proposed method for privacy-preserving node classification, link prediction, and graph clustering in social networks. The proposed method represents an interesting and important combination of classical anonymous technologies and recent GNNs and can preserve user privacy while providing business service. © 2021 Elsevier B.V.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

system development for micro-electrode assembly of cochlear implant

System development for micro-electrode assembly of cochlear ...

引用

IEEE International Conference on Real-time Computing and Robotics (RCAR)

作者： Shaokui Weng Weibin Rong Zeyang Xia Hao Deng Yangzhou Gan Jing Xiong Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China Key Laboratory of Human-Machine Intelligence-Synergy Systems Chinese Academy of Sciences Shenzhen China State Key Laboratory of Robotics and System Harbin Institute of Technology

ISBN: (纸本)9781467389600

Cochlear Implant is an implantable medical device for severe deafness patients to restore hearing function. The micro-electrode in cochlear implant is directly contacted with the human cochlea for signals transmission, thus its assembly is an important step of cochlear implant production. However, currently micro-electrode is assembled manually and the assembly precision and efficiency are unable to meet the industrial standard. In this paper, an automatic assembly system of micro-electrode for Cochlear Implant was designed. In this system, several mechanical mechanism specially for the micron level parts transmission and assembly were designed, including a wire feeder, a ring transmission mechanism, and a welding mechanism. And combined with the human-computer interaction interface, the effectiveness of the overall performance of the assembly system was verified by experiments.

关键词： Wires Welding Cochlear implants Assembly systems Tungsten Needles Electrodes

来源：评论

学校读者我要写书评

暂无评论

Dissolved oxygen control system based on the T-S fuzzy neural network

Dissolved oxygen control system based on the T-S fuzzy neura...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Wen-Tao Fu Jun-Fei Qiao Gai-Tang Han Meng College of Electronic Information and Control Engineering Beijing University of Technology Beijing CN College of Electronic Information and Control Engineering Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing China

In this paper, a novel kind of the dissolved oxygen (DO) concentration control system was proposed based on the T-S fuzzy neural network. The proposed T-S fuzzy neural network controller was used to control the DO concentration in the Benchmark Simulation Model No.1 (BSM1) wastewater treatment platform. The parameters of the neural network were adjusted online through the error back propagation algorithm to get the minimum error. By adjusting the learning rate online, the convergence speed of the system was accelerated, and then the DO concentration in the wastewater treatment system was controlled fast and efficiently in real-time. Compared with BP and PID controllers through the digital simulation, the results showed that the control effect of the DO concentration based on T-S fuzzy neural network control system was better. Besides, the test results under three kinds of weather condition showed that better adaptability and robustness were also gained in this control system.

关键词： Fuzzy control Benchmark testing Artificial neural networks Recycling Neurons

来源：评论

学校读者我要写书评

暂无评论

Trajectory Tracking Multi-mode Predictive control Based on Softswitching for Unmanned Surface Vehicle

Trajectory Tracking Multi-mode Predictive Control Based on S...

引用

第43届中国控制会议

作者： Kunpeng Duan Shanling Dong Meiqin Liu Senlin Zhang College of Electrical Engineering Zhejiang University National Key Laboratory of Industrial Control Technology Zhejiang University National Key Laboratory of Human-Machine Hybrid Augmented Intelligence Xi'an Jiaotong University Jinhua Institute of Zhejiang University

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

The unmanned surface vehicle(USV) plays a vital role in ocean exploration and utilization. Its primary tasks include navigating designated routes and safely avoiding obstacles in complex environments, ensuring efficient and secure arrival at destinations. This paper proposes a soft-switching-based multi-mode predictive control method. Specifically, A two-stage control model is defined to categorize the control modes, and a nonlinear model predictive controller(NMPC) embedding relevant obstacle avoidance constraints is developed. Then combined with NMPC framework, a sigmoid function is introduced to handle the multi-mode control problem. In addition, we apply the proposed algorithm successfully to the trajectory tracking control of USV. Simulation results show the strength and reliability of the proposed algorithm, which reduces the errors and improves the control accuracy effectively.

关键词： Unmanned surface vehicle model predictive control multi-mode control trajectory tracking

来源：评论

学校读者我要写书评

暂无评论

Short-Term and Mid-Term Population Projections Especially of Germany via WASD Neural Network: Theoretical Parts

Short-Term and Mid-Term Population Projections Especially of...

引用

第40届中国控制会议

作者： Zhiwen Yuan Siyuan Feng Chengxu Ye Yunong Zhang School of Computer Science and Engineering Sun Yat-sen University Guangdong Key Laboratory of Modern Control Technology Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education School of Computer Science Qinghai Normal University

Population has a direct impact on the demands of consumption, resource, and employment. Population factors, such as size and growth rate, are crucial in making decisions and plans of trade, environment protection, resource allocation and human resource development. Thus, population projection is an essential part of strategy development for companies as well as governments, and draws the attention of many researchers. Some projection methods have been developed, but most of the popular ones require a vast knowledge in demography and only can be operated by skilled professionals. In this paper, as an improvement, we theoretically develop a regression model and a subtrend model of WASD（weights and structure determination）neural network in a simultaneous manner to make population projections especially of Germany in the mid term and near ***, we aim at utilizing the learning capabilities of the WASD neural-network models with single input and multiple inputs, having been very popular recently, to propose these easy-used and high accuracy models for verifications and projections via later computer experiments.

关键词： Germany population Projections Neural network WASD（weights and structure determination） Multiple inputs

来源：评论

学校读者我要写书评

暂无评论

GC-IGTG: A rehabilitation gait trajectory generation algorithm for lower extremity exoskeleton

GC-IGTG: A rehabilitation gait trajectory generation algorit...

引用

2019 IEEE International Conference on Robotics and Biomimetics, ROBIO 2019

作者： He, Yong Wu, Xinyu Ma, Yue Cao, Wujing Li, Nan Li, Jinke Feng, Wei Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Shenzhen College of Advanced Technology University of Chinese Academy of Sciences Shenzhen518055 China Department of Mechanical and Automation Engineering Chinese University of Hong Kong Hong Kong

ISBN: (纸本)9781728163215

It is important to offer a natural and personalized rehabilitation gait trajectory, especially in the early stages of walking rehabilitation, for the patients with lower limb disability. Lower extremity exoskeleton has been proven to be efficient to provide highly repeatable and accurate rehabilitation exercise, but most existing exoskeletons' gait trajectories won't vary with the users. This paper proposes an algorithm, named as gait cell based individualized gait trajectory generation (GC-IGTG), for the purpose of offering a natural and personalized gait trajectory reference for the lower extremity exoskeleton based on the body parameters of the patients. The GC-IGTG is based on extreme learning machine and AutoEncoder, which makes it achieve fast training speed and suitable for small sample training conditions. The gait cell concept is proposed to improve the efficiency and safety of the algorithm. The experimental results indicate that the generated trajectories with GC-IGTG are almost identical to the original ones. © 2019 IEEE.

关键词： Patient rehabilitation

来源：评论

学校读者我要写书评

暂无评论

Lycopene Content Prediction Based on Support Vector machine with Particle Swarm Optimization

引用

Nongye Jixie Xuebao/Transactions of the Chinese Society of Agricultural machinery 2012年第4期43卷 143-147+155页

作者： Liu, Wei Wang, Jianping Liu, Changhong Ying, Tiejin School of Electrical Engineering and Automation Hefei University of Technology Hefei 230009 China Key Laboratory of Machine Vision and Intelligence Control Technology Hefei University Hefei 230601 China School of Biosystems Engineering and Food Science Zhejiang University Hangzhou 310058 China

Color-difference was presented to assess the lycopene content conveniently and non-destructively. Due to excessive affecting factors and strong correlation among the parameters in the process, the support vector machine (SVM) was used to set up the predict model. The selection and simplification of the feature parameters was discussed. A compound optimal objective function based on Akaike information criterion (AIC) was constructed. The particle swarm optimization (PSO) algorithm was used to search the optimal value of the objective function and enhance the efficiency. The predictable method had good performance in assessing the lycopene content of different maturity stages.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Spatially distributed sequential array stimulation of tibial anterior muscle for foot drop correction

Spatially distributed sequential array stimulation of tibial...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Hui Zhou Yingying Wang Wanzhen Chen Nanxin Zhang Ludovic Krundel Guanglin Li Key Laboratory of Human-Machine Intelligence-Synergy Systems Chinese Academy of Sciences Shenzhen Guangdong China Shenzhen Key Laboratory of Electromagnetic Control Shenzhen University Shenzhen Guangdong China School of Electronic Loughborough University UK

ISBN: (纸本)9781424492695

Electrode arrays for the ease of electrode placement in the correction of foot drop with surface electrical stimulation have been developed in recent years. However, the configuration and identification of optimal stimulation sites with regard to time efficiency, stimulation comfort, and fatigue resistance is yet to be solved. In this study, the candidate stimulation sites were ranked and selected according to the motor thresholds induced by 1 Hz stimulation trains. Then based on the selected sites, a new stimulation configuration method termed spatially distributed sequential stimulation was tested and compared with traditional single electrode stimulation for foot drop correction in two normal subjects. The preliminary results demonstrated that the motor threshold of spatially distributed sequential stimulation was equal or less than motor thresholds of each stimulus sites. Besides, with the same stimulation parameters, the spatially distributed sequential stimulation induced larger dorsiflexion motion compared with traditional single electrode stimulation. These findings suggest that spatially distributed sequential stimulation on the selected sites might be an effective electrode array configuration method for correcting foot drop with electrical stimulation.

关键词： Electrodes Arrays Muscles Foot Goniometers Fatigue Electrical stimulation

来源：评论

学校读者我要写书评

暂无评论

Train Safety control Based on Deep Deterministic Policy Gradient with control Barrier Function 21

Train Safety Control Based on Deep Deterministic Policy Grad...

引用

21st International Conference on Networking, Sensing and control, ICNSC 2024

作者： Wang, Guoteng Lv, Jidong Liu, Hongjie Chai, Ming Tang, Tao Zhang, Wentao School of Automation and Intelligence Beijing Jiaotong University Beijing China Beijing Jiaotong University National Engineering Research Center of Rail Transportation Operation and Control System Beijing China Beijing Jiaotong University State Key Laboratory of Advanced Rail Autonomous Operation Beijing China Beijing Zhengshi Environmental Engneering Company Beijing China

ISBN: (纸本)9798350365221

Train Relative Distance Braking Mode (RDBM) has great potential to increase line capacity by enabling shorter following distances based on train-to-train communication in-formation. However, it is difficult for traditional train control methods to ensure avoidance of potential collision risks in RDBM while dealing with the nonlinearity and uncertainty of train dynamics. In this paper, a novel train safety control method combining Deep Deterministic Policy Gradient (DDPG) and control Barrier Function(Cbf)is proposed. Firstly, the safety constraint set for adjacent trains, considering their braking capabilities, is analyzed, and the uncertainty of train dynamics is modeled using a Gaussian process. Secondly, DDPG is used to explore the optimal control strategy under the action of uncertain train dynamics, and CBF provides compensation control input to ensure safety during the learning process. Then, a DDPG-CBF algorithm is presented to achieve efficient safety controller design and implementation. Finally, sufficient numerical simulations demonstrate that, compared with DDPG algorithm alone, the DDPG-CBF algorithm can not only ensure the safe and stable operation of trains, but also learn train control strategies expe-ditiously and accurately under different operating environments, with an average efficiency increase of 38.94 %. © 2024 IEEE.

关键词： Braking

来源：评论

学校读者我要写书评

暂无评论

An Improved Task Planning Method for Unmanned Swarms with Coupled Physical and Logical Constraints

An Improved Task Planning Method for Unmanned Swarms with Co...

引用

2024 IEEE International Conference on Unmanned systems, ICUS 2024

作者： Chen, Xiubin Zhang, Lei Xu, Fang Yao, Weiran School of Astronautics Harbin Institude of Technology Harbin China Wuhan 2nd Ship Design and Research Institute Wuhan China Marine Military Intelligence Innovation Institute CSSC Systems Engineering Research Institute Beijing China National Key Laboratory of Complex System Control and Intelligent Agent Cooperation Beijing China

ISBN: (纸本)9798350384185

Traditional task allocation methods for unmanned swarm systems ignore the effects of actual paths, resulting in estimation accuracy *** paper formulates task planning problem by incorporating physical and logical constraints, and establishes an integrated framework of task allocation and path ***-based search method is used to address path planning with physical constraints.A genetic algorithm is employed to solve multi-traveling salesman allocation problem.A bounded suboptimal optimization, a data dictionary, and an island model are introduced to accelerate the convergence speed of the genetic *** experiments verify that compared to the decoupled task planning methods, the proposed method improves task execution efficiency and remains adaptability to various complex spatial maps. © 2024 IEEE.

关键词： Genetic algorithms

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：