检索结果-内蒙古大学图书馆

Parallel Reinforcement Learning:A Framework and Case Study

IEEE/CAA Journal of Automatica Sinica 2018年第4期5卷 827-835页

作者： Teng Liu Bin Tian Yunfeng Ai Li Li Dongpu Cao Fei-Yue Wang State Key Laboratory of Management and Control for Complex System Institute of AutomationChinese Academy of SciencesBeijing 100190China State Key Lab.of Management and Control for Complex System Institute of AutomationChinese Academy of SciencesBeijing 100190China Cloud Computing Center Chinese Academy of SciencesDongguan 523808China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100190China Department of Automation Tsinghua UniversityBeijing 100190China Driver Cognition and Automated Driving Laboratory University of WaterlooWaterloo N2L 3G1Canada IEEE

In this paper, a new machine learning framework is developed for complex system control, called parallel reinforcement learning. To overcome data deficiency of current data-driven algorithms, a parallel system is built to improve complex learning system by self-guidance. Based on the Markov chain(MC) theory, we combine the transfer learning, predictive learning, deep learning and reinforcement learning to tackle the data and action processes and to express the knowledge. Parallel reinforcement learning framework is formulated and several case studies for real-world problems are finally introduced.

关键词： Deep learning machine learning parallel reinforcement learning parallel system predictive learning transfer learning

来源：评论

学校读者我要写书评

暂无评论

Diffusion mechanism simulation of cloud manufacturing complex network based on cooperative game theory

引用

Journal of systems Engineering and Electronics 2018年第2期29卷 321-335页

作者： GENG Chao QU Shiyou XIAO Yingying WANG Mei SHI Guoqiang LIN Tingyu XUE Junjie JIA Zhengxuan Economics and Management School Harbin Institute of Technology at Weihai Beijing Complex Product Advanced Manufacturing Engineering Research Center Beijing Simulation Center State Key Laboratory of Intelligent Manufacturing System Technology Beijing Institute of Electronic System Engineering Science and Technology on Space System Simulation Laboratory Beijing Simulation Center

Cloud manufacturing is a specific implementation form of the "Internet + manufacturing" strategy. Why and how to develop cloud manufacturing platform(CMP), however, remains the key concern of both platform operators and users. A microscopic model is proposed to investigate advantages and diffusion forces of CMP through exploration of its diffusion process and mechanism. Specifically, a three-stage basic evolution process of CMP is innovatively proposed. Then, based on this basic process, a more complex CMP evolution model has been established in virtue of complex network theory, with five diffusion forces identified. Thereafter, simulations on CMP diffusion have been conducted. The results indicate that, CMP possesses better resource utilization,user satisfaction, and enterprise utility. Results of simulation on impacts of different diffusion forces show that both the time required for CMP to reach an equilibrium state and the final network size are affected simultaneously by the five diffusion forces. All these analyses indicate that CMP could create an open online cooperation environment and turns out to be an effective implementation of the "Internet + manufacturing" strategy.

关键词： complex network cloud manufacturing innovation diffusion network effect Gale-Shapley algorithm cooperative game theory

来源：评论

学校读者我要写书评

暂无评论

Group feature learning and domain adversarial neural network for aMCI diagnosis system based on EEG

arXiv

引用

arXiv 2021年

作者： Fan, Chen-Chen Xie, Haiqun Peng, Liang Yang, Hongjun Ni, Zhen-Liang Wang, Guanan Zhou, Yan-Jie Chen, Sheng Fang, Zhijie Huang, Shuyun Hou, Zeng-Guang State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China CAS Center for Excellence in Brain Science and Intelligence Technology Beijing100190 China Joint Laboratory of Intelligence Science and Technology Institute of Systems Engineering Macau University of Science and Technology China Department of Neurology First People’s Hospital of Foshan FoshanGuangdong528000 China

— Medical diagnostic robot systems have been paid more and more attention due to its objectivity and accuracy. The diagnosis of mild cognitive impairment (MCI) is considered an effective means to prevent Alzheimer’s disease (AD). Doctors diagnose MCI based on various clinical examinations, which are expensive and the diagnosis results rely on the knowledge of doctors. Therefore, it is necessary to develop a robot diagnostic system to eliminate the influence of human factors and obtain a higher accuracy rate. In this paper, we propose a novel Group Feature Domain Adversarial Neural Network (GF-DANN) for amnestic MCI (aMCI) diagnosis, which involves two important modules. A Group Feature Extraction (GFE) module is proposed to reduce individual differences by learning group-level features through adversarial learning. A Dual Branch Domain Adaptation (DBDA) module is carefully designed to reduce the distribution difference between the source and target domain in a domain adaption way. On three types of data set, GF-DANN achieves the best accuracy compared with classic machine learning and deep learning methods. On the DMS data set, GF-DANN has obtained an accuracy rate of 89.47%, and the sensitivity and specificity are 90% and 89%. In addition, by comparing three EEG data collection paradigms, our results demonstrate that the DMS paradigm has the potential to build an aMCI diagnose robot system. © 2021, CC BY.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

A Parallel Medical Diagnostic and Treatment system for Chronic Diseases

A Parallel Medical Diagnostic and Treatment System for Chron...

引用

Chinese Automation Congress (CAC)

作者： Jing Wang Xiao Wang Yuanyuan Guo Fei-Yue Wang The 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 Institute of Smart Healthcare Systems Qingdao Academy of Intelligent Industries Qingdao China

ISBN: (数字)9781728176871

ISBN: (纸本)9781728176888

In order to improve the accuracy of diagnosis and the effectiveness of treatment on chronic diseases, a parallel medical diagnostic and treatment system for chronic diseases is proposed in this paper. The system consists of the artificial system, computational experiments and parallel execution. Generally, the actual medical system includes real doctors, real patients, and the process of real doctors diagnosing and creating a treatment plan. Based on the components in actual medical system, the virtual doctors and virtual patients are created in artificial system. The computational experiments are to exhaustively explore and evaluate reasonable diagnoses and treatment options, so that the most accurate diagnosis and the best treatment plan are configured. The parallel execution between the artificial and the actual system includes the interaction between virtual doctors and real doctors as well as that between the virtual patients and actual patients. The parallel execution, on the doctors' end, is to ensure the precise diagnosis of diseases and the effectiveness of the treatment plan. On the other hand, the parallel execution, on the patients' end, is to provide patients with more personal guidance on following the treatment and to assist sending feedback to the system regarding the treatment effectiveness. As the chronic diseases generally require a long-term treatment, this parallel system can better accommodate the process by continuously monitoring the treatment and sending feedback to the model so as to actively optimize the treatment plan.

关键词： Medical diagnostic imaging Medical services Diseases Medical diagnosis Deep learning Neural networks Knowledge engineering

来源：评论

学校读者我要写书评

暂无评论

Graph Attention Model Embedded With Multi-Modal Knowledge For Depression Detection

Graph Attention Model Embedded With Multi-Modal Knowledge Fo...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Wenbo Zheng Lan Yan Chao Gou Fei-Yue Wang School of Software Engineering Xi’an Jiaotong University Xi’an China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Intelligent Systems Engineering Sun Yat-sen University

ISBN: (数字)9781728113319

ISBN: (纸本)9781728113326

With more than 300 million people depressed worldwide annually, depression is a global problem. The goal of depression detection is to improve diagnostic accuracy and availability, leading to faster intervention. The most important and challenging problem here is to design an effective and robust depression detection model. To this end, there are two challenges to overcome: 1) Multi-modal (audio, image, text, etc.) information must be jointly considered to make accurate inferences. 2) Existing deep learning-based work suffers from multi-modal data sufficiency problem. To address these issues, we propose a graph attention model embedded with multi-modal knowledge for depression detection. This approach learns not only reasonable embeddings for nodes in the knowledge graph, but also exploits medical knowledge to improve the performance of classification and prediction with the knowledge attention mechanism. Experimental results on the real-world datasets show that the proposed approach significantly improves the classification and prediction performance compared with other major state-of-the-art approaches, with guaranteed the robustness with each modality of multi-modal data. Overall, this paper shows how multi-modal knowledge attention mechanism and deep-learning-based networks can be combined to assist mental health patients and practitioners.

关键词： Biomedical imaging Robustness Data models Machine learning Task analysis Knowledge engineering

来源：评论

学校读者我要写书评

暂无评论

Parallel Building Process management system

Parallel Building Process Management System

引用

Chinese Automation Congress (CAC)

作者： Sheng Liu Xisong Dong Gang Xiong Zhen Shen Bin Hu Xiaoyu Chen State Key Laboratory for Management and Control of Complex System Institute of Automation Chinese Academy of Sciences Beijing China Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan China Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing China Institution of Intelligent Manufacturing Qingdao Academy of Intelligent Industries Qingdao China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781665426480

With the development of industrialized building and intelligence technology, it becomes necessary and possible to realize building process intelligence management. In recent years, digital twins and parallel management get more and more attentions in academic research and industrial applications. This paper addresses how parallel building system performs intelligence management on industrialized building process. Firstly, actual building model and artificial building model are created according to actual building system. Then business driving engine and simulation engine drive actual building model and artificial building model, respectively. Participants receive and send messages by software interfaces. Business driving engine changes the status of actual building model and sends the changes to simulation engine. Simulation engine updates the status of artificial building model and runs artificial building model with various parameters. Then it sends the parameter with the best effect to business driving engine. Business driving engine sends recommendations to participants according to the best parameter. Thus, building process intelligence management is achieved.

关键词： Automation Digital twin Buildings User interfaces Software Engines Business

来源：评论

学校读者我要写书评

暂无评论

Fault-Tolerant control of a CPG-Governed Robotic Fish

引用

Engineering 2018年第6期4卷 861-868页

作者： Yueqi Yang Jian Wang Zhengxing Wu Junzhi Yu State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100049China University of the Chinese Academy of Sciences Beijing 100049China

Fault tolerance is essential for the maneuverability of self-propelled biomimetic robotic fish in real-world aquatic *** paper explores the fault-tolerance control problem of a free-swimming robotic fish with multiple moving joints and a stuck tail *** created control system is composed of two main components:a feedback controller and a feedforward ***,the bio-inspired central pattern generator-based feedback controller is designed to make the robotic fish robust to external disturbances,while the feedforward compensator speeds up the convergence of the overall control *** are performed for control system analysis and performance validation of the faulty robotic *** experimental results demonstrate that the proposed fault-tolerant control method is able to effectively regulate the faulty robotic fish,allowing it to complete the desired motion in the presence of damage and thereby improving both the stability and the lifetime of the real robotic system.

关键词： Fault-tolerant control Robotic fish Motion control Feedback controller Feedforward compensator

来源：评论

学校读者我要写书评

暂无评论

Motion control and Motion Coordination of Bionic Robotic Fish： A Review

引用

Journal of Bionic Engineering 2018年第4期15卷 579-598页

作者： Junzhi Yu Ming Wang Huifang Dong Yanlu Zhang Zhengxing Wu State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China School of Information and Electrical Engineering Shandong Jianzhu University Jinan 250101 China

Fish＇s outstanding motion and coordination performance make it an excellent source of inspiration for scientists and engineers aiming to design and control next-generation autonomous underwater vehicles within the framework of bionics. This paper offers a general review of the current status of bionic robotic fish, with particular emphasis on the hydrodynamic modeling and testing, kinematic modeling and control, learning and optimization, as well as motion coordination control. Among these aspects, representative studies based on ideas and concepts inspired from fish motion and coordination are discussed. At last, the major challenges and the future research directions are addressed in the context of integration of various research streams from ichthyologic, hydrodynamic, mechanical, electronic, control, and artificial intelligence. Further development of bionic robotic fish can be utilized to execute some specific missions in complex underwater environments, where operations are unsafe or impractical for divers or conventional underwater vehicles.

关键词： bionic robotic fish motion control coordination control fish swimming learning and optimization

来源：评论

学校读者我要写书评

暂无评论

Research on Trajectory Planning and Motion control of 7-DoF Sawyer Manipulator

Research on Trajectory Planning and Motion Control of 7-DoF ...

引用

Digital Twins and Parallel Intelligence (DTPI), IEEE International Conference on

作者： Kun Luo Gang Xiong Yuxiao Wang Bin Hu Sheng Liu Shichao Chen The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijng China School of Artificial Intelligence University of Chinese Academy of Sciences Beijng China Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Beijng China Qingdao Academy of Intelligent Industries Chinese Academy of Sciences Beijng China

Regarding human-machine collaborative task, generated trajectories of a robot manipulator should be able to avoid joint limits and singularities, but the 6 Degrees of Freedom(DoF) or lower DoF manipulators encounter difficulties in many schemes. In this paper, research is implemented on the methods of trajectory planning and motion control on the newly human-machine collaborative 7-DoF Sawyer manipulator. We try to pay more attention to these approaches and find a better combination between trajectory planners and motion controllers for Sawyer manipulator. First of all, comparison is proposed between the methods about trajectory planning in task space and joint space, drawing a conclusion that the latter has the advantage of quickness and smoothness on trajectories in real time. Next, we choose to plan trajectory in the joint space by interpolating positions and orientations. Three approaches, i.e., trapezoidal velocity trajectory, cubic polynomial trajectory and basic spline trajectory, are applied to interpolate positions. Experimental results show that it results in the smoothest trajectory using basic spline trajectory planning. We also compare linear and nonlinear orientation interpolations to address the angle wrapping issue, which leads to difficulties in smooth orientation interpolation between several waypoints. Combining polynomial trajectory planning methods with the proportional-derivative (PD) motion controller and the computed-torque motion controller, we focus on the performance of the two different combinations. It is found that trajectories with computed-torque controller have shorter path with a congruous convergence on joint position, and more accurate trajectories with less overshoots in position than others.

关键词： Interpolation Trajectory planning Collaboration Aerospace electronics Manipulators Trajectory Task analysis

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning based Lane Change Decision-Making with Imaginary Sampling

Reinforcement Learning based Lane Change Decision-Making wit...

引用

IEEE Symposium Series on Computational Intelligence (SSCI)

作者： Dong Li Dongbin Zhao Qichao Zhang The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (数字)9781728124858

ISBN: (纸本)9781728124865

This paper investigates the autonomous driving lane change problem with reinforcement learning methods. A two-stage control method is proposed which includes a decision-making module computing the high-level lane change action and a lateral control module outputting the low-level steering angle. Due to the decoupling system framework, the proposed controller can flexibly cancel the previous improper lane change command. To improve the data efficiency in the lateral control module, the Gaussian process is employed to modeling the local time-interval system models. These models are used to generate imaginary samples and facilitate the reinforcement learning training process. The lateral control experiments show that the imaginary samples can improve the data efficiency and speed up the training process. Finally, the two-lane scene and three-lane scene experiments validate the effectiveness of the proposed two-stage lane change method.

关键词： Decision making Learning (artificial intelligence) Gaussian processes Uncertainty Estimation Autonomous vehicles Roads

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：