检索结果-内蒙古大学图书馆

A Parallel control Method for Zero-Sum Game with Unknown Time-Varying System

The International Journal of Intelligent control and systems 2024年第1期29卷 37-41页

作者： Qinglai Wei Zhenhua Zhu Jie Zhang Fei-Yue Wang State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China Institute of Systems Engineering Macao University of Science and TechnologyMacao 999078China

In this paper,based on ACP(ACP:artificial societies,computational experiments,and parallel execution)approach,a parallel control method is proposed for zero-sum games of unknown time-varying *** process of constructing a sequence of artificial systems,implementing the computational experiments,and conducting the parallel execution is *** artificial systems are constructed to model the real *** experiments adopting adaptive dynamic programming(ADP)are shown to derive control laws for a sequence of artificial *** purpose of the parallel execution step is to derive the control laws for the real ***,simulation experiments are provided to show the effectiveness of the proposed method.

关键词： Zero-sum games parallel control ACP(ACP:artificial societies computational experiments and parallel execution) adaptive dynamic programming(ADP)

来源：评论

学校读者我要写书评

暂无评论

Investigating the neural activity of various 3D visual fatigue degrees using depth-related visual evoked potentials

引用

JOURNAL OF THE SOCIETY FOR INFORMATION DISPLAY 2021年第3期29卷 196-206页

作者： Yue, Kang Wang, Danli Chinese Acad Sci Inst Automat Beijing Peoples R China State Key Lab Management & Control Complex Syst Beijing Peoples R China Beijing Inst Technol Sch Opt & Photon Beijing Peoples R China

Severe visual fatigue symptoms occur while users view three-dimensional (3D) content. These symptoms adversely affect the user experience and hinder the widespread application of 3D media. Existing studies mainly used electroencephalography (EEG) power (based on frequency domain analysis) to evaluate 3D visual fatigue (3DVF), but their results were often contradictory and confusing. To address this problem, we investigated the relationship between EEG features and visual fatigue from the perspective of both time and time-frequency domain. Random-dot stereograms (RDS) with various disparities were employed to elicit depth-related visual evoked potentials (VEPs). The experiment lasted about 27 min for each subject to induce fatigue, and the EEG was recorded synchronously. VEPs of different fatigue levels were processed to extract both time (such as P-120 and N-170 components in VEPs) and time-frequency (like event-related spectral perturbation [ERSP]) domain characteristics. A significant increase in P-120 amplitude was observed in the parietal region, and time-frequency analysis also revealed a significant ERSP decrease of theta bands in the central-frontal region with a latency of 200 to 300 ms when subjects suffered fatigue. Our results confirm the hypothesis that activity of theta decreased with 3DVF level, or rather, we found ERSPs of theta bands on FC4 and Cz in the 200- to 300-ms window decreased significantly across four fatigue levels. Furthermore, we first reported the relationship between P-120 amplitude and 3DVF, which implied this feature could be considered as a feature of 3DVF evaluation. In summary, our studies could provide a new insight for 3DVF evaluation using EEG.

关键词： 3D EEG visual fatigue

来源：评论

学校读者我要写书评

暂无评论

Deep patch learning algorithms with high interpretability for regression problems

引用

INTERNATIONAL JOURNAL OF INTELLIGENT systems 2022年第11期37卷 8239-8276页

作者： Huang, Yunhu Chen, Dewang Zhao, Wendi Lv, Yisheng Wang, Shiping Fuzhou Univ Coll Comp & Data Sci Fuzhou Peoples R China FuJian Univ Technol Sch Transportat Fuzhou 350118 Peoples R China Fujian Univ Technol Intelligent Transportat Syst Res Ctr Fuzhou Peoples R China Chinese Acad Sci State Key Lab Management & Control Complex Syst Inst Automat Beijing Peoples R China Fujian Prov Key Lab Network Comp & Intelligent In Fuzhou Peoples R China

Improving the performance of machine learning algorithms to overcome the curse of dimensionality while maintaining interpretability is still a challenging issue for researchers in artificial intelligence. Patch learning (PL), based on the improved adaptive network-based fuzzy inference system (ANFIS) and continuous local optimization for the input domain, is characterized by high accuracy. However, PL can only handle low-dimensional data set regression. Based on the parallel and serial ensembles, two deep patch learning algorithms with embedded adaptive fuzzy systems (DPLFSs) are proposed in this paper. First, using the maximum information coefficient (MIC) and Pearson's correlation coefficients for feature selection, the variables with the least relationship (linear or nonlinear) are excluded. Second, principal component analysis is used to reduce the complexity further of DPLFSs. Meanwhile, fuzzy C-means clustering is used to enhance the interpretability of DPLFSs. Then, an improved PL method is put forward for the training of each sub-fuzzy system in a fashion of bottom-up layer-by-layer, and finally, the structure optimization is performed to significantly improve the interpretability of DPLFSs. Experiments on several benchmark data sets show the advantages of a DPLFS: (1) it can handle medium-scale data sets;(2) it can overcome the curse of dimensionality faced by PL;(3) its precision and generalization are greatly improved;and (4) it can overcome the poor interpretability of deep learning networks. Compared with shallow and deep learning algorithms, DPLFSs have the advantages of interpretability, self-learning, and high precision. DPLFS1 is superior for medium-scale data;DPLFS2 is more efficient and effective for high-dimensional problems, has a faster convergence, and is more interpretable.

关键词： deep learning deep patch learning fuzzy system fuzzy C-means clustering interpretability maximum information coefficient (MIC) Pearson's correlation coefficients (PCC)

来源：评论

学校读者我要写书评

暂无评论

Biocompatible Ferrofluid Robot With Photothermal Property for Targeted Tumor Therapy

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2022年第4期7卷 11517-11522页

作者： Ji, Yiming Bai, Xue Sun, Hongyan Wang, Luyao Xu, Junjie Gan, Chunyuan Dai, Yuguo Hui, Hui Feng, Lin Beihang Univ Sch Mech Engn & Amp Automat Beijing 100191 Peoples R China Inst Automat CAS Key Lab Mol Imaging State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Beijing 100080 Peoples R China Beihang Univ Beijing Adv Innovat Ctr Biomed Engn Sch Mech Engn & Amp Automat Beijing 100083 Peoples R China

Magnetic-controlled micro-robots have promising applications in disease therapy due to their high targetability and drug utilization. Due to their unique deformable and divisible properties, ferrofluid robots have gained much attention in microchemical reaction chips and micromanipulation. This letter proposes a biocompatible ferrofluid robot and validates its potential to achieve targeted drug delivery and tumor cell killing. This biocompatible ferrofluidic robot contains 10 nm oleic acid-coated ferric tetroxide particles and vegetable oil and has good magnetic responsiveness, deformability, and photothermal properties, and can move in liquid environments such as blood. It can achieve motion with an error of less than 0.4 mm under closed-loop control and obstacle overturning and passage through narrow channels less than twice its diameter. In addition, the biocompatible ferrofluid robot can kill tumor cells in the target area due to the photothermal properties of the magnetic particles, and experimental results show that the tumor cell death rate can reach 95%. These capabilities give the biocompatible ferrofluid robot a significant advantage in getting the target location for cancer treatment through the vascular environment.

关键词： Soft robot materials and design soft robot applications medical robots and systems

来源：评论

学校读者我要写书评

暂无评论

Learning Continuous 3-DoF Air-to-Air Close-in Combat Strategy using Proximal Policy Optimization

Learning Continuous 3-DoF Air-to-Air Close-in Combat Strateg...

引用

IEEE Conference on Games (CoG)

作者： Li, Luntong Zhou, Zhiming Chai, Jiajun Liu, Zhen Zhu, Yuanheng Yi, Jianqiang Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Chinese Acad Sci Integrated Infoimat Syst Res Ctr Inst Automat Beijing 100190 Peoples R China

ISBN: (数字)9781665459891

ISBN: (纸本)9781665459891

Air-to-air close-in combat is based on many basic fighter maneuvers and can be largely modeled as an algorithmic function of inputs. This paper studies autonomous close-in combat, to learn new strategy that can adapt to different circumstances to fight against an opponent. Current methods for learning close-in combat strategy are largely limited to discrete action sets whether in the form of rules, actions or sub-polices. In contrast, we consider one-on-one air combat game with continuous action space and present a deep reinforcement learning method based on proximal policy optimization (PPO) that learns close-in combat strategy from observations in an end-to-end manner. The state space is designed to promote the learning efficiency of PPO. We also design a minimax strategy for the game. Simulation results show that the learned PPO agent is able to defeat the minimax opponent with about 97% win rate.

关键词： air-combat reinforcement learning proximal policy optimization flight simulation

来源：评论

学校读者我要写书评

暂无评论

Current Problems and Solutions of Industrial control Network Intrusion Detection: A Brief Survey

Current Problems and Solutions of Industrial Control Network...

引用

2022 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2022

作者： Jiang, Tianyu Zhang, Chen Wang, Rui Chai, Senchun Institute of Automation Chinese Academy of Sciences and University of Science and Technology Beijing China Beijing Institute of Technology China Institute of Automation Chinese Academy of Sciences State Key Laboratory of Management and Control for Complex Systems China Institute of Intelligent Information Processing and Control Beijing Institute of Technology China

ISBN: (数字)9781665469838

ISBN: (纸本)9781665469838

With the advancement of industrial intelligence, the Industrial Internet has been widely used in energy, manufacturing and other important industries. In recent years, security incidents have occurred frequently in industrial control network, which means that maintaining industrial control network security has become more and more important. Intrusion detection technology can actively detect abnormal behavior in the network, and is an important means to ensure the security of industrial control networks. Presently, the intrusion detection technology of industrial control network has problems such as extreme imbalance of classes and redundant interference of traffic characteristics. This paper analyzes these problems and clarifies the existing solutions for different problems in principle. © 2022 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Asynchronous L1-gain Filtering of Nonlinear Positive Semi-Markov Jump systems with Time-varying Delays

Asynchronous L1-gain Filtering of Nonlinear Positive Semi-Ma...

引用

第41届中国控制会议

作者： Chao Ma Hang Fu Yidao Ji Wei Wu School of Mechanical Engineering University of Science and Technology State Key Lab of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences

In this paper,the L-gain based filtering problem for nonlinear positive semi-Markov jump systems is investigated by proposing a novel asynchronous design *** precisely,the mode-dependent filters are designed in terms of practical observed modes instead of true system modes,such that less conservatism can be *** addition,the effect of time-varying delays is taken into account for more robustness and *** selecting suitable stochastic Lyapunov-Krasovskii functions and applying the linear programming method,sufficient conditions are established to fulfill the desired L-gain ***,the illustrative simulation is performed to verify the effectiveness of our developed control scheme.

关键词： Positive semi-Markov jump systems nonlinear semi-Markov jump systems asynchronous filtering L1-gain

来源：评论

学校读者我要写书评

暂无评论

A New Self-Learning Optimization management Scheme for Smart Grid systems

引用

The International Journal of Intelligent control and systems 2024年第2期29卷 66-70页

作者： Qinglai Wei Zehua Liao School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China Institute of Systems Engineering Macao University of Science and TechnologyMacao 999078China

This paper presents a new energy optimization management scheme for the smart grid system(SGS),which considers not only the inclusion of renewable energy in energy management but also the feedback sale of redundant renewable energy to the grid,so as to obtain better optimization management results and avoid energy waste.A new performance index function is constructed,which aims to save users’electricity costs and protect energy storage *** construct a periodic iterative self-learning method based on the characteristics that the relevant data of SGS are approximately *** proposed self-learning optimization method is based on adaptive dynamic programming(ADP).The initial iterative control law is obtained by pre-training,and the designed method can be realized by neural *** experiments are carried out by using the relevant data of SGS for four *** experimental results show that the new energy management scheme can help users save a lot of electricity costs,and is more effective than some common methods.

关键词： Smart grid system energy management renewable energy self-learning adaptive dynamic programming

来源：评论

学校读者我要写书评

暂无评论

A Spatiotemporal Hybrid Model for Airspace complexity Prediction

引用

IEEE INTELLIGENT TRANSPORTATION systems MAGAZINE 2023年第2期15卷 217-224页

作者： Du, Wenbo Li, Biyue Chen, Jun Lv, Yisheng Li, Yumeng Beihang Univ Sch Elect & Informat Engn Natl Engn Lab Big Data Applicat Technol Comprehen Beijing 100191 Peoples R China Queen Mary Univ London Sch Engn & Mat Sci London E1 4NS England Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

Airspace complexity is a key indicator that reflects the safety of airspace operations in air traffic management systems. Furthermore, to achieve efficient air traffic control, it is necessary to accurately predict the airspace complexity. In this article, we propose a novel spatiotemporal hybrid deep learning model for airspace complexity prediction to efficiently capture spatial correlations as well as temporal dependencies pertaining to the airspace complexity data. Specifically, we apply convolutional networks to discover the short-term temporal patterns and skip long short-term memory networks to model the longterm temporal patterns of airspace complexity data. Furthermore, it is observed that the graph attention network in our proposed model, which emphasizes capturing the spatial correlations of the airspace sectors, can significantly improve the prediction accuracy. Extensive experiments are conducted on the real data of six airspace sectors in Southwest China. The experimental results show that our spatiotemporal deep learning approach is superior to state-of-the-art methods.

关键词： complexity theory Atmospheric modeling Spatiotemporal phenomena Predictive models Deep learning Correlation Air traffic control

来源：评论

学校读者我要写书评

暂无评论

Traditional Chinese medicine diagnosis and treatment based on systematics

引用

iLIVER 2023年第4期2卷 181-187页

作者： Zhanhong Wang Danli Wang Wen Liu Zhongxia Wang The State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190 School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China Beijing Hospital of Traditional Chinese Medicine Capital Medical UniversityBeijing 100010China Department of Nutrition Fifth Medical CenterPLA General HospitalBeijing 100039China

Background:Traditional Chinese Medicine(TCM)is a well-established medical system with a long ***,the overall concept and systematic thinking in TCM are not comprehensively understood and applied in its inheritance and *** This study aims to provide a basic theory for TCM diagnosis using systematics as the guiding *** modern scientific and technological achievements,we aim to explore a new TCM diagnosis ***:We analyzed previous studies on TCM diagnosis and treatment,and reviewed clinical research on TCM diagnosis and treatment from the viewpoint of *** propose a new process model based on systematics for TCM diagnosis and *** is a generalized model that summarizes the process of“establishing an image to express meaning”.Results:The proposed model was implemented in the clinical practice of *** monitored the detailed treatment process of patients in the Department of Liver Diseases at Beijing *** patient underwent a treatment program that lasted 1 year and 45 days,consisting of 12 iterative cycles,each guided by the proposed diagnostic model and tailored to the patient's evolving *** case study validates the effectiveness of the proposed model in the diagnosis and treatment of liver disease in *** therapeutic efficacy has been validated through the examination of both TCM indicators and Western medical auxiliary *** these,the TCM indicators consist of 2 components:tongue diagnosis and pulse ***,the Western medical auxiliary indicators encompass a range of assessments,including whole blood cell analysis,professional liver function examination,a series of liver function assessments,a high-sensitivity hepatitis B pentathlete test,as well as color Doppler ultrasound evaluations of the liver,bile duct,pancreas,spleen,and assessments of liver elasticity,among other related examination *** conclusion,it is evident that the syndrome of l

关键词： Traditional Chinesemedicine Systematics Diagnosis and treatment model Liver disease

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：