检索结果-内蒙古大学图书馆

FCM-RDpA: TSK fuzzy regression model construction using fuzzy C-means clustering, regularization, Droprule, and Powerball Adabelief

引用

INFORMATION SCIENCES 2021年 574卷 490-504页

作者： Shi, Zhenhua Wu, Dongrui Guo, Chenfeng Zhao, Changming Cui, Yuqi Wang, Fei-Yue Huazhong Univ Sci & Technol Key Lab Sch Artificial Intelligence & Automat Minist Educ Image Proc & Intelligent Control Wuhan 430074 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100049 Peoples R China

To effectively optimize Takagi-Sugeno-Kang (TSK) fuzzy systems for regression problems, a mini-batch gradient descent with regularization, DropRule, and AdaBound (MBGD-RDA) algorithm was recently proposed. This paper further proposes FCM-RDpA, which improves MBGD-RDA by replacing the grid partition approach in rule initialization by fuzzy c-means clustering, and AdaBound by Powerball AdaBelief, which integrates recently proposed Powerball gradient and AdaBelief to further expedite and stabilize parameter optimization. Extensive experiments on 22 regression datasets with various sizes and dimensionalities validated the superiority of FCM-RDpA over MBGD-RDA, especially when the feature dimensionality is higher. We also propose an additional approach, FCM-RDpAx, that further improves FCM-RDpA by using augmented features in both the antecedents and consequents of the rules. (c) 2021 Elsevier Inc. All rights reserved.

关键词： TSK fuzzy system Mini-batch gradient descent DropRule Powerball AdaBelief Fuzzy c-means clustering

来源：评论

学校读者我要写书评

暂无评论

Gesture Recognition and Conductivity Reconstruction Parameters Analysis with an Electrical-Impedance-Tomography (EIT) Based Interface: Preliminary Results 14th

Gesture Recognition and Conductivity Reconstruction Paramete...

引用

14th International Conference on Intelligent Robotics and Applications (ICIRA)

作者： Liu, Xiaodong Zheng, Enhao Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

ISBN: (纸本)9783030890988;9783030890971

With the development of Human-machine interface (HMI), the requirements of perceiving the human intention are much higher. Electrical Impedance Tomography (EIT) is a promising alternative to existing HMIs because of its portability, non-invasiveness and inexpensiveness. In this study, we designed an EIT-based gesture recognition method achieving the recognition of 9 forearm motion patterns. We analysed the parameters, including current level and contact impedance, which are relevant for practical applications in robotic control. The gesture recognition method produced an average accuracy of 99.845% over nine gestures with PCA and QDA model on one subject. The preliminary results of parameter analysis suggested that the resolution increased with the current amplitude less than a threshold (5.5 mA) but decreased when the current amplitude was over 5.5 mA. The mean value of Region of Interest (ROI) nodes didn't change obviously when the contact impedance increased. In future works, extensive studies will be conducted on the priori information of forearm and biological-model-based methods to further improve recognition performances in more complicated tasks.

关键词： Human-machine interface (HMI) Electrical Impedance Tomography (EIT) Gesture recognition Quadratic Discriminant Analysis (QDA)

来源：评论

学校读者我要写书评

暂无评论

Zero-Sum Differential Game-Based Fault-Tolerant Tracking control for Nonlinear systems With Multiplicative Failures

Zero-Sum Differential Game-Based Fault-Tolerant Tracking Con...

引用

2022 Chinese Automation Congress, CAC 2022

作者： Tan, Cong Lin, Mingduo Xia, Hongbing Zhao, Bo Xu, Yancai School of Systems Science Beijing Normal University Beijing100875 China Key Laboratory of Industrial Internet of Things & Networked Control Ministry of Education Chongqing University of Posts and Telecommunications Chongqing400065 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China

ISBN: (纸本)9781665465335

A novel fault-tolerant tracking control (FTTC) approach for affine nonlinear systems is developed from the perspective of zero-sum differential games (ZSDG) to deal with unknown multiplicative actuator failures in this paper. By regarding the control input and the multiplicative actuator failure as two players of a zero-sum game, a performance index function reflecting the trajectory tracking error, the control policy and the unknown failure is established. To handle the tracking Hamilton-Jacobi-Isaacs (HJI) equation associated with the established performance index function, a critic neural network is utilized. Then, the Nash equilibrium solution can be obtained, and the FTTC is achieved. The stability of the faulty nonlinear system is examined through Lyapunov-based approach. Finally, simulation results of a spring system is provided to ensure the utility and the realizability of the ZSDG-based FTTC approach. © 2022 IEEE.

关键词： Nonlinear systems

来源：评论

学校读者我要写书评

暂无评论

MGRL: Graph neural network based inference in a Markov network with reinforcement learning for visual navigation

引用

NEUROCOMPUTING 2021年 421卷 140-150页

作者： Lu, Yi Chen, Yaran Zhao, Dongbin Li, Dong Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Beijing 101408 Peoples R China

Visual navigation is an essential task for indoor robots and usually uses the map as assistance to providing global information for the agent. Because the traditional maps match the environments, the map based and map-building-based navigation methods are limited in the new environments for obtaining maps. Although the deep reinforcement learning navigation method, utilizing the non-map-based navigation technique, achieves satisfactory performance, it lacks the interpretability and the global view of the environment. Therefore, we propose a novel abstract map for the deep reinforcement learning navigation method with better global relative position information and more reasonable interpretability. The abstract map is modeled as a Markov network which is used for explicitly representing the regularity of objects arrangement, influenced by people activities in different environments. Besides, a knowledge graph is utilized to initialize the structure of the Markov network, as providing the prior structure for the model and reducing the difficulty of model learning. Then, a graph neural network is adopted for probability inference in the Markov network. Furthermore, the update of the abstract map, including the knowledge graph structure and the parameters of the graph neural network, are combined into an end-to-end learning process trained by a reinforcement learning method. Finally, experiments in the AI2THOR framework and the physical environment indicate that our algorithm greatly improves the success rate of navigation in case of new environments, thus confirming the good generalization. (C) 2020 Elsevier B.V. All rights reserved.

关键词： Visual navigation Graph neural network Markov network Reinforcement learning Probabilistic graph model Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Childhood-onset systemic lupus erythematosus in China, 2016-21: a nationwide study

引用

LANCET CHILD & ADOLESCENT HEALTH 2024年第10期8卷 762-772页

作者： Gao, Sihao Yu, Zhongxun Ma, Xudong Sun, Jialu Ren, Aiguo Gao, Sifa Gong, Mengchun Zhou, Xiang Ma, Mingsheng Song, Hongmei Chinese Acad Med Sci & Peking Union Med Coll Peking Union Med Coll Hosp State Key Lab Complex Severe & Rare Dis Dept Pediat Beijing Peoples R China Chinese Acad Med Sci & Peking Union Med Coll Peking Union Med Coll Hosp Dept Crit Care Med State Key Lab Complex Severe & Rare Dis Beijing Peoples R China Chinese Acad Med Sci & Peking Union Med Coll State Key Lab Complex Severe & Rare Dis Dept Informat Management Informat Ctr DeptPeking Union Med Coll Hosp Beijing Peoples R China Natl Hlth Commiss Peoples Republ China Dept Med Adm Beijing Peoples R China Natl Hlth Commiss Peoples Republ China Natl Inst Hosp Adm Beijing 100044 Peoples R China Natl Hlth Commiss Peoples Republ China Inst Reprod & Child Hlth Key Lab Reprod Hlth Beijing Peoples R China Peking Univ Sch Publ Hlth Dept Epidemiol & Biostat Beijing Peoples R China Southern Med Univ Inst Hlth Management Guangzhou Peoples R China China Natl Crit Care Qual Control Ctr Grp Hong Kong Peoples R China Chinese Acad Med Sci & Peking Union Med Coll Peking Union Med Coll Hosp Dept Pediat State Key Lab Complex Severe & Rare Dis Beijing 100730 Peoples R China

Background Childhood-onset systemic lupus erythematosus (SLE) is a complex autoimmune disorder that can lead to serious organ damage. Despite the prevalence of SLE among children in Asian countries, treatment guidelines, prognosis, and clinical decision making for children with SLE are limited by gaps in region-specific epidemiological data. The aim of this study was to analyse epidemiological characteristics of childhood-onset SLE and associated organ involvement and in-hospital mortality in China. Methods In this nationwide study, we searched standardised hospital discharge records submitted to the Hospital Quality Monitoring System (HQMS) between Jan 1, 2016, and Dec 31, 2021, for patients with a diagnosis of childhood-onset SLE based on the 2019 American College of Rheumatology or 2012 Systemic Lupus International Collaborating Clinics classification criteria. We selected records for patients aged 18 years and younger containing relevant ICD 10th revision diagnostic codes (specifically M32) among discharge diagnostic codes. We excluded records for patients younger than 5 years, whose SLE diagnosis was presumed to be monogenic lupus, and for patients with overlap syndromes or unidentified sex. Date of diagnosis (equal to the first hospital discharge date), age, organ involvement, intensive care unit (ICU) treatment, and in-hospital mortality were extracted from the records. Incidence rates for 2017, 2018, 2019, 2020, and 2021 were identified with five washout periods ranging from 12 months (Jan 1-Dec 31, 2016) to 60 months (Jan 1, 2016-Dec 31, 2020). Data were stratified by sex, age relative to puberty onset, organ involvement and concurrent infection at time of diagnosis, human development index of region of residence, hospital level, and hospital type. Incidence trends by sex, age relative to puberty onset, and year were derived by joinpoint regression analysis, with 95% CIs calculated by the Poisson exact method. Major organ involvement was assessed according

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive Event-Triggered Near-Optimal Tracking control for Unknown Continuous-Time Nonlinear systems

引用

IEEE ACCESS 2022年 10卷 9506-9518页

作者： Wang, Kunfu Gu, Qijia Huang, Baiqiao Wei, Qinglai Zhou, Tianmin Nanjing Univ Informat Sci & Technol Sch Math & Stat Nanjing 210044 Peoples R China China State Shipbldg Corp Ltd Syst Engn Res Inst Beijing 100036 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

This paper studies the event-triggered optimal tracking control (ETOTC) problem of continuous-time (CT) unknown nonlinear systems. In order to solve the ETOTC problem, an augmented system composed of the error system dynamics and the reference dynamics is used to introduce a new discounted performance index function (DPIF). A novel event-triggered (ET) adaptive dynamic programming (ADP) method is developed to solve the ET Hamilton-Jacobi-Bellman equation (HJBE). The presented method is implemented via an identifier-critic architecture, which consists of two neural networks (NNs): an identifier NN is applied to estimate the unknown system dynamics, and a critic NN is constructed to obtain the approximate solution of the ET HJBE. The augmented closed-loop system and the critic estimation error are proved to be ultimately uniformly bounded (UUB) by the Lyapunov direct method. Finally, two simulations illustrate the effectiveness of the developed method.

关键词： Dynamic programming Estimation error Artificial neural networks Stability analysis Optimal control Asymptotic stability Adaptive systems Adaptive dynamic programming event-triggered mechanism optimal tracking control nonlinear system

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Inference Attention Module for Unsupervised Domain Adaptation

引用

IEEE TRANSACTIONS ON FUZZY systems 2024年第4期32卷 1706-1718页

作者： Wang, Zhengshan Chen, Long Wang, Fei-Yue Univ Macau Fac Sci & Technol Dept Comp & Informat Sci Macau 999078 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Qingdao Acad Intelligent Ind Parallel Blockchain Technol Innovat Ctr Qingdao 266109 Peoples R China Natl Univ Def Technol Res Ctr Mil Computat Expt & Parallel Syst Changsha 410073 Peoples R China

Unsupervised domain adaptation (UDA) aims to transfer knowledge acquired from the labeled source domain to the unlabeled target domain. However, the quality of samples can vary greatly. While partial samples are dominated by high-quality domain-invariant class-related information, others may only contain irrelevant domain-specific information or useless random noise. Treating all samples equally may lead to negative transfer, significantly impairing the performance. To address the issue of varying sample quality, we propose an attention module to emphasize the samples that are most suitable for transfer. Within the attention module, we have designed a fuzzy inference system to assess the quality of data based on its class and domain information. Such a fuzzy inference attention (FIA) module demonstrates strong interpretability due to its consideration of the fuzzy nature inherent in class and domain information within the data. FIA also has high flexibility and extensibility as the rule base can be easily adjusted by expert knowledge. More importantly, FIA does not use any parameters requiring training and has a low overhead. This makes it fast and applicable to most existing UDA methods. The experiments on several benchmark datasets prove that FIA can bring significant improvement to existing methods.

关键词： Attention module domain adaptation (DA) fuzzy inference system (FIS) negative transfer (NL)

来源：评论

学校读者我要写书评

暂无评论

Dynamic Modeling of the Tuna-Inspired Robotic Fish Based on the Elastic-Damping Mechanism 19

Dynamic Modeling of the Tuna-Inspired Robotic Fish Based on ...

引用

19th IEEE International Conference on Mechatronics and Automation (IEEE ICMA)

作者： Wang, Xiaofei Deng, Liangwei Zhu, Chunhui Yin, Zhaoran Wang, Jian Zhou, Chao Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China

ISBN: (数字)9781665408530

ISBN: (纸本)9781665408530;9781665408523

Compliant passive mechanism has been widely employed in the development of bioinspired aquatic robots that imitates the variable stiffness of fish muscles. However, the existing compliant passive mechanism cannot produce excellent propulsion performance in a wide frequency range. To solve this problem, this paper proposes a novel modeling method for a tuna-inspired robotic fish with passive compliant joint. The passive compliant joint is developed composed of double torsion springs and damping liquid, attempting to implement on the robotic fish to achieve high swimming performance. In order to analyze the motion of the passive joint, a hydrodynamic-twisting-damping torque (HTDT) model is proposed. A dynamic model based on Kane equation is established and indicates that the compliant joint could affect the torque transmitted to the caudal fin to improve the swimming speed of the robotic fish. The particle swarm optimization (PSO) algorithm is further employed to optimize the joint parameters for an enhanced velocity performance. The obtained simulation results suggest that the proposed robotic fish model can reach to a speed of 2.32 m/s, exhibiting an excellent swimming performance. The dynamic model established by this study can make a guideline for the development of robotic fishes with the compliant passive joint.

关键词： Kane dynamic method compliant passive joint velocity optimization PSO algorithm

来源：评论

学校读者我要写书评

暂无评论

Adaptive Event-Triggered control for Non-Strict Feedback Nonlinear CPSs With Time Delays Against Deception Attacks and Actuator Faults

引用

IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING 2024年第3期21卷 4106-4116页

作者： Chen, Wen-Di Niu, Ben Wang, Huan-Qing Li, Hai-Tao Wang, Ding Shandong Normal Univ Sch Informat Sci & Engn Jinan 250014 Peoples R China Bohai Univ Sch Math & Phys Jinzhou 121000 Liaoning Peoples R China Shandong Normal Univ Sch Math & Stat Jinan 250014 Peoples R China Beijing Univ Technol Sch Informat Technol Beijing 100124 Peoples R China Chinese Acad Sci Inst Automation State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

An adaptive event-triggered control strategy for non-strict feedback nonlinear cyber-physical systems with time delays against deception attacks and actuator faults is presented. The most prominent difficulty lies in after the system signals are damaged by malicious deception attacks, all the exact states in the system are unavailable. Another design difficulty is the common existence of unknown nonlinearities and time-varying time delays, which makes it difficult to get the desired controller. Thus, to stabilize the studied cyber-physical systems, an unusual coordinate transformation is presented, where the attack gains and the problem of unavailability of states are considered simultaneously. Furthermore, the effect of the malicious deception attacks on the studied system is tackled by using Nussbaum technology and designing the Lyapunov functions with the attack gains. The unknown nonlinear functions, the mismatch problem for the control input caused by the nonlinearities of time-varying time delays are processed by neural networks technology and Lyapunov-Krasovskii functions. As a result, a controller based on event-triggered mechanism is constructed to reduce the waste of communication resources. The presented control strategy can ensure the signals in the closed-loop system are bounded. Finally, the Matlab simulation experiments are showed to verify the effectiveness of the developed strategy. Note to Practitioners-This paper studies the adaptive event-triggered control strategy for non-strict feedback nonlinear cyber-physical systems with time delay under deception attacks and actuator faults. Cyber-physical systems are widely used in power system, aviation system and other practical systems. However, due to the openness of network communication channels, attackers are prone to transmitting incorrect data to controllers and actuators, resulting in unusable system states, which is a challenging problem to ensure system stability by only using the compromised s

关键词： Index Terms-Nonlinear cyber-physical systems deception attacks Nussbaum technology event-trigged mechanism actu-ator faults

来源：评论

学校读者我要写书评

暂无评论

Sharing Traffic Priorities via Cyber-Physical-Social Intelligence: A Lane-Free Autonomous Intersection management Method in Metaverse

引用

IEEE TRANSACTIONS ON systems MAN CYBERNETICS-systems 2023年第4期53卷 2025-2036页

作者： Li, Bai Cao, Dongpu Tang, Shiqi Zhang, Tantan Dong, Hairong Wang, Yaonan Wang, Fei-Yue Hunan Univ State Key Lab Adv Design & Mfg Vehicle Body Changsha 410082 Peoples R China Hunan Univ Coll Mech & Vehicle Engn Changsha 410082 Peoples R China Tsinghua Univ Sch Vehicle & Mobil Beijing 100084 Peoples R China Beihang Univ Sch Elect & Informat Engn Beijing 100191 Peoples R China Hunan Univ Coll Elect & Informat Engn Changsha 410082 Peoples R China Hunan Univ Natl Engn Lab Robot Visual Percept & Control Changsha 410082 Peoples R China Chinese Acad Sci Inst Automation State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

Replacing traffic signals with roadside vehicle-to-infrastructure systems in the era of connected and autonomous vehicles (CAVs) is promising. Managing CAVs in a signal-free intersection, known as autonomous intersection management (AIM), controls the driving behavior of each intersection-traverse CAV to maximize the throughput. Although AIM improves the gross throughput, the fairness of each individual vehicle in its right of way is not seriously considered. This study sets up an AIM system in the cyber-physical-social space to trade traverse priorities quantitatively and fairly. To that end, one needs an AIM method that is optimal and stable, otherwise no convincing trades of traverse priorities could be made. This study proposes a near-optimal lane-free AIM method based on numerical optimal control, wherein log-exp functions are deployed to convexify nondifferentiable collision-avoidance constraints. Besides that, a parameterized social force model (SFM) is proposed to provide a tunable initial guess for numerical optimal control. By tuning the urgency weights in SFM, one may get cooperative trajectories in different homotopy classes, which are further utilized to decide the amount of virtual currency to reward those CAVs who tend to share their traverse priorities. The overall method improves the traverse throughput with individual fairness respected. In experiencing this system, passengers learn how to behave with politeness when they drive manually. Experiments show the efficiency and robustness of the AIM method and also show the efficacy of the overall priority-sharing system.

关键词： Autonomous intersection management (AIM) cyber-physical-social intelligence metaverse numerical optimal control

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：