检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： Weili Guo Liping Xie Zhenyong Fu Jianhui Guo Guochen Pang Jian Yang PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Nanjing University of Science and Technology Nanjing P.R. China Key Laboratory of Measurement and Control of CSE Ministry of Education School of Automation Southeast University Nanjing P.R. China School of Automation and Electrical Engineering Linyi University Linyi P.R. China

ISBN: (数字)9781728169262

ISBN: (纸本)9781728169279

For the widely used multilayer perceptrons (MLPs), the existed singularities in the parameter space have seriously affected the learning dynamics of MLPs, which cause several singular learning behaviors. Since the Fisher information matrix (FIM) plays a significant role in analyzing the singular learning dyanmics of MLPs, it is very worthy to obtain the analytical form of FIM to do further investigation. In this paper, by choosing the bipolar error function as the activation function, the analytical form of FIM are obtained, where the validity of the obtained results are verified by taking three experiments.

关键词： Training Analytical models Multilayer perceptrons Indexes Mathematical model Standards

来源：评论

学校读者我要写书评

暂无评论

Adaptive tracking a linear system with unknown periodic signal in multi-agent systems

Adaptive tracking a linear system with unknown periodic sign...

引用

Chinese Intelligent systems Conference, CISC 2017

作者： Li, Feifei Zhang, Ya School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China

ISBN: (纸本)9789811064982

This paper studies the tracking control problem of multi-agent systems where each agent has homogeneous sensor and heterogeneous dynamic system, the moving target has unknown periodic input signal and the unknown periodic input can be modelled as a finite dimensional Fourier decomposition. Since some agents can not detect the target, a distributed estimation based tracking control algorithm is applied. We first design a consensus based distributed observer to estimate the state and the unknown periodic input of the system from the available measurement outputs. Leader-follower consensus protocol is applied, and the stability condition of the estimation errors is given. Then, based on the estimations, a model reference adaptive control (MRAC) algorithm is adopted to design the tracking controller. It is proved that under the proposed distributed estimation based tracking control algorithm, each agent can asymptotically track the target. A numerical simulation is given to prove the feasibility of the algorithm in this paper. © 2018, Springer Nature Singapore Pte Ltd.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Position tracking control of magnetic levitation system based on continuous sliding mode control*

Position tracking control of magnetic levitation system base...

引用

Chinese Automation Congress (CAC)

作者： Lei Zhao Linjie Chen Junxiao Wang Li Yu College of Information Zhejiang University of Technology Hangzhou China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Southeast University Nanjing Chian

In this paper, aiming at the problem of position tracking control of magnetic levitation system under parameter uncertainties and unknown external disturbance, a continuous sliding mode control(CSMC) method based on extended state observer(ESO) is proposed. Firstly, in order to suppress the adverse effects of disturbance and system unmeasurable states on control performance, an ESO for the system was designed to estimate system disturbances and unmeasured states. Meanwhile, in order to improve the robustness of the system and eliminate the chattering phenomenon caused by the high-frequency switching function in the sliding mode control law, a position tracking controller based on continuous sliding mode control is designed. Then combined with disturbance estimation technology and continuous sliding mode control technology, a composite position tracking controller(CSMC+ESO) is designed for the magnetic levitation system. Simulation and experimental results shows that compared with the general continuous sliding mode control(CSMC), the proposed control method improves the tracking accuracy, convergence rate, obtain better anti-interference capability and noise filtering performance for control input.

关键词： Magnetic levitation Observers Sliding mode control Mathematical model Uncertain systems Robustness

来源：评论

学校读者我要写书评

暂无评论

A Driver Fatigue Recognition Algorithm Based on Spatio-Temporal Feature Sequence

A Driver Fatigue Recognition Algorithm Based on Spatio-Tempo...

引用

International Congress on Image and Signal Processing, BioMedical engineering and Informatics

作者： Chen Zhang Xiaobo Lu Zhiliang Huang Shudong Xia Changqing Fu Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing China Beijing PKU TransInfo Technology Co. Ltd Beijing China

Researches show that fatigue driving is one of the important causes of road traffic accidents, so it is of great significance to study the driver fatigue recognition algorithm to improve road traffic safety. In recent years, with the development of deep learning, the field of pattern recognition has made great development. This paper designs a real-time fatigue state recognition algorithm based on spatio-temporal feature sequence, which can be mainly applied to the scene of fatigue driving recognition. The algorithm is divided into three task networks: face detection network, facial landmark detection and head pose estimation network, fatigue recognition network. Experiments show that the algorithm has the advantages of small volume, high speed and high accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ellipsoidal bounding set-membership identification approach for robust fault diagnosis with application to mobile robots

引用

Journal of systems engineering and Electronics 2017年第5期28卷 986-995页

作者： Bo Zhou Kun Qian Xudong Ma Xianzhong Dai School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education

A robust fault diagnosis approach is developed by incorporating a set-membership identification (SMI) method. A class of systems with linear models in the form of fault related parameters is investigated, with model uncertainties and parameter variations taken into account explicitly and treated as bounded errors. An ellipsoid bounding set-membership identification algorithm is proposed to propagate bounded uncertainties rigorously and the guaranteed feasible set of faults parameters enveloping true parameter values is given. Faults arised from abrupt parameter variations can be detected and isolated on-line by consistency check between predicted and observed parameter sets obtained in the identification procedure. The proposed approach provides the improved robustness with its ability to distinguish real faults from model uncertainties, which comes with the inherent guaranteed robustness of the set-membership framework. Efforts are also made in this work to balance between conservativeness and computation complexity of the overall algorithm. Simulation results for the mobile robot with several slipping faults scenarios demonstrate the correctness of the proposed approach for faults detection and isolation (FDI).

关键词： set-membership identification fault diagnosis fault detection and isolation (FDI) bounded error mobile robot

来源：评论

学校读者我要写书评

暂无评论

Copy and Paste GAN: Face Hallucination From Shaded Thumbnails

Copy and Paste GAN: Face Hallucination From Shaded Thumbnail...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yang Zhang Ivor W. Tsang Yawei Luo Chang-Hui Hu Xiaobo Lu Xin Yu School of Automation Southeast University China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University China Centre for Artificial Intelligence University of Technology Sydney Australia School of Computer Science and Technology Huazhong University of Science and Technology China Southeast University Nanjing China Australian Centre for Robotic Vision Australian National University Australia

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

Existing face hallucination methods based on convolutional neural networks (CNN) have achieved impressive performance on low-resolution (LR) faces in a normal illumination condition. However, their performance degrades dramatically when LR faces are captured in low or non-uniform illumination conditions. This paper proposes a Copy and Paste Generative Adversarial Network (CPGAN) to recover authentic high-resolution (HR) face images while compensating for low and non-uniform illumination. To this end, we develop two key components in our CPGAN: internal and external Copy and Paste nets (CPnets). Specifically, our internal CPnet exploits facial information residing in the input image to enhance facial details; while our external CPnet leverages an external HR face for illumination compensation. A new illumination compensation loss is thus developed to capture illumination from the external guided face image effectively. Furthermore, our method offsets illumination and upsamples facial details alternatively in a coarse-to-fine fashion, thus alleviating the correspondence ambiguity between LR inputs and external HR inputs. Extensive experiments demonstrate that our method manifests authentic HR face images in a uniform illumination condition and outperforms state-of-the-art methods qualitatively and quantitatively.

关键词： Face Lighting Gallium nitride Image resolution Feature extraction Generative adversarial networks Automation

来源：评论

学校读者我要写书评

暂无评论

Observer-Based Adaptive Multi-dimensional Taylor Network control for Nonlinear systems with Time-Delay

Observer-Based Adaptive Multi-dimensional Taylor Network Con...

引用

Data Driven control and Learning systems (DDCLS)

作者： Lei Chu Shuhua Zhang Mingxin Wang Shanliang Zhu Yuqun Han School of Mathematics and Physics Qingdao University of Science and Technology Qingdao P. R. China The Research Institute for Mathematics and Interdisciplinary Sciences Qingdao University of Science and Technology Qingdao China College of Electromechanical Engineering Qingdao University of Science and Technology Qingdao P. R. China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing P. R. China

ISBN: (数字)9781728159225

ISBN: (纸本)9781728159232

In this paper, an observer-based adaptive Multi-dimensional Taylor network (MTN) controller is proposed for strictly feedback nonlinear systems with time-delay and unmeasurable states. MTNs are utilized to approximate the unknown and desired control input signals directly instead of the unknown nonlinear functions. Moreover, a linear state observer is designed for estimating the unmeasured states. Based on the backstepping technique, a novel adaptive MTN control strategy with simple structure and good real time property is proposed. The designed controller can guarantee all the signals of the closed-loop system are bounded and the tracking error converges to a small neighborhood of the origin. Simulation results are given to demonstrate the effectiveness of the proposed method.

关键词： Nonlinear systems Backstepping Observers Closed loop systems Artificial neural networks Adaptive control Stability analysis

来源：评论

学校读者我要写书评

暂无评论

Copy and paste GAN: Face hallucination from shaded thumbnails

arXiv

引用

arXiv 2020年

作者： Zhang, Yang Tsang, Ivor W. Luo, Yawei Hu, Changhui Lu, Xiaobo Yu, Xin School of Automation Southeast University China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University China Centre for Artificial Intelligence University of Technology Sydney Australia School of Computer Science and Technology Huazhong University of Science and Technology China School of Automation Nanjing University of Posts and Telecommunications China Australian Centre for Robotic Vision Australian National University Australia

Existing face hallucination methods based on convolutional neural networks (CNN) have achieved impressive performance on low-resolution (LR) faces in a normal illumination condition. However, their performance degrades dramatically when LR faces are captured in low or non-uniform illumination conditions. This paper proposes a Copy and Paste Generative Adversarial Network (CPGAN) to recover authentic high-resolution (HR) face images while compensating for low and nonuniform illumination. To this end, we develop two key components in our CPGAN: internal and external Copy and Paste nets (CPnets). Specifically, our internal CPnet exploits facial information residing in the input image to enhance facial details;while our external CPnet leverages an external HR face for illumination compensation. A new illumination compensation loss is thus developed to capture illumination from the external guided face image effectively. Furthermore, our method offsets illumination and upsamples facial details alternately in a coarse-to-fine fashion, thus alleviating the correspondence ambiguity between LR inputs and external HR inputs. Extensive experiments demonstrate that our method manifests authentic HR face images in a uniform illumination condition and outperforms state-of-the-art methods qualitatively and quantitatively. Copyright © 2020, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Strategy via Reinforcement Learning for the Prisoner＇s Dilemma Game

引用

IEEE/CAA Journal of Automatica Sinica 2018年第1期5卷 301-310页

作者： Lei Xue Changyin Sun Donald Wunsch Yingjiang Zhou Fang Yu Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Southeast University Nanjing 210096 China Department of Electrical and Computer Engineering Missouri University of Science and Technology Rolla MO 65409 USA College of Automation Nanjing University of Posts and Telecommunications Nanjing 210023 China Institute of Logistics Science and Engineering Shanghai Maritime University Shanghai 210096 China IEEE

The iterated prisoner's dilemma(IPD) is an ideal model for analyzing interactions between agents in complex networks. It has attracted wide interest in the development of novel strategies since the success of tit-for-tat in Axelrod's tournament. This paper studies a new adaptive strategy of IPD in different complex networks, where agents can learn and adapt their strategies through reinforcement learning method. A temporal difference learning method is applied for designing the adaptive strategy to optimize the decision making process of the agents. Previous studies indicated that mutual cooperation is hard to emerge in the IPD. Therefore, three examples which based on square lattice network and scale-free network are provided to show two features of the adaptive strategy. First, the mutual cooperation can be achieved by the group with adaptive agents under scale-free network, and once evolution has converged mutual cooperation, it is unlikely to shift. Secondly, the adaptive strategy can earn a better payoff compared with other strategies in the square network. The analytical properties are discussed for verifying evolutionary stability of the adaptive strategy.

关键词： complex network prisoner’s dilemma reinforcement learning temporal differences learning

来源：评论

学校读者我要写书评

暂无评论

Disturbance rejection control for Raymond mill grinding system based on disturbance observer

引用

Journal of Central South University 2017年第9期24卷 2019-2027页

作者：牛丹陈夕松杨俊周杏鹏 Key Laboratory of Measurement and Control of Complex Systems of Engineering of Ministry of Education School of AutomationSoutheast UniversityNanjing 210096China

In the Raymond mill grinding processes,high-accuracy control for the current of Raymond mill is vital to enhance the product quality and production efficiency as well as cut down the consumption of spare ***,strong external disturbances,such as variations of ore hardness and ore size,always *** is not easy to make the current of Raymond mill constant due to these strong *** control strategies have been proposed to control the grinding ***,most of them(such as PID and MPC)reject disturbances merely through feedback regulation and do not deal with the disturbances directly,which may lead to poor control performance when strong disturbances *** improve disturbance rejection performance,a control scheme based on PI and disturbance observer is proposed in this *** scheme combines a feedforward compensation part based on disturbance observer and a feedback regulation part using *** test results illustrate that the proposed method can obtain remarkable superiority in disturbance rejection compared with PI method in the Raymond mill grinding processes.

关键词： disturbance observer proportional integral-disturbance observer （PI-DOB） disturbance rejection Raymond mill grinding process

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：