检索结果-内蒙古大学图书馆

2022 International Conference on Electronic information engineering and Computer Science, EIECS 2022

作者： Lu, Shengfu Yang, Chuang Li, Mi Kang, Jiaming Faculty of Information Technology Beijing University of Technology Beijing International Collaboration Base on Brain Informatics and Wisdom Services Engineering Research Center of Intelligent Perception and Autonomous Control Ministry of Education Beijing China Department of Automation Faculty of Information Technology Beijing University of Technology Beijing China Department of Automation Faculty of Information Technology Beijing China

ISBN: (纸本)9781510663312

Facial expression recognition has always been a focus of study in emotion computing. With the aim of solving the problem that previous facial expression recognition studies are susceptible to individual differences and background noise, as well as the loss of facial expression features in deep networks of deep convolutional networks, we propose a facial expression method based on convolutional difference contextual feature fusion. The convolutional difference module can carry out difference operation between emotional image and neutral image in the input image, eliminate individual difference and background noise in expression features and improve the accuracy and generalization of the network. Finally, convolutional difference and contextual features are combined to improve the accuracy of the network further. Experiment results of 4 public facial expression datasets illustrate that compared with the existing facial expression recognition methods, this method has higher accuracy, can extract facial expression features more effectively, and has a better generalization ability. © 2023 SPIE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

ReACT: Reinforcement Learning for controller Parametrization Using B-Spline Geometries

ReACT: Reinforcement Learning for Controller Parametrization...

引用

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Rudolf, Thomas Flögel, Daniel Schürmann, Tobias Süß, Simon Schwab, Stefan Hohmann, Sören FZI Research Center for Information Technology Embedded Systems and Sensors Engineering Department Karlsruhe76131 Germany Institute of Control Systems The Karlsruhe Institute of Technology Karlsruhe76131 Germany

ISBN: (纸本)9798350337020

Robust and performant controllers are essential for industrial applications. However, deriving controller parameters for complex and nonlinear systems is challenging and time-consuming. To facilitate automatic controller parametrization, this work presents a novel approach using deep reinforcement learning (DRL) with N-dimensional B-spline geometries (BSGs). We focus on the control of parameter-variant systems, a class of systems with complex behavior which depends on the operating conditions. For this system class, gain-scheduling control structures are widely used in applications across industries due to well-known design principles. Facilitating the expensive controller parametrization task regarding these control structures, we deploy an DRL agent. Based on control system observations, the agent autonomously decides how to adapt the controller parameters. We make the adaptation process more efficient by introducing BSGs to map the controller parameters which may depend on numerous operating conditions. To preprocess time-series data and extract a fixed-length feature vector, we use a long short-term memory (LSTM) neural networks. Furthermore, this work contributes actor regularizations that are relevant to real-world environments which differ from training. Accordingly, we apply dropout layer normalization to the actor and critic networks of the truncated quantile critic (TQC) algorithm. To show our approach's working principle and effectiveness, we train and evaluate the DRL agent on the parametrization task of an industrial control structure with parameter lookup tables. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sharing and Collaborating When Teaching Automatic control: An Experience-Based Needs Analysis 32

Sharing and Collaborating When Teaching Automatic Control: A...

引用

32nd Mediterranean Conference on control and Automation, MED 2024

作者： Knorn, Steffi Garone, Anja Varagnolo, Damiano Garone, Emanuele Technische Universität Department of Control Berlin Germany Brussels Institute for Advanced Studies Belgium Norwegian University of Science and Technology Department of Engineering Cybernetics Norway University of Padova Department of Information Engineering Italy Free University of Brussels Department of Automation and Systems Analysis Belgium

ISBN: (纸本)9798350395440

We discuss two specific issues that affected the workflows in our career as automatic control teachers and that are related to how teachers may establish teaching-oriented collaborations with colleagues from the same or different institutions. The first issue we identify is the systematic difficulty that one encounters when wanting to exchange instructional material with colleagues, while the second is the complexity of establishing students exchange programs across different institutions and nations. We discuss the nature and structure of the two problems, discuss why and how they are connected, and draw practical examples of how these problems may affect workflows. We then present a strategy that aims at solving these issues based on the introduction of an opportune indexing of instructional material in terms of contents and complexity of such contents, and how this information may be graphically displayed so to ease human and machine interpretability. We further discuss how this approach was used on a smaller scale to ease collaborations among close colleagues, and how it may be extended and adopted on a larger scale. © 2024 IEEE.

关键词： Process control

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Heterogeneous Green Vehicle Routing Problem with Customer Service Constraints 5

Multi-Objective Heterogeneous Green Vehicle Routing Problem ...

引用

5th International Conference on Robotics, Intelligent control and Artificial Intelligence, RICAI 2023

作者： Meng, Xianghu Gao, Wei Tang, Jing Anhui University of Technology Anhui Provincial Key Laboratory of Power Electronics and Motion Control Maanshan China Anhui University of Technology Department of Electrical and Information Engineering Maanshan China

ISBN: (纸本)9798350357950

Green Vehicle Routing Problem (GVRP) is a hot topic in the field of combinatorial optimization. In this paper, Multi-Objective Heterogeneous Green Vehicle Routing Problem with Customer Service Constraints (MOHGVRP-CSC) is proposed for the first time, and an integer planning model is established with three objectives to minimize the total traveling costs of vehicles, Carbon Emission cost and Customer Satisfaction cost. Then, a Hybrid Variable Neighborhood Search (HVNS) with hierarchical clustering and Brain Storm Optimization (BSO) is proposed. At the initial stage of the algorithm, the initial solution is constructed by hierarchical clustering algorithm and greedy algorithm. In addition, BSO is introduced into the global search of VNS to obtain a wider range of neighborhood searches. At the same time, 2-opt method is adopted in the local search to further improve the solution quality. Finally, the effectiveness of the proposed algorithm is verified by a large number of experimental simulations. © 2023 IEEE.

关键词： Customer service restrictions Green vehicle routing problem Multi-objective VNS

来源：评论

学校读者我要写书评

暂无评论

Integrated Path Tracking, and control of a Fixed Wing UAV based on Dual Quaternion Parameterized Dynamics

Integrated Path Tracking, and Control of a Fixed Wing UAV ba...

引用

Proceedings of the International Convention MIPRO

作者： Stephen Kimathi Bela Lantos Department of Control Engineering and Information Technology Budapest University of Technology and Economics Budapest Hungary

ISBN: (数字)9798350382501

ISBN: (纸本)9798350382518

Based on the dual quaternion formalism, the dynamics of a fixed wing UAV are formulated for path tracking, by incorporating the nonlinear gyroscopic terms. A control strategy is developed by exploiting the logarithmic map of the unit dual quaternion so as to ensure asymptotic stability in the three-dimensional space. The control and stabilization of the UAV, is carried out using dual quaternion parameterized dynamics such that a state feedback control law comprising of a PD controller ensures the simultaneous attitude and position tracking. Simulation results are presented to illustrate the applicability of this integrated approach in the tracking of a three-directional path.

关键词： State feedback Asymptotic stability Attitude control Quaternions Simulation Aerospace electronics Autonomous aerial vehicles

来源：评论

学校读者我要写书评

暂无评论

Robust Adaptive Formation control of Fixed Wing UAVs Using Disturbance Estimators

Robust Adaptive Formation Control of Fixed Wing UAVs Using D...

引用

International Symposium on Computational Intelligence and Informatics

作者： Stephen Kimathi Bela Lantos Department of Control Engineering and Information Technology Budapest University of Technology and Economics Budapest Hungary

ISBN: (数字)9798350353433

ISBN: (纸本)9798350353440

This paper presents the formation control of multiple homogeneous fixed-wing unmanned aerial vehicles subjected to parameter perturbations and external disturbances. A leader-follower with virtual leader formation architecture is used, and the communication between the vehicles is modelled using a directed graph. A distributed model reference adaptive control strategy is used for the formation acquisition and maintenance. The robustification of the control is achieved using a disturbance estimator developed to estimate and cancel out the effect of the disturbances on the dynamic model. In this formulation, the designed control law does not require any information about the magnitude of the disturbance, or derivative of the states. The simulation results validate the effectiveness of the proposed control strategy.

关键词： Adaptation models Uncertain systems Simulation Perturbation methods Directed graphs Computer architecture Formation control Topology Adaptive control Vehicle dynamics

来源：评论

学校读者我要写书评

暂无评论

Simultaneous attitude and position tracking using dual quaternion parameterized dynamics

Simultaneous attitude and position tracking using dual quate...

引用

International Symposium on Applied Machine Intelligence and Informatics (SAMI)

作者： Stephen Kimathi Bela Lantos Department of Control Engineering and Information Technology Budapest University of Technology and Economics Budapest Hungary

This paper presents the simultaneous attitude and position control of rigid bodies using the unit dual quaternion. A dual quaternion is a compound of a unit quaternion and a translational vector, using the dual number formalization, such that the real part represents the rotation and the dual part, the translation transformation. Since the unit dual quaternion can be used to represent the rigid body dynamics in the 3D space, then the error dual quaternion can be used to design feedback control laws for both set-point stabilization, and attitude and position tracking. Simulation results using a rigid-body model are presented to show the performance of the dual quaternion formalism for simultaneous attitude and position control.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimizing Electric Vehicle Charging considering Driver Satisfaction with Market Integration

Optimizing Electric Vehicle Charging considering Driver Sati...

引用

International Youth Conference on Energetics (IYCE)

作者： Shahab Sabzi László Vajta Department of Control Engineering and Information Technology Budapest University of Technology and Economics Budapest Hungary

ISBN: (数字)9798350372380

ISBN: (纸本)9798350372397

This paper presents a smart charging strategy for electric vehicles (EVs) by prioritizing driver satisfaction while integrating local electricity markets (LEMs). By developing the new optimization algorithm, we incorporate socio-demographic factors and real-time data to align EV charging schedules with market signals. This approach maximizes driver satisfaction while minimizing energy costs, transforming EVs into flexible resources that support grid management. The proposed method leverages advanced machine learning techniques to predict optimal charging scenarios, balancing the demands of EV drivers and grid requirements. Simulation results demonstrate significant improvements in driver satisfaction and achieving grid efficiency, highlighting the dual benefits of enhanced user experience and operational dynamics within LEMs. This integration not only supports renewable energy integration but also provides substantial economic benefits, illustrating the potential for EVs to act as dynamic components of a resilient and sustainable energy system.

关键词： Schedules Renewable energy sources Simulation Machine learning Electricity supply industry User experience Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Al-Biruni Earth Radius Optimization for COVID-19 Forecasting

引用

Computer Systems Science & engineering 2023年第7期46卷 883-896页

作者： El-Sayed M.El-kenawy Abdelaziz A.Abdelhamid Abdelhameed Ibrahim Mostafa Abotaleb Tatiana Makarovskikh Amal H.Alharbi Doaa Sami Khafaga Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt Department of Computer Science Faculty of Computer and Information SciencesAin Shams University11566CairoEgypt Department of Computer Science College of Computing and Information TechnologyShaqra University11961Saudi Arabia Computer Engineering and Control Systems Department Faculty of EngineeringMansoura University35516MansouraEgypt Department of System Programming South Ural State University454080ChelyabinskRussia Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia

Several instances of pneumonia with no clear etiology were recorded in Wuhan,China,on December 31,*** world health organization(WHO)called it COVID-19 that stands for“Coronavirus Disease 2019,”which is the second version of the previously known severe acute respiratory syndrome(SARS)Coronavirus and identified in short as(SARSCoV-2).There have been regular restrictions to avoid the infection spread in all countries,including Saudi *** prediction of new cases of infections is crucial for authorities to get ready for early handling of the virus ***:Analysis and forecasting of epidemic patterns in new SARSCoV-2 positive patients are presented in this research using metaheuristic optimization and long short-term memory(LSTM).The optimization method employed for optimizing the parameters of LSTM is Al-Biruni Earth Radius(BER)***:To evaluate the effectiveness of the proposed methodology,a dataset is collected based on the recorded cases in Saudi Arabia between March 7^(th),2020 and July 13^(th),*** addition,six regression models were included in the conducted experiments to show the effectiveness and superiority of the proposed *** achieved results show that the proposed approach could reduce the mean square error(MSE),mean absolute error(MAE),and R^(2)by 5.92%,3.66%,and 39.44%,respectively,when compared with the six base *** the other hand,a statistical analysis is performed to measure the significance of the proposed ***:The achieved results confirm the effectiveness,superiority,and significance of the proposed approach in predicting the infection cases of COVID-19.

关键词： COVID-19 prediction meta-heuristic optimization LSTM Al-Biruni earth radius algorithm

来源：评论

学校读者我要写书评

暂无评论

Subdivision of Nonlinear Systems into LPV and Uncertain Linear Subsystems for Robust control

Subdivision of Nonlinear Systems into LPV and Uncertain Line...

引用

International Conference on control, Decision and information Technologies (CoDIT)

作者： Zoltán Téczely Bálint Kiss Department of Control Engineering and Information Technology Budapest University of Technology and Economics Budapest Hungary

ISBN: (数字)9798350373974

ISBN: (纸本)9798350373981

This paper presents a novel approach for the subdivision of the parameter space in an LPV control framework. The least appealing characteristic of LPV controller design is the conservative nature of the synthesis suggesting a robustness-inclined overtone albeit handling of nonlinear systems by LPV is proven to be efficient with a moderately high performance level. As a possible remedy, parameter-space subdivision is a standard way of concentrating control effort more suited to the specific operating region in which the system resides. LPV, in the overwhelming majority of cases, is utilized either in the name of nonlinearity inherent in the controlled system or as a method for linear systems in which parameters are uncertain. This paper is an effort to combine these ideas in the polytopic LPV framework. First, the parameter-space division lines are drawn according to the presumed evolution of the scheduling variable. A subset of the parameter region is known a priori to behave ’close’ to linear, that is, in a certain range, any deviation from linear behaviour is handled as a parameter uncertainty and the system is controlled by regular linear controllers whereas in other regions an obvious nonlinearity is present motivating the utilization of LPV controllers. These subsegments are then blended in a way that any guaranteed characteristics of the individual controllers are maintained. The proposed approach is demonstrated on a simple torque-controlled pendulum example in a simulation environment.

关键词： Robust control Linear systems Uncertain systems Layout Switches Aerospace electronics control systems Logic Nonlinear systems Standards

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：