检索结果-内蒙古大学图书馆

27th International Conference on Automation, AUTOMATION 2023

作者： Oprzędkiewicz, Krzysztof Department of Automatic Control and Robotics Faculty of Electrical Engineering Automatic Control Informatics and Biomedical Engineering AGH University of Science and Technology al. A Mickiewicza 30 Krakow30-059 Poland

ISBN: (纸本)9783031258435

In the paper the numerical estimation of the internal positivity of the model of a two dimensional heat transfer process is addressed. The considered thermal process is described by the fractional order state equation, derived from parabolic heat equation with homogenous Neumann boundary conditions and distributed control and observation. Two numerical algorithms of the positivity testing are proposed and compared. The first one consists in the full examination of the whole area. The next one uses Monte Carlo method. From tests it can be concluded that the considered model can be internally positive only for its lower orders and heating and measurements located closely to the corner of the tested area. The use of the Monte Carlo method allows to significantly shorten the duration of computations. The presented results can be useful in measurements using a thermal camera. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Fractional order system Monte Carlo method Positivity Thermal camera

来源：评论

学校读者我要写书评

暂无评论

Policy Transfer with Maximum Entropy Deep Reinforcement Learning for Real Cart-Pole control 20

Policy Transfer with Maximum Entropy Deep Reinforcement Lear...

引用

20th IEEE International Conference on Intelligent Computer Communication and Processing Conference, ICCP 2024

作者： Paleu, Tudor-Andrei Burlacu, Adrian Pascal, Carlos Gheorghe Asachi Technical University of Iasi Department of Automatic Control and Applied Informatics D. Mangeron 27 Iasi700050 Romania

ISBN: (纸本)9798331539979

Transferring learned controllers from simulation to real-world domains is rarely observed for deep reinforcement learning applications, even physics-based tasks like the inverted pendulum being particularly difficult when transitioning to the physical world. Model-free controllers based on deep reinforcement learning have been a successful choice for many tasks. They are preferred over model-based ones due to their adaptive capability to situations not included in the initial design and for requiring less advanced expertise in control. This paper aims to apply learning-based model-free control to a real cart-pole system using a deep reinforcement learning policy transferred from simulation to a real environment without any fine-tuning involved with the dynamics model. In a simulation, the baseline deep Q-learning, an off-policy model-free algorithm, delivered an inferior performance on the Cart-Pole environment compared to the soft Q-learning, keeping the same hyper-parameters and ensuring reproducible outcomes. In the real experimental setup, besides a PD controller feasible for under-actuated systems, the soft version policy was transferred to accelerate the design process and enhance the control. Additionally, limitations related to the brittle robustness of PD controllers and the absence of accurate models in the learning phase are studied and addressed. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Validation of Real-world Measurements Through Ray Tracing Simulation for 5G Urban Scenarios 16

Validation of Real-world Measurements Through Ray Tracing Si...

引用

16th International Symposium on Electronics and Telecommunications, ISETC 2024

作者： Militaru, Andreea V. Lazar, Razvan G. Pascal, Carlos Comsa, Ciprian R. Bogdan, Ion Caruntu, Constantin F. Telecommunications and Information Technology Department of Electronics Romania Gheorghe Asachi Technical University of Iasi Department of Automatic Control and Applied Informatics Iasi Romania

ISBN: (纸本)9798350390865

This paper presents an approach to validate ray tracing simulations using real-world measurements in 5G urban scenarios. The measurements were obtained by traversing specific routes and recording parameters such as position, Signal-to-Interference-plus-Noise Ratio (SINR), Reference Signal Received Power (RSRP), and Reference Signal Received Quality (RSRQ) using the Quectel RM500Q 5G module as user equipment (UE). Subsequently, these real-world measurements are used to validate a MATLAB-based ray tracing simulation. Simulating such scenarios in a controlled environment allows for easy manipulation and study of various parameters, enabling compre-hensive verification of the simulator's accuracy. The advantage of this approach lies in its ability to ensure the reliability of the simulation tool, enabling robust testing of diverse scenarios and parameters for deployments in real-world use cases. © 2024 IEEE.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

Learning control laws in simulated environments for motion gestures of humanoid robots 24

Learning control laws in simulated environments for motion g...

引用

24th International Conference on control Systems and Computer Science, CSCS 2023

作者： Mateescu, Andrei Stefan, Ioana-Livia Popescu, Dragos Constantin Sacala, Ioan Stefan Raileanu, Silviu University Politehnica of Bucharest Automatic Control and Systems Engineering Faculty of Automatic Control and Computers Splaiul Independentei No. 313 Bucharest060042 Romania University Politehnica of Bucharest Automation and Industrial Informatics Faculty of Automatic Control and Computers Splaiul Independentei No. 313 Bucharest060042 Romania

ISBN: (纸本)9798350313390

This article presents a way to implement a collection of fitness moves on an iCub (Cognitive Universal Body) robot, whose objective is to act as a fitness instructor and interact with humans. Due to the advantages of a simulation medium, the robot is simulated in the Gazebo simulator, on The Construct online platform. The control is done using Robot Operating System (ROS) with PID controllers for the robot joints, with the proportional, integral and derivative parameters tuned using a Genetic Algorithm. The scripts for the collection of moves and the algorithm used to tune the PID controllers are written in Python. © 2023 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Constrained Predictive Current control in dq Frame for a Permanent Magnet Synchronous Machine 28

Constrained Predictive Current Control in dq Frame for a Per...

引用

28th IEEE International Conference on Emerging Technologies and Factory Automation, ETFA 2023

作者： Costin, Madalin Lazar, Corneliu Gheorghe Asachi Technical University of Iasi Dept.of Automatic Control and Applied Informatics Iasi Romania Dunarea de Jos University of Galati Dept. of Automatic Control and Electrical Engineering Galati Romania

ISBN: (纸本)9798350339918

In the paper, the design and Simulink implementation of a predictive current control structure in dq frame for a permanent magnet synchronous machine (PMSM) are presented. Starting from the multivariable model of the currents in the dq reference frame, first it is decoupled and through the rejection of the disturbance introduced by the back-EMF, two single-input single-output (SISO) systems result whose dynamics are generated by R-L circuits. For these SISO systems, the model predictive control (MPC) algorithms are designed that allow the consideration of physical limitations through constraints The performances of the current control structure with MPC algorithms are compared with those obtained with the conventional PI controllers. © 2023 IEEE.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Pneumonia Detection Using Federated Learning 24

Pneumonia Detection Using Federated Learning

引用

24th International Conference on control Systems and Computer Science, CSCS 2023

作者： Farkas, Camelia-Raluca Ciobanu, Radu-Ioan Dobre, Ciprian University Politehnica of Bucharest Faculty of Automatic Control and Computers Romania National Institute for Research and Development in Informatics Bucharest Romania

ISBN: (纸本)9798350313390

Pneumonia is a major cause of illness and death among older adults, and hospitalization rates for pneumonia in patients aged 65 and older have been increasing. However, detecting pneumonia automatically is challenging because it requires large amounts of data from many patients, making traditional machine learning solutions impractical in real life, despite the good results they can achieve. To address this issue, our paper focuses on using federated learning, a new method for applying machine learning techniques in a distributed environment while maintaining patients' privacy and reducing communication and storage overhead at the processing servers. We propose a federated learning system that can analyze X-rays of patients with and without pneumonia, present our approach, and demonstrate promising results. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Learning-Based Methodology for Detection of Postural Anomalies in Wheelchair Users

Unsupervised Learning-Based Methodology for Detection of Pos...

引用

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

作者： Vermander, Patrick Mancisidor, Aitziber Fortino, Giancarlo Cabanes, Itziar Gravina, Raffaele Department of Automatic Control and System Engineering Bilbao Spain Department of Informatics Modeling Electronics and Systems Engineering Rende Italy

ISBN: (纸本)9798350337020

Postural monitoring in wheelchair users is a topic of growing interest. The detection of changes in the sitting patterns of these patients may serve to detect changes in their functional status and be able to adapt rehabilitation early. For this reason, this paper presents a methodology for the detection of specific postural anomalies that, unlike previous works, adopts unsupervised learning. The proposed methodology involves data dimensionality reduction using Principal Component Analysis, and the application of K-means clustering to group different normal posture states. The anomalies are detected using a threshold approach, where data points that fall outside a certain threshold are considered as anomalies. The results show that the methodology is effective in identifying anomalies with a high degree of accuracy (around 90%). © 2023 IEEE.

关键词： Anomaly detection Kmeans PCA Postural monitoring Wheelchair

来源：评论

学校读者我要写书评

暂无评论

Investigation of the temperature impact on the operation of a nonlinear electromagnetic vibration energy harvester

引用

Bulletin of the Polish Academy of Sciences: Technical Sciences 2025年第3期73卷

作者： Kulik, Marcin Gabor, Rafal Opole University of Technology Faculty of Electrical Engineering Automatic Control and Informatics Opole Poland

This paper presents a detailed study of the impact of temperature on the performance of a nonlinear electromagnetic vibration energy harvester, which is applied in autonomous power systems. The variability of material properties under the influence of temperature, such as stiffness, damping, and magnetic induction, significantly affects the operational characteristics of the device. A mathematical model accounting for these factors, including linear and quadratic temperature coefficients, optimized using a genetic algorithm, is presented in the article. The simulation results were compared with experimental data, showing good agreement, particularly in the range of frequency bandwidth and output voltage. It was demonstrated that higher temperatures lead to a reduction in mechanical and magnetic stiffness, resulting in decreased energy conversion efficiency. © 2025 The Author(s).

关键词： Vibration analysis

来源：评论

学校读者我要写书评

暂无评论

TA-DA: Topic-Aware Domain Adaptation for Scientific Keyphrase Identification and Classification 37

TA-DA: Topic-Aware Domain Adaptation for Scientific Keyphras...

引用

37th AAAI Conference on Artificial Intelligence, AAAI 2023

作者： Smădu, Răzvan-Alexandru Zaharia, George-Eduard Avram, Andrei-Marius Cercel, Dumitru-Clementin Dascalu, Mihai Pop, Florin Faculty of Automatic Control and Computers University Politehnica of Bucharest Romania National Institute for Research and Development in Informatics - ICI Bucharest Romania

ISBN: (纸本)9781577358800

Keyphrase identification and classification is a Natural Language Processing and Information Retrieval task that involves extracting relevant groups of words from a given text related to the main topic. In this work, we focus on extracting keyphrases from scientific documents. We introduce TA-DA, a Topic-Aware Domain Adaptation framework for keyphrase extraction that integrates Multi-Task Learning with Adversarial Training and Domain Adaptation. Our approach improves performance over baseline models by up to 5% in the exact match of the F1-score. Copyright © 2023, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Evaluating the usage of Text to3D scene generation methods in Game-Based Learning 24

Evaluating the usage of Text to3D scene generation methods i...

引用

24th International Conference on control Systems and Computer Science, CSCS 2023

作者： Gradinaru, Alexandru Vrejoiu, Mihnea Moldoveanu, Florica Balutoiu, Maria-Anca University Politehnica of Bucharest Faculty of Automatic Control and Computer Science Bucharest Romania National Institute for Research and Development in Informatics Bucharest Romania

ISBN: (纸本)9798350313390

Computer games as an educational tool significantly improved information retention, student involvement, and motivation. Despite the growing popularity and the demonstrated positive impact, little progress is made to let educators create games without learning game programming or investing massive amounts of time, money, and human resources. This paper considers the usage of procedural content generation in simplifying the generation of game environments. Given that most educational material is in text format, we evaluate the possibility of generating 3D scenes starting from natural language text. A comprehensive survey of the current methods is presented, analyzing whether they can be successfully used in game-based learning. The study discusses several current limitations and possible improvements, highlighting a need for better progress in the domain. © 2023 IEEE.

关键词： Computer games

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：