检索结果-内蒙古大学图书馆

Signal Processing Algorithms, Architectures, Arrangements and Applications (SPA)

作者： Tomasz Marciniak Agnieszka Stankiewicz Przemysław Zaradzki Department of Control Robotics and Electrical Engineering Division of Electronic Systems and Signal Processing Institute of Automatic Control and Robotics Poznan University of Technology Poznan Poland

This paper presents an analysis of the effectiveness of blood vessel segmentation in human retinal images. The segmentation process was carried out for three-dimensional optical coherence tomography (OCT) scans using the author’s publicly available CAVRI-C database. A 3D version of the U-Net artificial neural network was used. Various dimensions of the input blocks were investigated to determine their influence on the segmentation process. The effectiveness of the proposed solutions was evaluated using various metrics and the results obtained were compared with the 2D solution, also based on neural networks. The use of the proposed solutions allowed us to improve the segmentation even by 15% (in the case of the F1-score).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reliability Improvement Method for Precision Micro and Special Motors Based on Response Surface Methodology 14

Reliability Improvement Method for Precision Micro and Speci...

引用

14th International Conference on Reliability, Maintainability and Safety, ICRMS 2023

作者： Xu, Hongwu Fu, Liping Xiang, Gang Peng, Yu Pan, Weidi Wu, Heyuan Aerospace Product Engineering Research Institute China Academy of Aerospace Standardization and Product Assurance Beijing China China Aerospace Science and Technology Corporation Beijing China National Key Laboratory on Aerospace Intelligent Control Beijing Aerospace Automatic Control Institute Beijing China Engineering Technology Department Guizhou Aerospace Linquan Motor Control Ltd. GuiYang China

ISBN: (纸本)9798350329988

Currently, precision micro and special motors are essential basic products in the industry. They are key components widely used in platforms such as aerospace, aircraft, automobiles, and unmanned intelligence. This paper proposes a reliability improvement method for precision micro and special motors based on a response surface methodology. Firstly, we identify key design parameters that affect motor performance through sensitivity analysis methods. Then, the key design parameters are evenly divided into a 5x5 matrix. We conduct 100 Monte Carlo simulation analyses per group and obtain the probability density function of motor speed. Finally, a response surface functional relationship between reliability and key design parameters is established. The values of key design parameters corresponding to the maximum reliability are calculated and used to improve the reliability of the motor. © 2023 IEEE.

关键词： precision micro andspecialmotors reliability response surface sensitivity

来源：评论

学校读者我要写书评

暂无评论

Narrow gap TIG arc weld process monitoring 27

Narrow gap TIG arc weld process monitoring

引用

27th International Conference on Automation and Computing, ICAC 2022

作者： Gambrill, Nathan Farnsworth, Michael Shaw, Rob Tedeschi, Stefano Tiwari, Divya Tiwari, Ashutosh The University of Sheffield Department of Automatic Control and Systems Engineering Sheffield United Kingdom The Welding Institute Ltd Abington Cambridge United Kingdom

ISBN: (数字)9781665498074

ISBN: (纸本)9781665498074

Joining processes play a critical role across several industries and manufacturing activities. One such activity is narrow gap TIG arc welding, present in a number of high value manufacturing domains the quality and outcomes are highly dependent on the operating parameters and the evolving state of the weld. Human supervision, and the application of vision systems to allow the operator to monitor the process as it is being undertaken is commonplace, however monitoring, characterisation and feedback in narrow gap use cases is less so. The work undertakes a comparative study into two different approaches to process monitoring of TIG arc welding. The first through more traditional machine vision (MV) methods, and the second through more modern deep neural network methods. Results show both methods developed are able to perform the role of process monitoring and defect detection with accuracy of 82% and 93% for the traditional and DNN methods respectively. © 2022 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

University Scheduling System on the Bologna Form of Education 5

University Scheduling System on the Bologna Form of Educatio...

引用

5th International Conference on Problems of Cybernetics and Informatics, PCI 2023

作者： Ismibayli, Reshad Rzayeva, Sona University of Architecture and Construction Faculty of Mechanics and Information Technology Department of Information Technology and Systems Baku Azerbaijan Institute of Control Systems Laboratory of Recognition Identification and Methods of Optimal Solutions Baku Azerbaijan

ISBN: (纸本)9798350319064

The paper considers the features of the process of scheduling in higher educational institutions in the conditions of the Bologna system of education. The stages of scheduling and the requirements and limitations to them are described. The mathematical formulation of the problem is given.A model for scheduling classes in an interactive mode, built on the principle of a traffic light, has been developed. The possibilities of the developed software are described, which provide facilitation and acceleration of the user's work, excluding the possibility of errors in the compiled schedule. © 2023 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Analysis of Texture Synthesis Algorithms in Computer Graphics

Analysis of Texture Synthesis Algorithms in Computer Graphic...

引用

2022 Conference of Russian Young Researchers in Electrical and Electronic Engineering, ElConRus 2022

作者： Gurenko, Vladimir V. Eliseev, Vyacheslav A. Usmanov, Maxim O. Selezneva, Maria S. Bauman Moscow State Technical University Department of Computer Systems and Networks Moscow Russia Bauman Moscow State Technical University Department of Automatic Control Systems Moscow Russia

ISBN: (纸本)9781665409933

The use of computer graphics methods is associated with the ongoing problem of texture synthesis. There are two groups of approaches to this problem. The first one is the creating textures by a digital artist using such software tools as Substance Painter. The second group includes automatic methods based on specialized algorithms. Some examples include synthesis using non-parametric sampling, as well as machine learning algorithms based on PSGAN. This paper provides a comparative analysis based on quality and performance criteria of texture synthesis algorithms. It is worth to mention that the difficulty of assessing the quality of synthesis is caused by the lack of a formal quantitative metric. The authors made conclusions about the preferred fields for application of the analyzed algorithms. The results of this survey can be used to optimize the production activities of digital art studios in terms of the time it takes to make textures. © 2022 IEEE.

关键词： Computer graphics

来源：评论

学校读者我要写书评

暂无评论

On the Use of Delayed State Information for Optimal control Synthesis 5

On the Use of Delayed State Information for Optimal Control ...

引用

5th International Conference on Problems of Cybernetics and Informatics, PCI 2023

作者： Abdullayev, Vagif Guliyev, Samir Azerbaijan State Oil and Industry University Faculty of Information Technology and Control Department of General and Applied Mathematics Baku Azerbaijan Institute of Control Systems Laboratory of Recognition Identification and Methods of Optimal Solutions Baku Azerbaijan

ISBN: (纸本)9798350319064

In the paper, we propose an approach to feedback control for distributed parameters systems by the example of the rod heating process. To form the control actions, we propose to use the process's state at the measurement points both at the current time moment and at some past time moments. We derive formulas for the objective functional's gradient with respect to the feedback parameters, and formulate necessary optimality conditions. © 2023 IEEE.

关键词： Feedback control

来源：评论

学校读者我要写书评

暂无评论

Offline Goal-Conditioned Reinforcement Learning for Shape control of Deformable Linear Objects

arXiv

引用

arXiv 2024年

作者： Laezza, Rita Shetab-Bushehri, Mohammadreza Waltersson, Gabriel Arslan Özgür, Erol Mezouar, Youcef Karayiannidis, Yiannis Division of Systems and Control Department of Electrical Engineering Chalmers University of Technology Sweden CNRS Clermont Auvergne INP Institut Pascal Université Clermont Auvergne France Department of Automatic Control Lund University Sweden

Deformable objects present several challenges to the field of robotic manipulation. One of the tasks that best encapsulates the difficulties arising due to non-rigid behavior is shape control, which requires driving an object to a desired shape. While shape-servoing methods have been shown successful in contexts with approximately linear behavior, they can fail in tasks with more complex dynamics. We investigate an alternative approach, using offline RL to solve a planar shape control problem of a Deformable Linear Object (DLO). To evaluate the effect of material properties, two DLOs are tested namely a soft rope and an elastic cord. We frame this task as a goal-conditioned offline RL problem, and aim to learn to generalize to unseen goal shapes. Data collection and augmentation procedures are proposed to limit the amount of experimental data which needs to be collected with the real robot. We evaluate the amount of augmentation needed to achieve the best results, and test the effect of regularization through behavior cloning on the TD3+BC algorithm. Finally, we show that the proposed approach is able to outperform a shape-servoing baseline in a curvature inversion experiment. © 2024, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Weighted Fuzzy Rough Sets Feature Selection for High Dimensional Classification Problems

Weighted Fuzzy Rough Sets Feature Selection for High Dimensi...

引用

2024 IEEE International Conference on systems, Man, and Cybernetics, SMC 2024

作者： Khabusi, Simon Peter Huang, Yo-Ping Vu, Van Phong National Taipei University of Technology Department of Electrical Engineering Taipei10608 Taiwan National Penghu University of Science and Technology Department of Electrical Engineering Penghu88046 Taiwan Ho Chi Minh City University of Technology and Education Department of Automatic Control Ho Chi Minh City71300 Viet Nam

ISBN: (纸本)9781665410205

Feature selection holds significant importance in knowledge mining as it plays a pivotal role in selecting and preserving the most informative features within a dataset while discarding irrelevant, redundant, or noisy attributes. This process contributes to enhancing model performance, reducing computational complexity, and refining interpretability, thus facilitating more accurate and efficient data analysis. In high-dimensional datasets, the necessity for feature selection becomes more pronounced due to the heightened risk of encountering the curse of dimensionality. Therefore, this study proposes a weighted fuzzy rough quickreduct (FRQR) feature selection approach employing feature weights to handle the equal situation problem inherent in FRQR. The proposed method is evaluated on ten publicly available datasets with feature sizes ranging from 2000 to 15154. The selected features are used to train and test random forest candidate models whose estimates are then combined according to the posterior probabilities by Bayesian Model Averaging (BMA). The performance of the model on the selected features is evaluated on four performance metrics. The essentiality of the selected features is further determined by comparing the model classification performance achieved on the non-selected features and all the dataset features. The results indicate competitiveness in the performance metric values achieved on selected features over the other two feature categories affirming the efficacy of the proposed method. © 2024 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Using dynamic extensions for the backstepping control of hyperbolic systems

arXiv

引用

arXiv 2024年

作者： Gehring, Nicole Deutscher, Jochim Irscheid, Abdurahmn Institute of Automatic Control and Control Systems Technology Johannes Kepler University Linz Linz Austria Institute of Measurement Control and Microtechnology Ulm University Ulm Germany Saarland University Saarbrücken Germany

This paper systematically introduces dynamic extensions for the boundary control of general heterodirectional hyperbolic PDE systems. These extensions, which are well known in the finite-dimensional setting, constitute the dynamics of state feedback controllers. They make it possible to achieve design goals beyond what can be accomplished by a static state feedback. The design of dynamic state feedback controllers is divided into first introducing an appropriate dynamic extension and then determining a static feedback of the extended state, which includes the system and controller state, to meet some design objective. In the paper, the dynamic extensions are chosen such that all transport velocities are homogenized on the unit spatial interval. Based on the dynamically extended system, a backstepping transformation allows to easily find a static state feedback that assigns a general dynamics to the closed-loop system, with arbitrary in-domain couplings. This new design flexibility is also used to determine a feedback that achieves complete input-output decoupling in the closed loop with ensured internal stability. It is shown that the modularity of this dynamic feedback design allows for a straightforward transfer of all results to hyperbolic PDE-ODE systems. An example demonstrates the new input-output decoupling approach by dynamic extension. © 2024, CC BY-NC-ND.

关键词： Backstepping

来源：评论

学校读者我要写书评

暂无评论

Comparison of Sensor Data Fusion Algorithms for Automotive Perception System 20

Comparison of Sensor Data Fusion Algorithms for Automotive P...

引用

20th IEEE Jubilee World Symposium on Applied Machine Intelligence and Informatics, SAMI 2022

作者： Lindenmaier, Laszlo Aradi, Szilard Becsi, Tamas Toro, Oliver Budapest University of Technology and Economics Department of Control for Transportation and Vehicle Systems Budapest Hungary

ISBN: (纸本)9781665497046

Reliable environment perception has an increased role in the spread of advanced driver assistance and autonomous systems. However, at present, neither automotive sensor can reliably meet the requirements for environmental sensing. The goal of sensor fusion is to construct a more accurate and reliable environment model using the available sensor data than either sensor is applied alone. The architecture of multi-object tracking algorithms is suitable for tracking and fusing object detections from multiple sensors. However, the parameters of widely used object-tracking algorithms such as PDA and JPDA can significantly affect their computational capacity demand and the reliability of the fused environment model. The present study aims to present the parameter sensitivity of these algorithms and their effects. © 2022 IEEE.

关键词： Sensitivity Runtime Computational modeling Object detection Sensor fusion Real-time systems Sensors

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：