检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Aquilina, Matthew Galea, Christian Abela, John Camilleri, Kenneth P. Farrugia, Reuben A. Dept. of Communications & Computer Engineering Faculty of ICT University of Malta UM Msida Malta Malta Deanery of Molecular Genetic & Population Health Sciences University of Edinburgh Scotland Edinburgh United Kingdom Dept. of Communications & Computer Engineering Faculty of ICT UM Dept. of Computer Information Systems Faculty of ICT UM Dept. of Systems & Control Engineering Faculty of Engineering UM

Convolutional Neural Networks (CNNs) have achieved impressive results across many super-resolution (SR) and image restoration tasks. While many such networks can upscale low-resolution (LR) images using just the raw pixel-level information, the ill-posed nature of SR can make it difficult to accurately super-resolve an image which has undergone multiple different degradations. Additional information (metadata) describing the degradation process (such as the blur kernel applied, compression level, etc.) can guide networks to super-resolve LR images with higher fidelity to the original source. Previous attempts at informing SR networks with degradation parameters have indeed been able to improve performance in a number of scenarios. However, due to the fully-convolutional nature of many SR networks, most of these metadata fusion methods either require a complete architectural change, or necessitate the addition of significant extra complexity. Thus, these approaches are difficult to introduce into arbitrary SR networks without considerable design alterations. In this paper, we introduce meta-attention, a simple mechanism which allows any SR CNN to exploit the information available in relevant degradation parameters. The mechanism functions by translating the metadata into a channel attention vector, which in turn selectively modulates the network’s feature maps. Incorporating meta-attention into SR networks is straightforward, as it requires no specific type of architecture to function correctly. Extensive testing has shown that meta-attention can consistently improve the pixel-level accuracy of state-of-the-art (SOTA) networks when provided with relevant degradation metadata. Despite average memory/runtime overheads of less than ≈2.6%/0.025 seconds for the datasets and models considered, meta-attention improves the performance for both PSNR and SSIM;for PSNR, the gain on blurred/downsampled (×4) images is of 0.2969 dB (on average) and 0.3320 dB for SOTA general and f

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Beyond bandit feedback in online multiclass classification

arXiv

引用

arXiv 2021年

作者： van der Hoeven, Dirk Fusco, Federico Cesa-Bianchi, Nicolò Dept. of Computer Science Università degli Studi di Milano Italy Dept. of Computer Control and Management Engineering Sapienza Università di Roma Italy DSRC Dept. of Computer Science Università degli Studi di Milano Italy

We study the problem of online multiclass classification in a setting where the learner’s feedback is determined by an arbitrary directed graph. While including bandit feedback as a special case, feedback graphs allow a much richer set of applications, including filtering and label efficient classification. We introduce Gappletron, the first online multiclass algorithm that works with arbitrary feedback graphs. For this new algorithm, we prove surrogate regret bounds that hold, both in expectation and with high probability, for a large class of surrogate losses. Our bounds are of order B√ρKT, where B is the diameter of the prediction space, K is the number of classes, T is the time horizon, and ρ is the domination number (a graph-theoretic parameter affecting the amount of exploration). In the full information case, we show that Gappletron achieves a constant surrogate regret of order B2K. We also prove a general lower bound of order max {B2K, √T} showing that our upper bounds are not significantly improvable. Experiments on synthetic data show that for various feedback graphs our algorithm is competitive against known baselines. Copyright © 2021, The Authors. All rights reserved.

关键词： Directed graphs

来源：评论

学校读者我要写书评

暂无评论

Beyond bandit feedback in online multiclass classification 21

Beyond bandit feedback in online multiclass classification

引用

Proceedings of the 35th International Conference on Neural Information Processing Systems

作者： Dirk van der Hoeven Federico Fusco Nicolò Cesa-Bianchi Dept. of Computer Science Università degli Studi di Milano Italy Dept. of Computer Control and Management Engineering Sapienza Università di Roma Italy DSRC & Dept. of Computer Science Università degli Studi di Milano Italy

ISBN: (纸本)9781713845393

We study the problem of online multiclass classification in a setting where the learner's feedback is determined by an arbitrary directed graph. While including bandit feedback as a special case, feedback graphs allow a much richer set of applications, including filtering and label efficient classification. We introduce GAP-PLETRON, the first online multiclass algorithm that works with arbitrary feedback graphs. For this new algorithm, we prove surrogate regret bounds that hold, both in expectation and with high probability, for a large class of surrogate losses. Our bounds are of order $B\sqrt{\rho KT}$, where B is the diameter of the prediction space, K is the number of classes, T is the time horizon, and ρ is the domination number (a graph-theoretic parameter affecting the amount of exploration). In the full information case, we show that GAPPLETRON achieves a constant surrogate regret of order B2K. We also prove a general lower bound of order max {B2K, √T} showing that our upper bounds are not significantly improvable. Experiments on synthetic data show that for various feedback graphs our algorithm is competitive against known baselines.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Predictive control for Linear Parameter-Varying Systems ⁎

引用

IFAC-PapersOnLine 2021年第8期54卷 101-108页

作者： Chris Verhoek Hossam S. Abbas Roland Tóth Sofie Haesaert Control Systems Group Dept. of Electrical Engineering Eindhoven University of Technology Eindhoven 5600MB The Netherlands Institute for Electrical Engineering in Medicine Universität zu Lübeck 23558 Lübeck Germany Systems and Control Lab Institute for Computer Science and Control (SZTAKI) Kende u. 13-17 1111 Budapest Hungary

Based on the extension of the behavioral theory and the Fundamental Lemma for Linear Parameter-Varying (LPV) systems, this paper introduces a Data-driven Predictive control (DPC) scheme capable to ensure reference tracking and satisfaction of Input-Output (IO) constraints for an unknown system under the conditions that (i) the system can be represented in an LPV form and (ii) an informative data-set containing measured IO and scheduling trajectories of the system is available. It is shown that if the data set satisfies a persistence of excitation condition, then a data-driven LPV predictor of future trajectories of the system can be constructed from the IO data set and online measured data. The approach represents the first step towards a DPC solution for nonlinear and time-varying systems due to the potential of the LPV framework to represent them. Two illustrative examples, including reference tracking control of a nonlinear system, are provided to demonstrate that the data-based LPV-DPC scheme, achieves similar performance as LPV model-based predictive control.

关键词： Predictive control Data-Driven control Linear Parameter-Varying Systems Non-Parametric Methods

来源：评论

学校读者我要写书评

暂无评论

Forecasting Breakdowns of Electric Motors of a Sugar Factory Using Machine Learning Methods

Forecasting Breakdowns of Electric Motors of a Sugar Factory...

引用

Advanced Technology (KhPIWeek), IEEE KhPI Week on

作者： Nataliia Zaiets Nataliia Lutska Lidiia Vlasenko Andrii Zhyltsov dept. of Automation and Robotic Systems National University of Life and Environmental Sciences of Ukraine Kyiv Ukraine dept. of Automation and Computer Technologies of Control Systems National University of Food Technologies Kyiv Ukraine dept. of Software Engineering and Cyber Security State University of Trade and Economics Kyiv Ukraine dept. of electromagnetic systems The Institute of Electrodynamics of the National Academy of Sciences of Ukraine Kyiv Ukraine

the paper demonstrates the process of developing mathematical models for identifying breakdowns of electric motors using machine learning methods. The authors have developed three mathematical models for identifying breakdowns of electric drives with a power of 55 kW, 1500 rpm on the example of sugar production: model for quadratic discriminant analysis; binary classification decision tree; feed-forward neural network model. The best structures and parameters of the models were determined by machine learning methods. The performance of the models on the training and test sets was more than 96% by F-score. It was proposed to use all three models independently for diagnosing breakdowns of electric drives, while the decision maker makes the final decision on the replacement or repair of electrical equipment. This approach is justified and effective because of the diversity of models. The developed models, except for assessing the state of the engine, can also be used for simulation modelling, forecasting, and serve as information support for process operators in organizing equipment maintenance. The availability of real-time information about the state of equipment in production will allow timely repair or replacement of equipment, thereby reducing the risks of stopping production and increasing the resource efficiency of technological processes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Overcoming the Fear of the Dark: Occlusion-Aware Model-Predictive Planning for Automated Vehicles Using Risk Fields

arXiv

引用

arXiv 2023年

作者： van der Ploeg, Chris Nyberg, Truls Sánchez, José Manuel Gaspar Silvas, Emilia van de Wouw, Nathan Netherlands Organisation for Applied Scientific Research Integrated Vehicle Safety Group Helmond5700 AT Netherlands Eindhoven University of Technology Dynamics and Control Group Mechanical Engineering Dept. P.O. Box 513 Eindhoven5600 MB Netherlands Eindhoven University of Technology Control Systems Technology Group Mechanical Engineering Dept. P.O. Box 513 Eindhoven5600 MB Netherlands KTH Royal Institute of Technology Division of Robotics Perception and Learning School of Electrical Engineering and Computer Science Stockholm100 44 Sweden Scania CV AB Södertälje151 87 Sweden

As vehicle automation advances, motion planning algorithms face escalating challenges in achieving safe and efficient navigation. Existing Advanced Driver Assistance Systems (ADAS) primarily focus on basic tasks, leaving unexpected scenarios for human intervention, which can be error-prone. Motion planning approaches for higher levels of automation in the state-of-the-art are primarily oriented toward the use of risk- or anti-collision constraints, using over-approximates of the shapes and sizes of other road users to prevent collisions. These methods however suffer from conservative behavior and the risk of infeasibility in high-risk initial conditions. In contrast, our work introduces a novel multi-objective trajectory generation approach. We propose an innovative method for constructing risk fields that accommodates diverse entity shapes and sizes, which allows us to also account for the presence of potentially occluded objects. This methodology is integrated into an occlusion-aware trajectory generator, enabling dynamic and safe maneuvering through intricate environments while anticipating (potentially hidden) road users and traveling along the infrastructure toward a specific goal. Through theoretical underpinnings and simulations, we validate the effectiveness of our approach. This paper bridges crucial gaps in motion planning for automated vehicles, offering a pathway toward safer and more adaptable autonomous navigation in complex urban contexts. Copyright © 2023, The Authors. All rights reserved.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Robust Point-to-Set control of Hybrid Systems with Uncertainties Using Constraint Tightening

引用

IFAC-PapersOnLine 2020年第2期53卷 6806-6812页

作者： Zonglin Liu Olaf Stursberg Control and System Theory Dept. of Electrical Engineering and Computer Science University of Kassel Germany

This paper proposes a solution to the problem of computing optimized point-to-set control strategies for hybrid systems with mixed inputs and uncertainties in the continuous-valued dynamics as well as the reset functions. The solution is based on the idea to account for the uncertainties by tightening the guard and invariant sets, and thus construct a substitute hybrid automaton with deterministic transition dynamics. It can be ensured that a solution for this new model also solves the problem for the original system, i.e. the latter is robustly transferred between initial point and target set.

关键词： Hybrid systems uncertain systems constrained control robust control optimization

来源：评论

学校读者我要写书评

暂无评论

Grid-following three-phase inverter with RMS current-limiting property 12

Grid-following three-phase inverter with RMS current-limitin...

引用

12th Mediterranean Conference on Power Generation, Transmission, Distribution and Energy Conversion, MEDPOWER 2020

作者： Skentzos, Panagiotis Konstantopoulos, George C. Dept. of Automatic Control and Systems Engineering University of Sheffield Mappin Street SheffieldS1 3JD United Kingdom Dept. of Electrical and Computer Engineering University of Patras Rio26504 Greece

ISBN: (纸本)9781839535635

A novel nonlinear controller that inherently limits the RMS value of a three-phase grid-following inverter current is presented in this paper. Using the dynamic model of the inverter in the rotating dq reference frame, a nonlinear control scheme is formulated to ensure accurate real and reactive power regulation with RMS current limitation that avoids the use of saturation units with upper/lower limit adaptation, as commonly used in the existing approaches. In particular, it is analytically proven by using fundamental nonlinear systems theory, that the RMS value of the inverter current will never violate a given maximum value, both during the transient response and at the steady-state. Moreover, a detailed root locus analysis is provided to guarantee the asymptotic stability of the desired equilibrium point for the closed-loop system. Finally, to validate the proposed controller performance, simulation results of a grid-following three-phase inverter equipped with the proposed control approach are presented under both normal and unrealistic values of the real and reactive power setpoints. © 2020 Institution of engineering and Technology. All rights reserved.

关键词： Asymptotic stability

来源：评论

学校读者我要写书评

暂无评论

Brownian motion simulation of SiO2 abrasive nanoparticle on SiC substrate surface 10

Brownian motion simulation of SiO2 abrasive nanoparticle on ...

引用

10th International Conference on Leading Edge Manufacturing Technologies in 21st Century, LEM 2021

作者： Saenna, Soraya Khajornrungruang, Panart Blattler, Aran Permpatdechakul, Thitipat Suzuki, Keisuke Bakier, Mohammed A. Graduate School of Computer Science and Systems Engineering Kyushu Institute Technology 680-4 Kawazu Iizuka-shi Fukuoka820-8502 Japan Dept. of Intelligent and Control Systems Advanced Mechanical Division Kyushu Institute of Technology 680-4 Kawazu Iizuka-shi Fukuoka820-8502 Japan

Chemical-Mechanical Polishing (CMP) process has emerged as the method of choice for planarization in the semiconductor industry. The interaction force between the surface being polished and the abrasive nanoparticles plays a significant role in flattening the substrate surface in the CMP process. For example, when the SiO2 nanoparticle is distant from the SiC substrate surface, the interaction force between the surface and the nanoparticles is presented. This force could be analysed using Derjaguin and Landau and Verwey and Overbeek (DLVO) theory and particle Brownian motion. According to the simulation results, we found that very fine abrasive nanoparticle such as smaller than approximately 10 nm is comparatively approach to the surface being polished more certainly. © 2021 The Japan Society of Mechanical Engineers.

关键词： Silicon carbide

来源：评论

学校读者我要写书评

暂无评论

Stabilization with Zero Location Constraints for Delay-Based Non-collocated Vibration Suppression ⁎

引用

IFAC-PapersOnLine 2021年第18期54卷 121-126页

作者： Haik Silm Wim Michiels Tomáš Vyhlídal Departement of Computer Science KU Leuven Celestijnenlaan 200A 3001 Leuven Belgium Dept. Instrumentation and Control Engineering Faculty of Mechanical Engineering and Czech Institute of Informatics Robotics and Cybernetics Czech Technical University in Prague Prague 6 Czechia

A generally applicable design of non-collocated vibration absorption by a delayed resonator is proposed. It is grounded in the direct assignment of imaginary axis zeros of the transfer function between the periodic disturbance force and the target. We show that these transmission zeros are characterized as eigenvalues of a delay differential-algebraic system. Furthermore, a stabilizing local controller is added to the setup in order to widen the range of admissible vibration frequencies. These design requirements are translated into an optimization problem of the spectral abscissa function subjected to zero location constraints. The presented approach and algorithm are validated by a simulation on a three body lumped mass-spring system.

关键词： Vibration control Delayed resonator Transmission zeros Stability Spectral method

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：