检索结果-内蒙古大学图书馆

Proceedings of the 36th International Conference on Neural Information Processing Systems

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

ISBN: (纸本)9781713871088

The framework of feedback graphs is a generalization of sequential decisionmaking with bandit or full information feedback. In this work, we study an extension where the directed feedback graph is stochastic, following a distribution similar to the classical Erdős-Rényi model. Specifically, in each round every edge in the graph is either realized or not with a distinct probability for each edge. We prove nearly optimal regret bounds of order $\min\bigl\{\min_{\varepsilon} \sqrt{(\alpha_\varepsilon/\varepsilon) T},\, \min_{\varepsilon} (\delta_\varepsilon/\varepsilon)^{1/3} T^{2/3}\bigr\}$ (ignoring logarithmic factors), where αε and δε are graph-theoretic quantities measured on the support of the stochastic feedback graph G with edge probabilities thresh-olded at ε. Our result, which holds without any preliminary knowledge about G, requires the learner to observe only the realized out-neighborhood of the chosen action. When the learner is allowed to observe the realization of the entire graph (but only the losses in the out-neighborhood of the chosen action), we derive a more efficient algorithm featuring a dependence on weighted versions of the independence and weak domination numbers that exhibits improved bounds for some special cases.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pursuit-Evasion on a Sphere and When It Can Be Considered Flat

Pursuit-Evasion on a Sphere and When It Can Be Considered Fl...

引用

IEEE Conference on Decision and control

作者： Dejan Milutinović Alexander Von Moll Satyanarayana G. Manyam David W. Casbeer Isaac E. Weintraub Meir Pachter Dept. University of California Santa Cruz Electrical and Computer Engineering Santa Cruz CA USA Control Science Center Aerospace Systems Directorate Air Force Research Laboratory Dayton OH USA DCS Corporation Dayton OH USA Dept. of Electrical Engineering Air Force Institute of TechnologyWright-Patterson AFB OH USA

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

In planar pursuit-evasion differential games considering a faster pursuer and slower evader, the interception points resulting from equilibrium strategies lie on the Apollonius circle. This property is instrumental for leveraging geometric approaches for solving multiple pursuit-evasion scenarios in the plane. Here, we study a pursuit-evasion differential game on a sphere and generalize the planar Apollonius set to the spherical domain. We find that the interception point from the equilibrium strategies can leave the Apollonius set boundary and present a condition to keep the intercept point on the boundary. This condition allows for generalizing planar pursuitevasion strategies to the sphere.

关键词： Geometry Instruments Differential games Games

来源：评论

学校读者我要写书评

暂无评论

Mobile Application for Visualizing the Measurements

Mobile Application for Visualizing the Measurements

引用

International Conference on Modern Electrical and Energy Systems (MEES)

作者： Simona Kirešová Milan Guzan Branislav Sobota Viacheslav Melnykov Rostyslav Yatsiuk Bohdan Peryvertailo Dept. of Theoretical and Industrial Electrical Engineering Technical University of Košice Košice Slovakia Dept. of Computers and Informatics Technical University of Košice Košice Slovakia Dept. of Systems of Automatic Control and Electric Drive Kremenchuk Mykhailo Ostrohradskyi National University Kremenchuk Ukraine Dept. of Computer Engineering and Electronics Kremenchuk Mykhailo Ostrohradskyi National University Kremenchuk Ukraine

This paper deals with the design of an Android mobile application and visualization of the measured values of particulate matter and meteorological factors from the measurement stations. The application can in principle be effectively used in any field of data visualization. The architecture of the mobile application, the security, the use of AWS services to access the data in the InfluxDB databases, as well as the user interface and graphical visualizations of the measured data are described and illustrated. The application is user tested and the paper documents their first experiences using the mobile application.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning on the Edge: Online Learning with Stochastic Feedback Graphs

arXiv

引用

arXiv 2022年

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

The framework of feedback graphs is a generalization of sequential decision-making with bandit or full information feedback. In this work, we study an extension where the directed feedback graph is stochastic, following a distribution similar to the classical Erdős-Rényi model. Specifically, in each round every edge in the graph is either realized or not with a distinct probability for each edge. We prove nearly optimal regret bounds of order min(Fomula Presented)(ignoring logarithmic factors), where αΕ and δΕ are graph-theoretic quantities measured on the support of the stochastic feedback graph G with edge probabilities thresholded at Ε. Our result, which holds without any preliminary knowledge about G, requires the learner to observe only the realized out-neighborhood of the chosen action. When the learner is allowed to observe the realization of the entire graph (but only the losses in the out-neighborhood of the chosen action), we derive a more efficient algorithm featuring a dependence on weighted versions of the independence and weak domination numbers that exhibits improved bounds for some special cases. Copyright © 2022, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

An Approach for Improving Automatic Mouth Emotion Recognition

arXiv

引用

arXiv 2022年

作者： Biondi, Giulio Franzoni, Valentina Gervasi, Osvaldo Perri, Damiano University of Florence Dept. of Mathematics and Computer Science Florence Italy University of Perugia Dept. of Mathematics and Computer Science Perugia Italy Sapienza University of Rome Department of Computer Control and Management Engineering "Antonio Ruberti" Rome Italy

The study proposes and tests a technique for automated emotion recognition through mouth detection via Convolutional Neural Networks (CNN), meant to be applied for supporting people with health disorders with communication skills issues (e.g. muscle wasting, stroke, autism, or, more simply, pain) in order to recognize emotions and generate real-time feedback, or data feeding supporting systems. The software system starts the computation identifying if a face is present on the acquired image, then it looks for the mouth location and extracts the corresponding features. Both tasks are carried out using Haar Feature-based Classifiers, which guarantee fast execution and promising performance. If our previous works focused on visual micro-expressions for personalized training on a single user, this strategy aims to train the system also on generalized faces data sets. © 2022, CC BY-NC-ND.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Application of a systematic approach to the analysis of requirements and testing of NPP automated process control systems in the field of information security using specialized software

Application of a systematic approach to the analysis of requ...

引用

2021 International Conference on Electrotechnical Complexes and Systems, ICOECS 2021

作者： Kemkin, Vladislav Doroshenko, Boris Sakharov, Konstantin Salov, Igor Salova, Julia Chernyaev, Alexey National Research University 'Moscow Power Engineering Institute' Dept. of Automated Control Systems for Thermal Processes Moscow Russia Joint-stock Company 'Rasu' Dept. of Design of I&C Computer Security Systems Moscow Russia National Research University 'Moscow Power Engineering Institute' Joint-stock Company 'Rasu' Dept. of Automated Control Systems for Thermal Processes Moscow Russia

ISBN: (纸本)9781665407274

This article reports examines the prerequisites for development and the expected results of the application of a new systematic approach to testing Industrial control System of Nuclear Power Plants (NPP ICS) in the field of information security using specialized software. The regulatory and technical documentation containing the requirements for testing the NPP ICS in the field of information security is considered, the requirements are analyzed and criteria for systematization of these requirements are formed. The result of the research is the creation of a systematic list of requirements for testing of NPP ICS subsystems in terms of information security, as a basis for the software of formation of programs, methods of checking and testing of NPP ICS subsystems in terms of information security. © 2021 IEEE.

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

LPV Modeling of the Atmospheric Flight Dynamics of a Generic Parafoil Return Vehicle

引用

IFAC-PapersOnLine 2022年第35期55卷 37-42页

作者： Matthis H. de Lange Chris Verhoek Valentin Preda Roland Tóth Control Systems Group Dept. of Electrical Engineering Eindhoven University of Technology Eindhoven 5600 MB The Netherlands ESTEC European Space Agency Noordwijk 2200 AG The Netherlands Systems and Control Lab Institute for Computer Science and Control Budapest 1111 Hungary

Obtaining models that can be used for flight control is of outmost importance to ensure reliable guidance and navigation of spacecrafts, like a Generic Parafoil Return Vehicle (GPRV). In this paper, we convert an existing, high-fidelity nonlinear model of the atmospheric flight dynamics of a GPRV to a Linear Parameter-Varying (LPV) form that enables high-performance navigation control design. Application of existing systematic conversion methods for such complicated nonlinear models often result in complex LPV representations, which are not suitable for controller synthesis. We apply and compare state-of-the-art conversion techniques on the GPRV model, including learning based approaches, to optimize the complexity and conservatism of the resulting LPV embedding. The results show that we can obtain an LPV embedding that approximates the complex nonlinear dynamics sufficiently well, where the balance between complexity, conservatism and model performance is efficiently chosen.

关键词： linear parameter-varying systems scheduling reduction spacecraft modeling aerodynamics principle component analysis deep neural networks

来源：评论

学校读者我要写书评

暂无评论

On the Use of MPC Techniques to Decide Intervention Policies against COVID-19

引用

IFAC-PapersOnLine 2021年第14期54卷 476-481页

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

This paper aims at demonstrating how and that model predictive control (MPC) strategies can be used to determine optimal intervention policies against the COVID-19 pandemic. Especially for the time after a first wave of infection and before a vaccine can be safely distributed to a sufficient extent, the intervention experience from the first outbreak can be utilized to guide the policy decision in this period. The MPC problem in this paper takes the pandemic in different regions of a country and its neighboring countries into account, while policies such as wearing masks or social distancing are selected as inputs to be optimized. This optimized policy balances the risk of a second outbreak and socio-economic costs, while considering that the measure should not be too severe to be rejected by the population. Effectiveness of this policy compared to standard intervention policies is compared through numerical simulations.

关键词： Biomedical Systems Networked Systems Nonlinear Model Predictive control

来源：评论

学校读者我要写书评

暂无评论

Investigation of the Necessity of Past Input/output Information in Reinforcement Learning based Robust control

引用

Transactions of the Korean Institute of Electrical Engineers 2021年第12期70卷 1953-1957页

作者： Shim, Hyungbo Kim, Jeong Woo Park, Jooyoung Dept. of Electrical and Computer Engineering Seoul National University Korea Republic of Dept. of Control & Instrumentation Engineering Korea University Korea Republic of

Reinforcement learning yields a feedback controller that achieves specific control goal (which is often translated as a reward function). However, it often suffers from the Sim2Real gap, and domain randomization is known to be a method to overcome this issue. In this paper, we demonstrate necessity of input/outpu history when domain randomization is employed by a formal example and a simulation result. This is equivalent to the necessity of dynamic feedback controller in terms of control theory. © The Korean Institute of Electrical Engineers

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Multi-label transfer learning for identifying lung diseases using chest X-rays 2

Multi-label transfer learning for identifying lung diseases ...

引用

2nd IEEE International Conference on Electronic engineering, ICEEM 2021

作者： El-Fiky, Azza Shouman, Marwa Ahmed Hamada, Salwa El-Sayed, Ayman Karar, Mohamed Esmail Electronics Research Institute Department of Informatics Cairo Egypt Menoufia University Faculty of Electronic Engineering Department of Computer Science and Engineering Minuf Egypt Menoufia University Faculty of Electronic Engineering Dept. Industrial Electronics and Control Engineering Minuf Egypt

ISBN: (纸本)9781665418423

Chest radiography presents one of the main medical imaging modalities for diagnosing lung diseases. To assist radiologists during interventional procedures, this paper aims at proposing a transfer learning-based classifier to automatically identify 14 different thoracic diseases in Chest X-ray (CXR) images. The proposed method is relied on deep residual neural networks with 50 layers (ResNet-50) to accomplish the diagnostic task of many chest diseases. In this study, a public dataset of 112, 120 frontal radiograph images for Chest X-ray has been used for validating the proposed deep learning classifier. It achieved the best performance of multi-label classification of normal and 14 different lung diseases with an average area under curve (AUC) of 0.911 and F1-score of 0.66. This study demonstrated that the proposed ResNet-50 classifier as a transfer learning model outperforms other relevant methods in the previous studies for automatic multi-label classification of chest X-rays. © 2021 IEEE.

关键词： computer aided diagnosis

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：