检索结果-内蒙古大学图书馆

5th Experiment at International Conference, exp.at 2019

作者： Huba, Mikulas Anthony Rossiter, J. Zakova, Katarina Serbezov, Atanas Visioli, Antonio Institute of Automotive Mechatronics Faculty of Electrical Engineering and Information Technology Slovak University of Technology Bratislava Slovakia Department of Automatic Control and Systems Engineering University of Sheffield Sheffield United Kingdom Rose-Hulman Institute of Technology Terre Haute United States Department of Mechanical and Industrial Engineering University of Brescia Brescia Italy

ISBN: (纸本)9781728136370

关键词： Engineering education

来源：评论

学校读者我要写书评

暂无评论

A Guide to Image and Video based Small Object Detection using Deep Learning: Case Study of Maritime Surveillance

arXiv

引用

arXiv 2022年

作者： Rekavandi, Aref Miri Xu, Lian Boussaid, Farid Seghouane, Abd-Krim Hoefs, Stephen Bennamoun, Mohammed The Department of Computer Science and Software Engineering The University of Western Australia 35 Stirling Highway CrawleyWA6009 Australia The Department of Electrical Electronics and Computer Engineering The University of Western Australia 35 Stirling Highway CrawleyWA6009 Australia The School of Mathematics and Statistics The University of Melbourne Melbourne Australia submarine optronics undersea combat systems and undersea command and control maritime division Defence Science and Technology Group Australia

Small object detection (SOD) in optical images and videos is a challenging problem that even state-of-the-art generic object detection methods fail to accurately localize and identify such objects. Typically, small objects appear in real-world due to large camera-object distance. Because small objects occupy only a small area in the input image (e.g., less than 10%), the information extracted from such a small area is not always rich enough to support decision making. Multidisciplinary strategies are being developed by researchers working at the interface of deep learning and computer vision to enhance the performance of SOD deep learning based methods. In this paper, we provide a comprehensive review of over 160 research papers published between 2017 and 2022 in order to survey this growing subject. This paper summarizes the existing literature and provide a taxonomy that illustrates the broad picture of current research. We investigate how to improve the performance of small object detection in maritime environments, where increasing performance is critical. By establishing a connection between generic and maritime SOD research, future directions have been identified. In addition, the popular datasets that have been used for SOD for generic and maritime applications are discussed, and also well-known evaluation metrics for the state-of-the-art methods on some of the datasets are provided. © 2022, CC BY-NC-SA.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

LPV active fault-tolerant control strategy of large civil aircraft under elevator failures

LPV active fault-tolerant control strategy of large civil ai...

引用

CSAA/IET International Conference on Aircraft Utility systems 2020, AUS 2020

作者： Zhou, Zhiyuan Wang, Xingjian Wang, Shaoping Zhang, Yuwei Gavrilov, Alexander I. Nagamune, Ryozo School of Automation Science and Electrical Engineering Beihang University Beijing100191 China Beijing Advanced Innovation Center for Big Data-Based Precision Medicine Beihang University Beijing100191 China Ningbo Institute of Technology Beihang University Ningbo315800 China Bauman Moscow State Technical University Department of Automatic Control Systems Moscow105005 Russia Department of Mechanical Engineering The University of British Columbia VancouverBCV6T1Z4 Canada

ISBN: (纸本)9781839535635

This paper proposes a scheme to achieve fault tolerant control to elevator failure of large aircraft. Meanwhile, the model of aircraft is expressed by linear-parameter-varying (LPV), and an LPV controller is designed. The approaches of H-infinity and pole assignment using linear matrix inequalities (LMIs) tools are used to design the states feedback controller, keeping the stability, rapidity and robustness. Moreover, an additional scheduling parameter of effectiveness of the elevator is introduced to the model and controller, keeping the desired performance when elevator failure happens by the nominal controller, avoiding the retuning the controller. The simulation are shown to prove the method. © 2020 Institution of Engineering and technology. All rights reserved.

关键词： controllers

来源：评论

学校读者我要写书评

暂无评论

Vehicle control in Highway Traffic by Using Reinforcement Learning and Microscopic Traffic Simulation

Vehicle Control in Highway Traffic by Using Reinforcement Le...

引用

International Symposium on Intelligent systems and Informatics (SISY)

作者： Laszlo Szoke Szilard Aradi Tamas Becsi Peter Gaspar Department of Control for Transportation and Vehicle Systems Budapest University of Technology and Economics Megyetem rkp. 3 Budapest Hungary Systems and Control Laboratory Computer and Automation Research Institute Hungarian Academy of Sciences Kende u. 13-17 Budapest Hungary

ISBN: (数字)9781728173528

ISBN: (纸本)9781728173535

The paper presents a simple yet powerful and intelligent driver agent, designed to operate in a preset highway situation using Policy Gradient Reinforcement Learning (RL) agent. The goal is to navigate safely in dense highway traffic and proceed through the defined length with the shortest time possible. The algorithm uses a dense neural network as a function approximator for the agent with discrete action space on the control level, e.g., acceleration and steering. The developed simulation environment uses the open-source traffic simulator called Simulation of Urban MObility (SUMO), integrated with an interface, to interact with the agent in real-time. With this tool, numerous driving and highway situations can be created and fed to the agent from which it can learn. The environment opens the opportunity to randomize and customize the other road users' behavior. Thus the experience can be more diverse, and thus the representation becomes more general. The article describes the modeling environment, the details on the learning agent, and the rewarding scheme. After evaluating the experiences gained from the training, some ideas for optimization and further development goals are also proposed.

关键词： Learning (artificial intelligence) Task analysis Vehicles Roads Training Microscopy

来源：评论

学校读者我要写书评

暂无评论

Influence of Sintered Conditions on Electrophysical Properties of the Ceramics Based on BeO with a Dopant of a TiO2Powder

Influence of Sintered Conditions on Electrophysical Properti...

引用

2022 Ural Symposium on Biomedical Engineering, Radioelectronics and Information technology, USBEREIT 2022

作者： Malkin, Alexander Kijko, Victor Mikhaylovskaya, Zoya Korotkov, Alexey Knyazev, Sergei Malkina, Sofia Petrova, Sofia Belova, Ksenia Pavlov, Alexander Ural Federal University Named after the First President of Russia B. N. Yeltsin Engineering School of Information Technologies Telecommunications and Control Systems Yekaterinburg Russia Department of Chemical Technology of Ceramics and Refractory Materials Ural Federal University Named after the First President of Russia B. N. Yeltsin Yekaterinburg Russia Zavaritsky Institute of Geology and Geochemistry Ural Br. of Ras Yekaterinburg Russia Institute of Metallurgy Ural Br. of Ras Yekaterinburg Russia Ural Federal University Named after the First President of Russia B. N. Yeltsin Yekaterinburg Russia Siberian Federal University Krasnoyarsk Russia

ISBN: (数字)9781665460927

ISBN: (纸本)9781665460927

The BeO-based ceramics with adding micro and nano-size powders of TiO2 have a number of unique properties such as a high specific thermal conductivity, high insertion loss values for an electromagnetic wave propagating through the material under research. All of these features of BeO-based ceramics give us the possibility to use this material for a high power load realization in the RF range. The investigation of the influence of the sintering temperature of ceramics on electrophysical properties of studying materials in the frequency range from 8 to 12 GHz has been presented in this article. The vector network analyzer R&S ZVA50 with a set of measuring equipment consisting of the waveguide transmission line WR90 standard and calibration kit for performing TRL calibration procedure has been used for performing measurement of electrodynamics properties of researching materials. Structural characteristics of BeO-based ceramic samples with the addition of TiO2 micro and nanopowders were investigated using scanning electron microscopy and differential thermal analysis. The density of research samples was defined by the hydrostatic weighing method. The comparison of ceramic samples with different sintering temperatures of ceramics 1550 0C and 1660 0C was presented in the article. The frequency dependences of the complex dielectric permittivity of studied samples are given. © 2022 IEEE.

关键词： Permittivity

来源：评论

学校读者我要写书评

暂无评论

Optimal Experiment Design for Multi-variable Motion systems: with Application to a Next-Generation Wafer Stage ⁎

引用

IFAC-PapersOnLine 2019年第15期52卷 615-620页

作者： Nic Dirkx Jeroen van de Wijdeven Tom Oomen ASML Research Mechatronics & Control Veldhoven The Netherlands Eindhoven University of Technology Department of Mechanical Engineering Control Systems Technology Eindhoven The Netherlands

Frequency Response Functions (FRFs) are essential for motion control design of complex mechatronic systems. The aim of this paper is to develop Optimal Experiment Design (OED) approaches for accurate identification of FRF models, with the particular focus on Multiple Input Multiple Output (MIMO) systems in closed-loop. The resulting optimization problem is shown to be highly challenging, especially for complex systems. A practical and feasible numerical approach based on a convex relaxation is developed. Experimental results on a next-generation wafer stage confirm that the quality of FRF measurements can be improved significantly using the proposed techniques.

关键词： Optimal experiment design system identification multivariable systems frequency response function multisines

来源：评论

学校读者我要写书评

暂无评论

Brain-wide N2cG compensation permits glycoprotein-deleted rabies virus to trace neural circuits across multiple synapses

引用

Journal of Innovative Optical Health Sciences 2023年第6期16卷 13-21页

作者： Nengsong Luo Zengpeng Han Jiaxin Kou Yuxiang Cai Xin Yang Jie Wang Kunzhang Lin Fuqiang Xu Wuhan National Laboratory for Optoelectronics Huazhong University of Science and TechnologyWuhan 430074P.R.China State Key Laboratory of Magnetic Resonance and Atomic and Molecular Physics Key Laboratory of Magnetic Resonance in Biological SystemsWuhan Center for Magnetic ResonanceInnovation Academy for Precision Measurement Science and TechnologyChinese Academy of SciencesWuhan430071P.R.China University of Chinese Academy of Sciences Beijing100049P.R.China Shenzhen Key Laboratory of Viral Vectors for Biomedicine Key Laboratory of Quality Control Technology for Virus-Based TherapeuticsGuangdong Provincial Medical Products AdministrationNMPA Key Laboratory for Research and Evaluation of Viral Vector Technology in Cell and Gene Therapy Medicinal Productsthe Brain Cognition and Brain Disease Institute(BCBDI)Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen-Hong Kong Institute of Brain Science-Shenzhen Fundamental Research InstitutionsShenzhen518055P.R.China Department of Pathophysiology Key Lab of Neurological Disorder of Education MinistrySchool of Basic MedicineTongji Medical CollegeHuazhong University of Science and TechnologyWuhanP.R.China Shenzhen-Hong Kong Institute of Brain Science-Shenzhen Fundamental Research Institutions Shenzhen518055P.R.China Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of SciencesShanghai200031P.R.China

Rabies-viruses-based retrograde tracers can spread across multiple synapses in a retrograde direction in the nervous system of rodents and primates,making them powerful tools for determining the structure and function of the complicated neural circuits of the ***,they have some limitations,such as posing high risks to human health and the inability to retrograde trans-synaptic label inputs from genetically-de¯ned starter ***,we established a new retrograde trans-multi-synaptic tracing method through brain-wide rabies virus glycoprotein(RVG)compensation,followed by glycoprotein-deleted rabies virus(RV-△G)infection in specific brain ***,in combination with the avian tumor virus receptor A(TVA)controlled by a cell-type-specific promoter,we found that EnvA-pseudotyped RV-△G can mediate e±cient retrograde trans-multi-synaptic transduction from cell-type-specific starter *** study provides new alternative methods for neuroscience researchers to analyze the input neural networks of rodents and nonhuman primates.

关键词： Rabies virus retrograde tracers trans-multi-synaptic tracing AAV-PHP.eB celltype-specific input neural networks

来源：评论

学校读者我要写书评

暂无评论

The ateb-gabor filter for fingerprinting 14th

The ateb-gabor filter for fingerprinting

引用

14th International Scientific and Technical Conference on Computer Science and Information Technologies, CSIT 2019

作者： Nazarkevych, Mariya Logoyda, Mykola Troyan, Oksana Vozniy, Yaroslav Shpak, Zoreslava Publishing Information Technology Department Institute of Computer Science and Information Technologies Lviv Polytechnic National University 12 Bandery str. Lviv79013 Ukraine Department of Automated Control Systems Institute of Computer Science and Information Technologies Lviv Polytechnic National University 12 Bandery str. Lviv79013 Ukraine

ISBN: (纸本)9783030336943

In biometric protection systems, a lot of time is spent on recognition processes. The quality of recognition also remains unsatisfactory. A new Ateb-Gabor filtration method is proposed that extends the classic filtration methods. Applying the Ateb-Gabor filter fully utilizes the Gabor filter and uses the apparatus of Ateb functions. These functions extend the capabilities of trigonometry and build on accurate solutions of differential equations with significant second order nonlin-earity. This approach allows the intensity of both the entire image and certain predefined portions to be altered, allowing for more accurate outlines in biometric images. The functions used depend on two rational parameters m and n, the change of which leads to the change of certain areas of the image. Fingerprints were filtered with a developed filter, showing the effectiveness of its use. Sketches of filtered biometric images have been developed. © Springer Nature Switzerland AG 2020.

关键词： Gabor filters

来源：评论

学校读者我要写书评

暂无评论

A Fault Tolerant control Scheme Using the Feasible Constrained control Allocation Strategy

引用

International Journal of Automation and computing 2019年第5期16卷 628-643页

作者： Mehdi Naderi Tor Arne Johansen Ali Khaki Sedigh Center of Excellence in Industrial Control Faculty of Electrical EngineeringK.N.Toosi University of TechnologySeyyed Khandan BridgeShariati AvenueTehran ***Iran Center for Autonomous Marine Operation and Systems Department of Engineering CyberneticsNorwegian University of Science and TechnologyTrondheim 7491Norway

This paper investigates the necessity of feasibility considerations in a fault tolerant control system using the constrained control allocation methodology where both static and dynamic actuator constraints are considered. In the proposed feasible control allocation scheme, the constrained model predictive control(MPC) is employed as the main controller. This considers the admissible region of the control allocation problem as its constraints. Using the feasibility notion in the control allocation problem provides the main controller with information regarding the actuator′s status, which leads to closed loop system performance improvement. Several simulation examples under normal and faulty conditions are employed to illustrate the effectiveness of the proposed methodology. The main results clearly indicate that closed loop performance and stability characteristics can be significantly degraded by neglecting the actuator constraints in the main controller. Also, it is shown that the proposed strategy substantially enlarges the domain of attraction of the MPC combined with the control allocation as compared to the conventional MPC.

关键词： control allocation feasibility fault tolerant control model predictive control domain of attraction

来源：评论

学校读者我要写书评

暂无评论

Kartalol: A New Deep Neural Network Framework Based on Transfer Learning for Iris Segmentation and Localization Task: New Dataset for Iris Segmentation

SSRN

引用

SSRN 2022年

作者： Khiarak, Jalil Nourmohammadi Oskouei, Amin Golzari Nasab, Samaneh Salehi Jaryani, Farhang Moafinejad, Seyed Naeim Pourmohamad, Rana Amini, Yasin Noshad, Morteza Institute of Control and Computation Engineering Warsaw University of Technology Warsaw Poland Department of Computer Engineering Faculty of Electrical and Computer Engineering University of Tabriz Iran School of Engineering Lorestan University Aleshtar Campus Aleshtar Iran Malek-Ashtar University of Technology Department of Physics Shahid Beheshti University Tehran Iran School of Computing Informatics and Decision Systems Engineering Arizona State University AZ United States Faculty of Electrical and Computer Engineering University of Kharazmi Iran Stanford University United States

Iris segmentation and localization in unconstrained environments is challenging due to long distances, illumination variations, limited user cooperation, and moving subjects. Some existing methods in the literature, each of which has somehow mitigated some of the mentioned issues. In this paper, motivated by these weaknesses, we propose a framework that employs a deep neural network-based approach to iris segmentation and localization. The proposed framework is based on a U-Net architecture that has been initialized with a pre-trained MobileNetV2 model. In addition, we have collected 1000 images to study the detectors in iris recognition scenarios better. The provided dataset (KartalOl) is available free for the research community. In the proposed framework, to better generalizability, we fine-tune the MobileNetV2 model on the provided data for NIR-ISL 2021 from the CASIA-Iris-Asia, CASIA-Iris-M1, and CASIA-Iris-Africa and our dataset. Also, data augmentation technics are applied on images. We chose the binarization threshold for the binary masks by iterating over the images in the provided dataset. The proposed framework is trained and tested in CASIA-Iris-Asia, CASIA-Iris-M1, CASIA-Iris-Africa, along the KartalOl dataset. The experimental results highlight that our method surpasses state-of-the-art methods on mobile-based benchmarks. The codes and evaluation results are publicly available at https://***/Jalilnkh/KartalOl-NIR-ISL2021031301. © 2022, The Authors. All rights reserved.

关键词： Deep neural networks

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：