检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Muneta, Hideyuki Horisaki, Ryoichi Nishizaki, Yohei Naruse, Makoto Tanida, Jun Department of Information and Physical Sciences Graduate School of Information Science and Technology Osaka University 1-5 Yamadaoka Osaka Suita565-0871 Japan Department of Information Physics and Computing Graduate School of Information Science and Technology The University of Tokyo 7-3-1 Hongo Bunkyo-ku Tokyo113-8656 Japan Systems and Control Laboratory Environmental Technology Research Division Osaka Research Institute of Industrial Science and Technology 1-6-50 Morinomiya Joto-ku Osaka536-8553 Japan

In this paper, we present a method for single-shot blind deconvolution incorporating a coded aperture (CA). In this method, we utilize the CA, inserted on the pupil plane, as support constraints in blind deconvolution. Not only an object but also a point spread function of turbulence are estimated from a single captured image by a reconstruction algorithm with the CA support. The proposed method is demonstrated by a simulation and an experiment in which point sources are recovered under severe turbulence. © 2022, CC BY.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Logical-combinatorial approaches in dynamic recognition problems

arXiv

引用

arXiv 2021年

作者： Aslanyan, Levon H. Krasnoproshin, Viktor V. Ryazanov, Vladimir V. Sahakyan, Hasmik A. Institute for Informatics and Automation Problems NAS RA Armenia Belarusian State University Department of Information Management Systems Belarus Dorodnitsyn Computing Centre Federal Research Center Computer Science and Control RAS Russia

A pattern recognition scenario, where instead of object classification into the classes by the learning set, the algorithm aims to allocate all objects to the same, the so-called "normal" class, is the research objective. Given the learning set L;the class K! is called "normal", and the reminder l classes K", K#,..., K$ from the environment K are "deviated". The classification algorithm is for a recurrent use in a "classification, action" format. Actions A% are defined for each "deviated" class K%. Applied to an object X ∈ K%, the action delivers update A%(x) of the object. The goal is in constructing a classification algorithm that applied repeatedly (small number of times) to the objects of L, moves the objects (correspondingly, the elements of K) to the "normal" class. In this way, the static recognition action is transferred to a dynamic domain. This paper is continuing the discussion on the "normal" class classification problem, its theoretical postulations, possible use cases, and advantages of using logical-combinatorial approaches in solving these dynamic recognition problems. Some light relation to the topics like reinforcement learning, and recurrent neural networks are also provided. Copyright © 2021, The Authors. All rights reserved.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

A Learning Convolutional Neural Network Approach for Network Robustness Prediction

arXiv

引用

arXiv 2022年

作者： Lou, Yang Wu, Ruizi Li, Junli Wang, Lin Li, Xiang Chen, Guanrong The Department of Computing and Decision Sciences Lingnan University Hong Kong The Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China The College of Computer Science Sichuan Normal University Chengdu610066 China The Department of Automation Shanghai Jiao Tong University Shanghai200240 China The Institute of Complex Networks and Intelligent Systems Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai201210 China The Department of Control Science and Engineering Tongji University Shanghai200240 China The Department of Electrical Engineering City University of Hong Kong Hong Kong

Network robustness is critical for various societal and industrial networks again malicious attacks. In particular, connectivity robustness and controllability robustness reflect how well a networked system can maintain its connectedness and controllability against destructive attacks, which can be quantified by a sequence of values that record the remaining connectivity and controllability of the network after a sequence of node- or edge-removal attacks. Traditionally, robustness is determined by attack simulations, which are computationally very time-consuming or even practically infeasible. In this paper, an improved method for network robustness prediction is developed based on learning feature representation using convolutional neural network (LFR-CNN). In this scheme, higher-dimensional network data are compressed to lower-dimensional representations, and then passed to a CNN to perform robustness prediction. Extensive experimental studies on both synthetic and real-world networks, both directed and undirected, demonstrate that 1) the proposed LFR-CNN performs better than other two state-of-the-art prediction methods, with significantly lower prediction errors;2) LFR-CNN is insensitive to the variation of the network size, which significantly extends its applicability;3) although LFR-CNN needs more time to perform feature learning, it can achieve accurate prediction faster than attack simulations;4) LFR-CNN not only can accurately predict network robustness, but also provides a good indicator for connectivity robustness, better than the classical spectral measures. © 2022, CC BY.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Reconfigurable Intelligent Surface Enhanced Wireless Localization: Phase Optimization for Malicious Interference Mitigation

引用

IEEE Transactions on Communications 2025年

作者： Zhang, Yi Xie, Yajing Wang, Lijia Liwang, Minghui Wang, Xianbin Xiamen University Ministry of Education of China Department of Information and Communication Engineering Key Laboratory of Multimedia Trusted Perception and Efficient Computing Xiamen China Tongji University Shanghai Research Institute for Intelligent Autonomous Systems Department of Control Science and Engineering Shanghai China Western University Department of Electrical and Computer Engineering ON Canada

Recently, unmanned aerial vehicles (UAVs) and reconfigurable intelligent surfaces (RISs) have merged as important enabling technologies for localization coverage extension and localization accuracy improvement under signal blockage and malicious interference conditions. However, most existing works assume known locations of jammers, which is generally impractical in real-world networks. To overcome this challenge, we propose a novel RIS-enhanced wireless localization framework against malicious interference with the support of either narrowband or orthogonal frequency division multiplexing (OFDM) pilot signals. A two-stage anti-jamming localization approach is developed to first estimate the unknown channel and signal information of the jammer and then localize the user’s position by eliminating the jamming signal. More importantly, we utilize the full potential of RIS to improve localization accuracy by optimizing the phase shift profile during the iterative process. Extensive simulation results demonstrate the commendable performance of our proposed framework, which can not only mitigate the jamming effect but also achieve better localization accuracy, offering a good reference for future heterogeneous and complex wireless networks. © 1972-2012 IEEE.

关键词： Frequency division multiplexing

来源：评论

学校读者我要写书评

暂无评论

A Survey of Robot Manipulation in Contact

arXiv

引用

arXiv 2021年

作者： Suomalainen, Markku Karayiannidis, Yiannis Kyrki, Ville Center of Ubiquitous Computing Faculty of Information Technology and Electrical Engineering University of Oulu Finland Systems and Control Department of Electrical Engineering Chalmers University of Technology Gothenburg Sweden Intelligent Robotics research group Department of Electrical Engineering and Automation School of Electrical Engineering Aalto University Helsinki Finland

In this survey, we present the current status on robots performing manipulation tasks that require varying contact with the environment, such that the robot must either implicitly or explicitly control the contact force with the environment to complete the task. Robots can perform more and more manipulation tasks that are still done by humans, and there is a growing number of publications on the topics of 1) performing tasks that always require contact and 2) mitigating uncertainty by leveraging the environment in tasks that, under perfect information, could be performed without contact. The recent trends have seen robots perform tasks earlier left for humans, such as massage, and in the classical tasks, such as peg-in-hole, there is a more efficient generalization to other similar tasks, better error tolerance, and faster planning or learning of the tasks. Thus, in this survey we cover the current stage of robots performing such tasks, starting from surveying all the different in-contact tasks robots can perform, observing how these tasks are controlled and represented, and finally presenting the learning and planning of the skills required to complete these tasks. © 2021, CC BY.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Method of Robotic Process Automation in Software Testing Using Artificial Intelligence

Method of Robotic Process Automation in Software Testing Usi...

引用

International Conference on Advanced Computer information Technologies (ACIT)

作者： Nataliya Yatskiv Solomiya Yatskiv Anatoliy Vasylyk Department for Information and Computing Systems and Control Ternopil National Economic University Ternopil Ukraine Department of Computer Science Ternopil National Economic University Ternopil Ukraine

ISBN: (数字)9781728167602

ISBN: (纸本)9781728167619

Robotic process automation (RPA) offers numerous benefits over typical software for test automation. It allows saving money and freeing up human resources without any modifications in the processes and implemented solutions. Despite many advantages, RPA solution has limited functionality and it is not able to automatically adapt to changes in the system without human interaction. One of the technologies that may be used to leverage these disadvantages is Artificial Intelligence (AI). AI can facilitate process automation by using the intelligent decision making and interface analysis. In this paper the main approaches of RPA usage, their advantages and disadvantages are investigated. This paper describes the proposed method for software test automation with RPA which allows to make RPA software more flexible and decrease human involvement in the support processes.

关键词： Automation Artificial intelligence Software Tools Business Computer vision

来源：评论

学校读者我要写书评

暂无评论

Depth-Aware Multi-Modal Fusion for Generalized Zero-Shot Learning

Depth-Aware Multi-Modal Fusion for Generalized Zero-Shot Lea...

引用

IEEE International Conference on Industrial Informatics (INDIN)

作者： Weipeng Cao Xuyang Yao Zhiwu Xu Yinghui Pan Yixuan Sun Dachuan Li Bohua Qiu Muheng Wei Guangdong Laboratory of Artificial Intelligence and Digital Economy (Shenzhen) Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Stony Brook University New York United States Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China ZhenDui Industry Artificial Intelligence Co. Ltd Shenzhen China Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China

ISBN: (数字)9798331527471

ISBN: (纸本)9798331527488

Realizing Generalized Zero-Shot Learning (GZSL) based on large models is emerging as a prevailing trend. However, most existing methods merely regard large models as black boxes, solely leveraging the features output by the final layer while disregarding potential performance enhancements from other layers. Indeed, numerous researchers have visually depicted variations in the features learned across different layers of neural networks. Motivated by this observation, we propose a Vision Transformer (ViT)-based GZSL method named Depth-Aware Multi-Modal ViT (DAM2ViT), which exploits multi-level features of ViT. DAM2ViT incorporates a multi-modal interaction block to align semantic information of categories across multiple layers, thereby augmenting the model's capacity to learn associations between visual and semantic spaces. Extensive experiments conducted on three benchmark datasets (i.e., CUB, SUN, AWA2) have showcased that DAM2ViT achieves competitive results compared to state-of-the-art methods.

关键词： Visualization Adaptation models Semantics Zero shot learning Neural networks Termination of employment Transformers Market research Sun Optimization

来源：评论

学校读者我要写书评

暂无评论

A Lossless Image Compression Algorithm Based On Group Encoding

A Lossless Image Compression Algorithm Based On Group Encodi...

引用

International Conference on Advanced Computer information Technologies (ACIT)

作者： Vasyl Koval Vasyl Yatskiv Igor Yakymenko Diana Zahorodnia Department of Information Computing Systems and Control Ternopil National Economic University Ternopil city 8 Chekhova str. Ukraine Department of Cyber Security Ternopil National Economic University Ternopil city 8 Chekhova str. Ukraine

ISBN: (数字)9781728167602

ISBN: (纸本)9781728167619

This paper considers a new lossless image compression algorithm that provides reduction of data redundancy in video processing systems. To achieve the high compression level group encoding approach is proposed. The experimental research shows that proposed algorithm provides 1.33 times better compression quality index than the Run Length Encoding (RLE) algorithm.

关键词： Image coding Image color analysis Channel coding Image segmentation Arrays

来源：评论

学校读者我要写书评

暂无评论

Conception of Ontology for Computer Methods of Paintings Analysis

Conception of Ontology for Computer Methods of Paintings Ana...

引用

2019 International Multi-Conference on Engineering, Computer and information Sciences, SIBIRCON 2019

作者： Beloozerov, Viktor Murashov, Dmitrij Trusova, Yuliya Berezin, Aleksej Ivanova, Ekaterina All-Russia Institute for Scientific and Technical Information Department for Classification Systems Development Moscow Russia Institute of Educational Informatics Federal Research Center 'Information and Control' Moscow Russia A. A. Dorodnicyn Computing Center Federal Research Center 'Information and Control' Moscow Russia State Historical Muzeum Restoration Department Moscow Russia Ilya Glazuvov Russian Academy of Painting Sculpture and Architecture Department of Painting Restoration Moscow Russia

ISBN: (纸本)9781728144016

This paper describes the procedure of developing the 'OntArt' ontology for the subject area 'Attribution and restoration of works of easel oil painting'. Special attention is paid to the domain of computer methods application. The basis of the work is a previously developed thesaurus of this domain. The conceptual shell of the original thesaurus descriptors is the standard CIDOC CRM framework, which binds domain concepts to abstract philosophical categories. In order to connect particular concepts with abstract categories, it is proposed to include 21 intermediate-level conceptual classes in the CIDOC CRM structure. Thus, we have built a formalized structure of concepts for the area of attribution and restoration of painting, ranging from the highest philosophical abstractions to specialized methods of computer analysis of picture images. This structure includes about 1300 terms in Russian. The English part has about 500 terms and is replenished as the interlanguage equivalence of the terms is agreed. In the part of vocabulary of computer methods, we have a full bilingual ontology with one-To-one correspondence of the Russian and English versions. The current version of the ontology is implemented as a TiddlyWiki software module and is publicly available. © 2019 IEEE.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Mathematical modeling of the synthesis process of vinyl acetate 5

Mathematical modeling of the synthesis process of vinyl acet...

引用

5th International Scientific and Practical Conference on Virtual Simulation, Prototyping and Industrial Design 2018, VSPID 2018

作者： Arapov, D. Tikhomirov, S. Podvalny, S. Denisenko, V. Avcinov, I. Higher Mathematics and Information Technology Voronezh State University of Engineering Technologies 19 Revolution Avenue Voronezh394036 Russia Information and Control Systems Voronezh State University of Engineering Technologies 19 Revolution Avenue Voronezh394036 Russia Head of the Department of Automated and Computing Systems Voronezh State Technical University 14 Moskovsky Avenue Voronezh394026 Russia

A complete mathematical modeling of the technological process of manufacturing vinyl acetate monomer by vapor-phase method has been implemented. The model is partial differential equations of the material and energy balance and catalyst aging. An algorithm for an integrated equation based on the second-order Gregg-Bulirsh-Shter rectangle symbol has been developed. The error in modeling the process is equal (CH3COOCH=CH2) ± 5.4% rel. for the target matter, and (CO2) ± 6.4% rel. for the secondary substance The kinetic coefficients of differential equations, namely the pre-exponential factors and the activation energy have been refined. The obtained data of the modeling of the vapor-phase manufacturing process of vinyl acetate are shown in the form of tables and graphic three-dimensional dependencies of quality indicators on technological parameters. © 2019 IOP Publishing Ltd. All rights reserved.

关键词： Activation energy

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：