检索结果-内蒙古大学图书馆

Hierarchical Residual Embedding Network for Real-Time De-focus Blur Detection

Journal of Physics: Conference Series 2021年第1期1815卷

作者： Chunlei Zhang Jing Nie Xiao Zheng Electronic Engineering College Naval University of Engineering Wuhan 430033 China Teaching and Research Support Center Naval University of Engineering Wuhan 430033 China School of Computer Science National University of Defense Technology Changsha 410073 China

Defocus blur detection, as an important pre-processing step of image processing, has attracted more and more attention. Albeit great success has been made, there are still several challenges for accurate defocus blur detection, such as the interference of background clutter, sensitivity to scales, missing boundary details and large computational burden. For handling these issues, we present a deep neural network which hierarchically embeds residual learning blocks for defocus blur detection. Based on the feature pyramid structure, we extract deep features with varying scales via utilizing a backbone fully convolutional network and generate a coarse score map by using the last layer of feature maps. Then we design a hierarchical residual embedding module to fuse different levels of features in a layer-wise manner. By embedding different layer-wise features in the top-down pathway, coarse-level semantic information from the deep layers can be seamlessly propagated to shallow layers, while fine details in the shallow layers can be used to refine the boundary between out-of-focus and in-focus regions. For each layer, a side output is generated by using a residual learning block. For capturing multi-scale information, the multiple side outputs of different layers are fed into a designed fusion block for yielding the final blur map result. Experimental results on two commonly used datasets show that our proposed network can more accurately locate the defocus blur regions with sharpened details being well preserved when compared to other previous state-of-the-arts. In addition, our approach is fast as well and can run at a speed of more than 25 FPS when processing an image with size 427 x 640.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design of an Infological Model for Prediction of Problems during Drilling Using Machine Learning and Systems Analysis

引用

IOP Conference Series: Earth and Environmental science 2022年第4期988卷

作者： A L Zolkin V D Munister R V Faizullin N N Smoktal Ph.D. in Engineering Science Senior Lecturer of Computer and Information Sciences Department of the Povolzhskiy State University of Telecommunications and Informatics Department of Mathematical Methods and Computer-Aided Design Private educational institution 'Donetsk Academy of Transport' Department of Enterprise Economics State educational institution of higher professional education 'Donetsk National Technical University' Associate Professor of the Department of Information Technologies in Public Administration Institute of Management Technologies MIREA — Russian technological university Teacher at the Department of 'Renewable Energy Sources and Electrical Systems and Networks' Sevastopol State University

The article deals with the actual problem of identification of probabilistic processes as a result of the operation of drilling rigs in the oil industry. The world experience of finding ways to solve optimal forecasting tools using machine learning is summarized. Mnemonic rule for the implementation of classification and ranking systems in the detection of feedbacks as probable indicators of complications of ongoing technological processes is implemented through the description of the formal model of the drilling process in form of a hidden Markov model. The results of evaluation of the developed mathematical apparatus in the form of predictive analytics and a cut of basic complications in the drilling process are presented. An infological diagram of the developed architectural solution of the analysis project is proposed. The results of the control algorithms formalization are given in conclusion. These results allow to ensure the effective procees modes of equipment operation and make it possible to save electricity and water.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cognitive Robotic Architecture for Semi-Autonomous Execution of Manipulation Tasks in a Surgical Environment

Cognitive Robotic Architecture for Semi-Autonomous Execution...

引用

2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Giacomo De Rossi Marco Minelli Alessio Sozzi Nicola Piccinelli Federica Ferraguti Francesco Setti Marcello Bonfé Cristian Secchi Riccardo Muradore Department of Computer Science University of Verona Verona Italy Department of Engineering Sciences and Methods University of Modena and Reggio Emilia Reggio Emilia Italy Department of Engineering University of Ferrara Ferrara Italy

The development of robotic systems with a certain level of autonomy to be used in critical scenarios, such as an operating room, necessarily requires a seamless integration of multiple state-of-the-art technologies. In this paper we propose a cognitive robotic architecture that is able to help an operator accomplish a specific task. The architecture integrates an action recognition module to understand the scene, a supervisory control to make decisions, and a model predictive control to plan collision-free trajectory for the robotic arm taking into account obstacles and model uncertainty. The proposed approach has been validated on a simplified scenario involving only a da VinciO surgical robot and a novel manipulator holding standard laparoscopic tools.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learn to compress CSI and allocate resources in vehicular networks

arXiv

引用

arXiv 2019年

作者： Wang, Liang Ye, Hao Liang, Le Li, Geoffrey Ye Key Laboratory of Modern Teaching Technology Ministry of Education Xi'an710062 China School of Computer Science Shaanxi Normal University Xi'an710119 China School of Electrical and Computer Engineering Georgia Institute of Technology AtlantaGA30332 United States

Resource allocation has a direct and profound impact on the performance of vehicle-to-everything (V2X) networks. In this paper, we develop a hybrid architecture consisting of centralized decision making and distributed resource sharing (the C-Decision scheme) to maximize the long-term sum rate of all vehicles. To reduce the network signaling overhead, each vehicle uses a deep neural network to compress its observed information that is thereafter fed back to the centralized decision making unit. The centralized decision unit employs a deep Q-network to allocate resources and then sends the decision results to all vehicles. We further adopt a quantization layer for each vehicle that learns to quantize the continuous feedback. In addition, we devise a mechanism to balance the transmission of vehicle-to-vehicle (V2V) links and vehicle-to-infrastructure (V2I) links. To further facilitate distributed spectrum sharing, we also propose a distributed decision making and spectrum sharing architecture (the D-Decision scheme) for each V2V link. Through extensive simulation results, we demonstrate that the proposed C-Decision and D-Decision schemes can both achieve near-optimal performance and are robust to feedback interval variations, input noise, and feedback noise. Copyright © 2019, The Authors. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

A Note on Comparison Between the Wiener Index and the Zagreb Indices

引用

Communications in Mathematical Research 2018年第4期34卷 296-302页

作者： YOU ZHI-FU HUANG YU-FEI Du Xian-kun School of Computer Science Guangdong Polytechnic Normal UniversityGuangzhou510665 Department of Mathematics Teaching Guangzhou Civil Aviation CollegeGuangzhou510403 不详

In this note, we correct a wrong result in a paper of Das et al. with regard to the comparison between the Wiener index and the Zagreb indices for trees （Das K C, Jeon H, Trinajstic N. The comparison between the Wiener index and the Zagreb indices and the eccentric connectivity index for trees. Discrete Appl. Math., 2014, 171：35 41）, and give a simple way to compare the Wiener index and the Zagreb indices for trees. Moreover, the comparison between the Wiener index and the Zagreb indices for unicyclic graphs is carried out.

关键词： Wiener index Zagreb indice tree unicyclic graph

来源：评论

学校读者我要写书评

暂无评论

A Doubly-Masked-Ballot Multi-questions Voting Scheme with Distributed Trust

A Doubly-Masked-Ballot Multi-questions Voting Scheme with Di...

引用

Computing Conference, 2019

作者： Szabo, Robert Telcs, Andras Department of Telecommunications and Media Informatics Budapest University of Technology and Economics Budapest Hungary Department of Computational Sciences Wigner Research Centre for Physics of the Hungarian Academy of Sciences Budapest Hungary Department of Computer Science and Information Theory Faculty of Electrical Engineering and Informatics Budapest University of Technology and Economics Budapest Hungary Department of Quantitative Methods Faculty of Business and Economics University of Pannonia Veszprem Hungary

ISBN: (纸本)9783030228675

We propose an electronic voting scheme for multiple questions voting based on masked ballots, homomorph counting, publicly verifiable secret sharing based tallying and public communication channels. In our scheme all on-line authority functions (authentication, candidate slate check, counting and tallying) are distributed among the active voters. Off-line authorities only prepare and distribute election secrets. We analyze our scheme for different adversary attacks and show that the maximum that the strongest adversary can achieve is a random attack. © 2019, Springer Nature Switzerland AG.

关键词： Security of data

来源：评论

学校读者我要写书评

暂无评论

RRLFSOR: An Efficient Self-Supervised Learning Strategy of Graph Convolutional Networks

arXiv

引用

arXiv 2021年

作者： Sun, Feng Ajith, Kumar V. Yang, Guanci Zhu, Qikui Zhang, Yiyun Zhang, Ansi Makwana, Dhruv Experimental Teaching Center for Liberal Arts Zhejiang Normal University Zhejiang Jinhua321004 China School of AI Bangalore560002 India Key Laboratory of Advanced Manufacturing Technology of Ministry of Education Guizhou University Guizhou Guiyang550025 China Department of Medical Imaging Western University LondonW1k 6NG Canada Engineering College Zhejiang Normal University Zhejiang Jinhua321004 China School of Mechanical Engineering Guizhou University Guizhou Guiyang550025 China Computer Science College Gujarat Technological University Bangalore560002 India

Graph Convolutional Networks (GCNs) are widely used in many applications yet still need large amounts of labelled data for training. Besides, the adjacency matrix of GCNs is stable, which makes the data processing strategy cannot efficiently adjust the quantity of training data from the built graph structures. To further improve the performance and the self-learning ability of GCNs, in this paper, we propose an efficient self-supervised learning strategy of GCNs, named randomly removed links with a fixed step at one region (RRLFSOR). RRLFSOR can be regarded as a new data augmenter to improve over-smoothing. RRLFSOR is examined on two efficient and representative GCN models with three public citation network datasets – Cora, PubMed, and Citeseer. Experiments on transductive link prediction tasks show that our strategy outperforms the baseline models consistently by up to 21.34% in terms of accuracy on three benchmark datasets. © 2021, CC BY-SA.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Learning graphons via structured gromov-wasserstein barycenters

arXiv

引用

arXiv 2020年

作者： Xu, Hongteng Luo, Dixin Carin, Lawrence Zha, Hongyuan Gaoling School of Artificial Intelligence Renmin University of China 59 Zhongguancun St Haidian District Beijing100872 China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China School of Computer Science and Technology Beijing Institue of Technology 5 Zhongguancun St Haidian District100811 China Department of ECE Duke University DurhamNC27708 United States School of Data Science Shenzhen Research Institute of Big Data Chinese University of Hong Kong Hong Kong

We propose a novel and principled method to learn a nonparametric graph model called graphon, which is defined in an infinite-dimensional space and represents arbitrary-size graphs. Based on the weak regularity lemma from the theory of graphons, we leverage a step function to approximate a graphon. We show that the cut distance of graphons can be relaxed to the Gromov-Wasserstein distance of their step functions. Accordingly, given a set of graphs generated by an underlying graphon, we learn the corresponding step function as the Gromov-Wasserstein barycenter of the given graphs. Furthermore, we develop several enhancements and extensions of the basic algorithm, e.g., the smoothed Gromov-Wasserstein barycenter for guaranteeing the continuity of the learned graphons and the mixed Gromov-Wasserstein barycenters for learning multiple structured graphons. The proposed approach overcomes drawbacks of prior state-of-the-art methods, and outperforms them on both synthetic and real-world data. The code is available at https://***/HongtengXu/SGWB-Graphon. © 2020, CC BY.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Güney-Hillery approach to Bell inequalities

引用

Physical Review A 2019年第5期99卷 052122-052122页

作者： Katarzyna Bolonek-Lasoń Piotr Kosiński Faculty of Economics and Sociology Department of Statistical Methods University of Lodz 41/43 Rewolucji 1905 Street Lodz 90-214 Poland Department of Computer Science Faculty of Physics and Applied Informatics University of Lodz 149/153 Pomorska Street Lodz 90-236 Poland

We analyze certain aspects of the group-theoretical approach to Bell inequalities proposed by Güney and Hillery. The general procedure for constructing the relevant group orbits is described. Using Hall theorem we determine the form of Bell inequality in the single-orbit case. It is shown that in this case the Bell inequality is not violated for a maximally entangled state generating trivial subrepresentation if the representation under consideration is real.

关键词： Nonlocality

来源：评论

学校读者我要写书评

暂无评论

Selected methodological and practical aspects of the multi-criteria method PVM

引用

Procedia computer science 2019年 159卷 2267-2278页

作者： Nermend Kesra Piwowarski Mateusz Wojciech Sałabun Department of Computational Methods in Experimental Economics Faculty of Economics and Management Institute of IT in Management University of Szczecin Mickiewicza 64 Szczecin 71-101 Poland Department of Artificial Intelligence Methods and Applied Mathematics Faculty of Computer Science and Information Technology West Pomeranian University of Technology in Szczecin ul. Żołnierska 49 71-210 Szczecin Poland

In multi-criteria decision support methods a significant participation of the decision maker is required. The obtained assessment is subjective, and the decision-making process is usually difficult to automate. Limiting interaction with the decision-maker, while maintaining the characteristics of multi-criteria analysis seems to be a desirable direction of methodological research. One of the solutions going in this direction is the original multi-criteria PVM method. The applicability of the method has been verified in the context of research on the assessment of EU countries in terms of ensuring healthy living conditions.

关键词： Multiple-Criteria Decision Analysis PVM Sustainable Development Goals

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：