检索结果-内蒙古大学图书馆

Descriptive Algorithmic Schemes as Image Analysis Machine Programs 1

26th International Conference on Pattern Recognition, ICPR 2022

作者： Gurevich, Igor Yashina, Vera Federal Research Center "Computer Science and Control" of the Russian Academy of Sciences Building 2 44 Vavilov Street Moscow119333 Russia

ISBN: (数字)9783031377426

ISBN: (纸本)9783031377419

This article is continued description of an original approach to the definition and description of a Turing machine (TM) for implementing descriptive image analysis methods based on an information structure for generating descriptive algorithmic schemes for automating image analysis. The fundamental problem, to which the subject of the study belongs, is the automation of extracting information from images that is necessary for making intelligent decisions. One of the important and promising areas of research in this problem is the automation of the choice of a method for solving the problem of image analysis. A necessary condition for such automation is a comparative analysis and optimization of the image analysis algorithms, which, in turn, requires estimates of the complexity and efficiency of algorithms and a universal calculator to obtain them. One of the strategic goals for the development of descriptive image analysis is the study of models of image analysis processes. To do this, it is proposed to define and build an ‘‘Image Analysis Machine,’’ i.e., TMs specialized for processing spatial information. A method for determining a TM for modeling descriptive algorithmic schemes for image analysis is proposed and described. This machine can also be used to evaluate the mathematical characteristics of image analysis algorithms. © 2023, Springer Nature Switzerland AG.

关键词： Turing machines

来源：评论

学校读者我要写书评

暂无评论

Linear Regression-Based Autonomous Intelligent Optimization for Constrained Multiobjective Problems

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第9期5卷 4620-4634页

作者： Wang, Yan Sun, Xiaoyan Zhang, Yong Gong, Dunwei Hu, Hejuan Zuo, Mingcheng China University of Mining and Technology School of Information and Control Engineering Jiangsu Xuzhou221116 China Qingdao University of Science and Technology College of Automation and Electronic Engineering Shandong Qingdao266061 China China University of Mining and Technology Artificial Intelligence Research Institute Jiangsu Xuzhou221116 China

It is very challenging to autonomously generate algorithms suitable for constrained multiobjective optimization problems due to the diverse performance of existing algorithms. In this article, we propose a linear regression (LR)-based autonomous intelligent optimization method. It first extracts typical features of a constrained multiobjective optimization problem by focused sampling to form a feature vector. Then, a LR model is designed to learn the relationship between optimization problems and intelligent optimization algorithms (IOAs). Finally, the trained model autonomously generates a suitable IOA by inputting the feature vector. The proposed method is applied to six constrained multiobjective benchmark test sets with various characteristics and compared with seven popular optimization algorithms. The experimental results verify the effectiveness of the proposed method. In addition, the proposed method is used to solve the operation optimization problems of an integrated coal mine energy system, and the experimental results show its practicability. © 2020 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Intelligent Methods for Restructuring Digital science-Intensive Solutions of Network Innovation Institutions 6th

Intelligent Methods for Restructuring Digital Science-Intens...

引用

6th Computational Methods in Systems and Software, CoMeSySo 2022

作者： Zubkov, A.V. Pronichkin, S.V. Kasymov, O.K. Gilka, V.V. Rozaliev, V.L. Volgograd State Technical University Volgograd Russia Federal Research Center "Computer Science and Control" of Russian Academy of Sciences Moscow Russia

ISBN: (纸本)9783031214349

The success of any method of restructuring the digital science-intensive solutions of network innovation institutions depends on the correct choice of representative indicators of the state of innovative enterprises, the forms of links between them, as well as the volume and composition of the data sample under which the model is built. Few authors in their research use exactly the built complex of models, most scientific works are limited to individual coefficients or discriminant indicators. For a systematic analysis of the restructuring of digital knowledge-intensive solutions, it is proposed to jointly use intelligent predicative and normative models. A decision support system has been developed for the analysis of complex scientific and technical systems based on dominance verbal scales. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Decision support system Digital economy Innovations science-intensive solutions

来源：评论

学校读者我要写书评

暂无评论

A Cycling Friendliness Measurement System for Dockless Bike-sharing Dynamic Scheme

Journal of Network Intelligence

引用

Journal of Network Intelligence 2023年第4期8卷 1557-1569页

作者： Li, Ben Huang, Dejuan Liao, Lyuchao Xiao, Hankun Ma, Huankun Fujian Provincial Universities Key Laboratory of Industrial Control Data Analysis Fujian Provincial Universities Engineering Research Center for Intelligent Driving Technology School of Transportation Fujian University of Technology Fuzhou350118 China

The rapid growth of Dockless Bike-sharing (DLBS) provides an excellent opportunity to meet the strong demand for convenient green travel services. However, with the increasing number of cyclists and DLBS, the issue of DLBS friendliness faces several challenges: (1) the hardness of renting in empty fences;(2) the difficulty of parking in overload fences;(3) different road conditions have different effects on cycling friendliness. To deal with these challenges, we design a DLBS friendliness (DLBSF) sys-tem, consisting of DLBS recommendation (DLBSR) system and DLBS scoring (DLBSS) system to comprehensively alleviate the problem of decreasing friendliness. The former optimizes cycling friendliness by first identifying the overload fences where the morning peak tide phenomenon is most prominent, and then provides guidance for cyclists to park the nearest idle fences. The latter gives the riding friendliness scheme by scoring and analyzing each road section to improve friendliness. Experiments on real-world DLBS datasets verify the accuracy, effectiveness, and feasibility of the proposed DLBSF system. © 2023, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Fences

来源：评论

学校读者我要写书评

暂无评论

Analysis of Block Stokes-Algebraic Multigrid Preconditioners on GPU Implementations 16th

Analysis of Block Stokes-Algebraic Multigrid Preconditioner...

引用

16th International Conference on Parallel Computational Technologies, PCT 2022

作者： Evstigneev, N.M. Federal Research Center "Computer Science and Control" of the Russian Academy of Sciences Moscow Russia

ISBN: (纸本)9783031116223

The Stokes and Oseen problems are saddle-point problems common to many methods aimed at the efficient solution of incompressible flows. There are basically two methods for solving saddle problems – coupled (solution of the whole system) and segregated (fractional step method). In this paper, we consider the first approach as the most efficient for steady state problems, in the form of block-triangular preconditioning and its variants. The most difficult part is the design of an efficient preconditioner for the saddle-point problem. Different variants of preconditioning and formulations of pressure Schur complement approximate matrices are considered. The main question is: Given that computations on Graphics Processing Units (GPUs) are cheaper and less energy demanding than computations only on Central Processing Units (CPUs), can an efficient preconditioner be implemented in GPU-only calculation mode? We apply these preconditioners with the most advanced Algebraic Multigrid methods (AMG) based on the AMGCL framework developed by D. Demidov. The AMGCL framework is extensively modified for the purpose of testing in GPU-only calculation modes. To formulate the Stokes problem, we use the classical MAC method on a staggered grid and consider different types of 3D problems. It is concluded that GPU-only computations can be approximately 3–4 times more efficient than CPU+GPU implementations and about 20 times more efficient than CPU-only implementations of the original AMGCL framework. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

New Method for Automating the Diagnostic Analysis of Human Fundus Images Produced by Optical Coherent Tomography Angiography. research and Software Kit Realization 1

引用

26th International Conference on Pattern Recognition, ICPR 2022

作者： Gurevich, I.B. Yashina, V.V. Tleubaev, A.T. Federal Research Center "Computer Science and Control" Russian Academy of Sciences Building 2 44 Vavilov street Moscow119333 Russia

ISBN: (数字)9783031377426

ISBN: (纸本)9783031377419

This article presents the results of the joint work of specialists in the field of image analysis and ophthalmologists on the task of analyzing images obtained by the method of optical coherence tomography angiography. A descriptive algorithmic scheme for analyzing images obtained using optical coherence tomography angiography is built to automate the detection of pathological changes in the morphometric characteristics of the fundus. The algorithmic scheme is based on the methods of image processing, analysis, and recognition. The previously developed feature space is supplemented and modified, based on which it is possible to identify pathological changes in the structure of the choroid plexuses of the human retina. It was possible to improve the accuracy of classifying images of healthy and pathological eyes, as well as significantly increasing the accuracy of classification of borderline cases. Software is created that makes it possible to accurately carry out differential diagnostics of the normal state of vessels from the pathological one in the offline mode, which increases its diagnostic value. It is planned to achieve higher classification accuracy results for all three cases. © 2023, Springer Nature Switzerland AG.

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

A nanoflower-on-nanowire heterogeneous electrocatalyst for enhanced interfacial water activation in nitrate reduction reaction

引用

Nano research 2025年第2期18卷 173-183页

作者： Jingwen Yu Yunliang Liu Cunhao Fan Naiyun Liu Jingya Yin Yaxi Li Yuanyuan Cheng Xinya Yuan Xinyue Zhang Yixian Liu Sanjun Fan Lei Xu Haitao Li Institute for Energy Research School of Chemistry and Chemical EngineeringJiangsu UniversityZhenjiang 212013China Qingdao Municipal Center for Disease Control and Prevention Qingdao 266033China Department of Chemistry and Biochemistry The Ohio State UniversityColumbusOhio 43210USA Jiangsu Engineering Technology Research Center of Biomass Composites and Addictive Manufacturing Institute of Agricultural Facilities and EquipmentJiangsu Academy of Agricultural SciencesNanjing 210014China Key Laboratory for Protected Agricultural Engineering in the Middle and Lower Reaches of Yangtze River Ministry of Agriculture and Rural AffairsNanjing 210014China

Electrocatalytic nitrate reduction reaction(NitRR)is an efficient route for simultaneous wastewater treatment and ammonia production,but the conversion of NO_(3)–to NH_(3) involves multiple electron and proton transfer processes and diverse ***,developing ammonia catalysts with superior catalytic activity and selectivity is an urgent *** distinctive electronic structure of Cu enhances the adsorption of nitrogen-containing intermediates,but the insufficient activation capability of Cu for interfacial water restricts the generation of reactive hydrogen and inhibits the hydrogenation *** this work,a Ce-doped CuO catalyst(Ce_(10)/CuO)was synthesized by in situ oxidative etching and *** redox of Ce^(3+)/Ce^(4+)enables the optimization of the electronic structure of the catalyst,and the presence of Ce^(3+)as a defect indicator introduces more oxygen *** results demonstrate that Ce10/CuO provides an impressive ammonia yield of 3.88±0.14 mmol·cm^(–2)·h^(–1) at 0.4 V *** hydrogen electrode(RHE)with an increase of 1.04 mmol·cm^(–2)·h^(–1) compared to that of pure CuO,and the Faradaic efficiencies(FE)reaches 93.2%±3.4%.In situ characterization confirms the doping of Ce facilitates the activation and dissociation of interfacial water,which promotes the production of active hydrogen and thus enhances the ammonia production efficiency.

关键词： active hydrogen electron transfer nitrate ammonia

来源：评论

学校读者我要写书评

暂无评论

Seasonal variations, temperature dependence, and sources of size-resolved PM components in Nanjing, east China

引用

Journal of Environmental sciences 2022年第11期34卷 175-186页

作者： Mingjie Xie Wei Feng Shuyan He Qin’geng Wang Collaborative Innovation Center of Atmospheric Environment and Equipment Technology Jiangsu Key Laboratory of Atmospheric Environment Monitoring and Pollution ControlSchool of Environmental Science and EngineeringNanjing University of Information Science&TechnologyNanjing 210044China State Key Laboratory of Pollution Control and Resources Reuse School of the EnvironmentNanjing UniversityNanjing 210023China

Size-segregated ambient particulate matter(PM) samples were collected seasonally in suburban Nanjing of east China from 2016 to 2017 and chemically speciated. In both fine( 2.1 μm, PM>2.1) PM, organic carbon(OC) a... 详细信息

Size-segregated ambient particulate matter(PM) samples were collected seasonally in suburban Nanjing of east China from 2016 to 2017 and chemically speciated. In both fine(< 2.1μm, PM2.1) and coarse(> 2.1 μm, PM>2.1) PM, organic carbon(OC) accounted for the highest fractions(26.9% ± 10.9% and 23.1% ± 9.35%) of all measured species, and NO3-lead in average concentrations of water-soluble inorganic ions(WSIIs). The size distributions of measured components were parameterized using geometric mean diameter(GMD). GMD values of NO_(3)^(-), Cl^(-), OC, and PM for the whole size range varied from < 2.1 μm in winter to > 2.1μm in warm seasons, which was due to the fact that the size distributions of semi-volatile components(e.g., NH4NO3, NH4Cl, and OC) had a dependency on the ambient *** OC, elemental carbon(EC), and elements, NH_(4)^(+), NO_(3)^(-), and SO_(4)^(2-)exhibited an increase trend in GMD values with relative humidity, indicating that the hygroscopic growth might also play a role in driving seasonal changes of PM size distributions. Positive matrix factorization was performed using compositional data of fine and coarse particles, respectively. The secondary formation of inorganic salts contributing to the majority(> 70%) of fine PM and 20.2% ± 19.9% of speciated coarse PM. The remaining coarse PM content was attributed to a variety of dust sources. Considering that coarse and fine PM had comparable mass concentrations, more attention should be paid to local dust emissions in future air quality plans.

关键词： Particulate matter Size distribution Seasonal variation Semi-volatility Source apportionment

来源：评论

学校读者我要写书评

暂无评论

Multi-omics graph convolutional networks for digestive system tumour classification and early-late stage diagnosis

引用

CAAI Transactions on Intelligence Technology 2024年第6期9卷 1572-1586页

作者： Lin Zhou Zhengzhi Zhu Hongbo Gao Chunyu Wang Muhammad Attique Khan Mati Ullah Siffat Ullah Khan School of Information Science and Technology University of Science and Technology of ChinaHefeiAnhuiChina Anhui Engineering Research Center on Information Fusion and Control of Intelligent Robot WuhuAnhuiChina Department of Breast Center West District of The Affiliated Hospital of University of Science and Technology of ChinaDivision of Life Sciences and MedicineUniversity of Science and Technology of ChinaHefeiAnhuiChina Institute of Advanced Technology University of Science and Technology of ChinaHefeiAnhuiChina School of Electrical and Electronic Engineering Nanyang Technological UniversitySingaporeSingapore School of Biological and Environmental Engineering Chaohu UniversityChaohu Regional Collaborative Technology Service Center for Rural RevitalizationHefeiChina Department of Artificial Intelligence College of Computer Engineering and SciencePrince Mohammad Bin Fahd UniversityAl-KhobarSaudi Arabia School of Automation Northwestern Polytechnical UniversityXi'anShaanxiChina Institute of Engineering and Computing Science University of Science and Technology of BannuKPKBannuPakistan

The prevalence of digestive system tumours(DST)poses a significant challenge in the global crusade against *** neoplasms constitute 20%of all documented cancer diagnoses and contribute to 22.5%of cancer-related *** accurate diagnosis of DST is paramount for vigilant patient monitoring and the judicious selection of optimal *** this challenge,the authors introduce a novel methodology,denominated as the Multi-omics Graph Transformer Convolutional Network(MGTCN).This innovative approach aims to discern various DST tumour types and proficiently discern between early-late stage tumours,ensuring a high degree of *** MGTCN model incorporates the Graph Transformer Layer framework to meticulously transform the multi-omics adjacency matrix,thereby illuminating potential associations among diverse samples.A rigorous experimental evaluation was undertaken on the DST dataset from The Cancer Genome Atlas to scrutinise the efficacy of the MGTCN *** outcomes unequivocally underscore the efficiency and precision of MGTCN in diagnosing diverse DST tumour types and successfully discriminating between early-late stage DST *** source code for this groundbreaking study is readily accessible for download at https://***/bigone1/MGTCN.

关键词： digestive system tumors early-late stage multi-omics tumor types

来源：评论

学校读者我要写书评

暂无评论

Decision Support System for Multi-criteria Information-Logical Analysis of Scientific and Technical Projects of Innovative Enterprises 6th

Decision Support System for Multi-criteria Information-Logic...

引用

6th Computational Methods in Systems and Software, CoMeSySo 2022

作者： Kuznetsova, A.S. Kulikova, Y.V. Rozaliev, V.L. Pronichkin, S.V. Kasymov, O.K. Volgograd State Technical University Volgograd Russia Federal Research Center "Computer Science and Control" of Russian Academy of Sciences Moscow Russia

ISBN: (纸本)9783031214349

The search for effective approaches to the analysis of scientific and technical projects, taking into account the conditions for the development of a modern competitive environment, is one of the main tasks of managing innovative enterprises. The determining factor in the effective functioning of the organizational and economic mechanism of scientific research and development is the successful operation of all its constituent elements. A decision support system has been developed that implements a conceptual model of the organizational and economic mechanism for evaluating scientific and technical projects. For multi-criteria information-logical analysis of scientific and technical projects, it is proposed to use technical and organizational subsystems on multisets of binary relations. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Decision making Knowledge economy Scientific research System approach

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：