检索结果-内蒙古大学图书馆

Ivannikov ISPras Open Conference (ISPras)

作者： Anastasiia Ryzhova Ilya Sochenkov Skoltech Institute of Science and Technology “Computer Science & Control” of the Russian Academy of Sciences FRC CSC RAS

The article is devoted to the customs classification of goods based on their textual descriptions. In our work we propose different machine and deep learning models for solving this task using two variants of datasets... 详细信息

关键词： Data models Random forests Deep learning Task analysis Libraries Logistics

来源：评论

学校读者我要写书评

暂无评论

On fusion schemes for multiclass object classification with reject in a given ensemble of sources 4

On fusion schemes for multiclass object classification with ...

引用

4th International Conference on Information Technology and Nanotechnology, ITNT 2018

作者： Lange, M.M. Ganebnykh, S.N. FRC Computer Science and Control of RAS Vavilov str. 40 Moscow Russia

Given ensemble of the different modality sources, we investigated two data fusion schemes for constructing metric-based multiclass classifiers with a reject option. The decisions made for the composite objects given by the collections of the source objects of the same class with one object per each source. The fusion schemes are based on using different compositions. The first scheme uses the composition of the decisions on the objects of the individual sources and this scheme is known as the fusion by the weighted majority vote or WMV scheme. The second scheme uses the composition in a form of the general dissimilarity measure between any pair of the composite objects. This scheme is original and it is called by GDM scheme. We constructed multiclass classifiers as the appropriate collections of NN or SVM elementary "class-vs-all" classifiers. We performed classification experiments in the ensemble of decorrelated components of face RGB images. We shown that GDM scheme gives fewer error rates with respect to WMV scheme. © 2018 Institute of Physics Publishing. All rights reserved.

关键词： Data fusion

来源：评论

学校读者我要写书评

暂无评论

The longtime global climatic consequences modeling of the Chicxulub asteroid impact event

引用

Journal of Physics: Conference Series 2021年第1期2090卷

作者： V P Parkhomenko Bauman Moscow State Technical University ul. Baumanskaya 2-ya 5/1 Moscow 105005 Russia Federal Research Center "Computer Science and Control" of the Russian Academy of Sciences (FRC CSC RAS) Moscow 119333 Russia

Studies indicate the mass death of a significant number of biological groups on Earth, in particular - dinosaurs, at the end of the Cretaceous period 66 million years ago. Currently, there are two main theories: large-scale volcanic eruptions and the asteroid impact that formed the Chicxulub crater (Mexico). The production of sulfur-containing gases from the Earth's surface layers vapors during impact is considered a main source of climatic effects, as they form stratospheric sulfate aerosols that block sunlight and thus cool the Earth's atmosphere and interfere with photosynthesis. It is presented an application of the 3-D coupled global hydrodynamic climate model of intermediate complexity, including ocean model, sea ice evolution model and energy - moisture balance atmosphere model to study this asteroid impact effects on the Earth's climate. The model continents and ocean depths distribution corresponds to Cretaceous period. A series of calculations with different residence times and deposition times of the stratosphere aerosol have been carried out. It was found that, depending on the stratosphere aerosol time parameters, the global annual average surface air temperature decreased by 18°C - 27°C, remained below zero for 4 - 30 years, and a recovery time of more than 30 years was observed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Modeling the influence of the Earth rotation axis position on the global climate variations

引用

Journal of Physics: Conference Series 2021年第1期1730卷

作者： V P Parkhomenko Bauman Moscow State Technical University ul. Baumanskaya 2-ya 5/1 Moscow 105005 Russia Federal Research Center 'Computer Science and Control' of the Russian Academy of Sciences (FRC CSC RAS) Moscow 119333 Russia

This study presents the results of numerical experiments to determine the Earth's climate when its rotation axis is displaced without changing the axis tilt to the ecliptic plane. There is some evidence of the possibility of this shift in the past. The calculations were carried out using a hydrodynamic three-dimensional global climate model, including blocks of atmosphere, thermohaline large-scale ocean circulation and sea ice. Numerical experiments demonstrate a significant temperature changes throughout the world. A large area of Antarctica warmed up to temperatures above 15 ° C. This is reason of intense melting of glaciers for a long time. Significant warming of the Arctic Ocean will lead to sea ice melting in the Arctic. Strong changes in temperature and ice cover lead to significant changes in horizontal ocean circulation. A procedure is proposed for calculating wind speed in atmosphere energy - moisture balance model. It is based on the geostrophic approach, taking into account the thermal component of the wind, and introducing the mechanism of friction on the underlying surface. A technique has been developed for the formation of the necessary maps and the relationships between them when turning the Earth rotation axis or using new cartographic data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparison of different convolution neural network architectures for the solution of the problem of emotion recognition by facial expression 8

Comparison of different convolution neural network architect...

引用

Selected Papers of the 8th International Conference "Distributed Computing and Grid-Technologies in science and Education", GRID 2018

作者： Vorontsov, A.O. Averkin, A.N. Dubna State University Institute of System Analysis and Management Universitetskaya str. 19 Dubna Moscow Reg.141980 Russia FRC Computer Science and Control of RAS Vavilova Str. 40 Moscow117333 Russia

In this paper the usage of convolution neural networks has been considered for solving the problem of emotion recognition by images with facial expression. Emotion recognition is a complex task and the result of recognition is highly dependent on the choice of the neural network architecture. In this paper various architectures of convolutional neural networks were reviewed and training experiments were conducted on selected neural networks. The overviewed neural network architectures were trained on FER2013 and AffectNet datasets, both widely used for emotion recognition experiments. A comparison of the selected neural network architectures was made using the accuracy metrics. At the end of this paper the comparative analysis was made and obtained results were overviewed. © 2018 Anton O. Vorontsov, Alexey N. Averkin.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Processing of x-ray tomographic projections collected in different schemes

引用

AIP Conference Proceedings 2021年第1期2356卷

作者： M. V. Chukalina V. V. Arlazarov D. P Nikolaev 1Institute for Information Transmission Problems (Kharkevich Institute) RAS Bolshoy Karetny per. 19 build.1 127051 Moscow Russia 2Smart Engines Service LLC Skolkovo 121205 Moscow Russia 3FRC “Computer Science and Control” of Russian Academy of Science Institute for System Analysis 60-letiya Oktyabrya 9 119333 Moscow Russia

Since 1971, when the EMI scanner appeared on the market, work on optimizing the hardware of X-ray tomography complexes has not stopped for a single day. X-ray sources are constantly being improved (brighter, more stable, etc.), detectors (increased sensitivity, resolution, etc.), new geometric schemes and modes of projections collecting are being proposed. Another component of the tomographic complex is a computer that implements, in addition to starting measurements and controlling them, pre-processing of collected projections and reconstruction of a 3D digital image of an object, its processing and analysis. This paper presents mathematical approaches to working with tomographic projections collected in different schemes, as the basis for implementing reconstruction algorithms. The words scheme in the work are understood as monochromatic or polychromatic scanning was performed, what type of signal was recorded (transmission, fluorescent, phase contrast), whether the optical element was installed in the optical path.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development of identification list of binaries ILB 19

Development of identification list of binaries ILB

引用

19th International Conference on Data Analytics and Management in Data Intensive Domains, DAMDID/RCDL 2017

作者： Skvortsov, N.A. Kalinichenko, L.A. Karchevsky, A.V. Kovaleva, D.A. Malkov, O.Yu. FRC Computer Science and Control RAS Moscow Russia Institute of Astronomy RAS Moscow Russia

Binary and multiple stellar systems have been observed using various methods and tools. Catalogs of binaries of different observational types are independent and use inherent star identification systems. Moreover, components of stellar systems refer identifiers of surveys and catalogs of single stars. The problem of cross-identification of binary stars of different observational types as well as sky surveys is non-trivial and related to resolution of various kinds of conflicts. It requires not only combining lists of existing identifiers of specific stars, but matching components of multiple systems according to astrometric and astrophysical parameters for further referring of identifiers to matched components and to each other. This paper describes development of tools for creating the Identification List of Binaries (ILB) including cross-matching of systems, their components and pairs of all observational types. This work continues research of binary and multiple systems matching methods.

关键词： Stars

来源：评论

学校读者我要写书评

暂无评论

An efficient algorithm for packing cuts and (2,3)-metrics in a planar graph with three holes

arXiv

引用

arXiv 2018年

作者： Karzanov, Alexander V. Institute for System Analysis at FRC Computer Science and Control of the RAS 9 Prospect 60 Let Oktyabrya Moscow117312 Russia

We consider a planar graph G in which the edges have nonnegative integer lengths such that the length of every cycle of G is even, and three faces are distinguished, called holes in G. It is known that there exists a packing of cuts and (2,3)-metrics with nonnegative integer weights in G which realizes the distances within each hole. We develop a strongly polynomial purely combinatorial algorithm to find such a packing.90C27, 05C10, 05C12, 05C21, 05C85 Copyright © 2018, The Authors. All rights reserved.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Arctic Sea Ice Cover Sensitivity Analysis in Global Climate Model

引用

IOP Conference Series. Earth and Environmental science 2020年第4期459卷

作者： Parkhomenko, V P Bauman Moscow State Technical University ul. Baumanskaya 2-ya 5/1 Moscow 105005 Russia Federal Research Center “Computer Science and Control” of the Russian Academy of Sciences (FRC CSC RAS) Moscow 119333 Russia

Results of numerical of coupled numerical experiments with 3D atmospheric general circulation model, upper layer ocean model and sea ice evolution model are carried out and discussed for Arctic region. Model calculations to analyze sea ice cover evolution are carried out. Calculated sea ice cover distributions for different seasons are presented. Sea ice cover sensitivity analysis to base models parameters, determining atmosphere, ocean and ice interaction, sensible heat flux from sea ice and snow surface, heat flux from ocean to ice is presented. The spatial and seasonal structure of changes has rather complex non-uniform character, there are great areas of opposite changes. It is connected with nonlinear behavior of feedback and interactions in model system including an atmosphere, sea ice and ocean. The author was supported by the Russian Foundation for Basic Research (project no. №17-01-00693).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Intelligent data analysis and machine learning: Are they really equivalent Concepts?

Intelligent data analysis and machine learning: Are they rea...

引用

2017 IEEE International Conference on Cyber Conflict U.S., CyCon U.S. 2017

作者： Victor, K. Finn Michael, I. Zabezhailo Laboratory of Intelligent Data Analysis IPI FRC 'Computer Science and Control' RAS Moscow Russia

ISBN: (纸本)9781538612064

Some specific features of modern Artificial Intelligence (AI) technologies are discussed. Intelligent Data Analysis (IDA), defined as data analysis by means of computer intelligent systems (more formal - reasoning systems), is in focus of our discussion. We compare effectiveness of classical Machine Learning (ML) and IDA in extraction of empirical laws (i.e. stable empirical regularities - dependencies) from open collections of experimental data - i.e. in so called knowledge discovery (KD) problems. We'll demonstrate (by examples of applications of JSM Method of automated support for scientific research) that IDA is more general concept than classical ML. Some new IDA-based abilities to improve effectiveness of AI-technologies in important applications are presented. © 2017 IEEE.

关键词： Machine learning

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：