### ?

## Об энтропийных критериях отбора признаков в задачах анализа данных

Информационные технологии и вычислительные системы. 2018. № 2. С. 60-69.

The paper considers the problem of reducing the dimension of the feature space for describing objects

in data analysis problems using the example of binary classification. The article provides a detailed

overview of existing approaches to solving this problem and proposes several modifications. In which

the dimensionality reduction is considered as the problem of extracting the most relevant information

from the characteristic description of objects and is solved in terms of the Shanon's entropy. To identify

the most significant features information criteria such as crossentropy, mutual information and Kullback-

Leibler divergence are used.

Language:
Russian

Popkov Y., Popkov A., Dubnov Y. A., Математическое моделирование 2020 Т. 32 № 9 С. 35-52

We develop a new method of dimensionality reduction based on direct and inverse projection of data matrix and calculation of projectors minimizing cross-entropy functional. Concept of information capacity of matrix which is used as a restriction in a problem of optimal reduction is introduced. We conduct a comparison of proposed method with known ones based ...

Added: October 31, 2020

Dubnov Y. A., Искусственный интеллект и принятие решений 2020 № 2 С. 78-85

The paper considers the problem of feature selection in the classification problem. A method for selecting informative features based on a probabilistic approach and cross-entropy metrics is proposed. Several variants of the information criterion for selecting features for a binary classification problem are considered, as well as its generalization to the case of a multiclass ...

Added: October 31, 2020

Zhuk R., Ignatov D. I., Konstantinova N., Procedia Computer Science 2014 Vol. 31 P. 928-938

We propose extensions of the classical JSM-method and the Na ̈ıve Bayesian classifier for the case of triadic relational data. We performed a series of experiments on various types of data (both real and synthetic) to estimate quality of classification techniques and compare them with other classification algorithms that generate hypotheses, e.g. ID3 and Random ...

Added: June 9, 2014

Kuznetsov S., Serdyukov P., Segalovich I. et al., L. : Springer, 2013

Higher School of Economics (HSE) and supported by the Information Retrieval Specialist Group at the British Computer Society (BCS–IRSG). The conference was held during March 24–27, 2013, in Moscow, Russia – the easternmost location in the history of the ECIR series. ECIR 2013 received a total of 287 submissions in three categories: 191 full papers, ...

Added: April 15, 2013

Башмаков А. И., Белоозеров В. Н., Starykh V., Информационные системы и технологии 2013 № 6(80) С. 88-102

In article process of construction formal ontology of information resources system for an education, that pursues the aim to reflect representation about this sphere in the automated systems intended for creation, account, ordering, storage, search and use of these resources in educational institutions of various level is stated. The system of information resources is set ...

Added: January 16, 2014

Popkov Y., Dubnov Y. A., Volkovich Z. et al., Entropy 2017 Vol. 19(4) No. 178 P. 1-14

A proposal for a new method of classification of objects of various nature, named “2”-soft classification, which allows for referring objects to one of two types with optimal entropy probability for available collection of learning data with consideration of additive errors therein. A decision rule of randomized parameters and probability density function (PDF) is formed, ...

Added: May 26, 2017

Popkov Y., Popkov A., Dubnov Y. A., Автоматика и телемеханика 2020 № 7 С. 148-172

A randomized forecasting method based on the generation of ensembles of entropy-optimal forecasting trajectories is developed. The latter are generated by randomized dynamic regression models containing random parameters, measurement noises, and a random input. The probability density functions of random parameters and measurement noises are estimated using real data within the randomized machine learning procedure. ...

Added: October 31, 2020

Alekseev V., Zakharova D. V., Malyshev D. et al., Вестник Нижегородского университета им. Н.И. Лобачевского. Серия: Математика 2012 № 6(1) С. 115-120

Рассматриваются вопросы асимптотического перечисления наследственных классов графов и их структурного описания, исследуется сложность некоторых задач на таких классах. ...

Added: May 17, 2013

Kitov V. V., Вестник Российского экономического университета им. Г.В. Плеханова 2015 Т. 82 № 4 С. 148-152

Methods of classification by nature of decision-making divide on methods using global optimization (all training samples are used), and local optimization (only samples in the neighbourhood of the studied object are used). The perspective direction of research is combination of advantages of each approach in one integrated classifier. In article the method of combination of ...

Added: March 16, 2016

Bufetov A. I., Geometric and Functional Analysis 2012 Vol. 22 No. 4 P. 938-975

Vershik and Kerov conjectured in 1985 that dimensions of irreducible representations of finite symmetric groups, after appropriate normalization, converge to a constant with respect to the Plancherel family of measures on the space of Young diagrams. The statement of the Vershik-Kerov conjecture can be seen as an analogue of the Shannon-McMillan-Breiman Theorem for the non-stationary ...

Added: October 18, 2012

Kuznetsov V. O., Логистика и управление цепями поставок 2018 № 4 (87) С. 27-33

One of the options for a more flexible approach to analyzing the reliability of supply chains is the principal component analysis (PCA). With a large number of variables describing supply chain, it is a difficult task to analyze the structure of variables in two-dimensional space. Within the analysis of the variables dependencies PCA allows to ...

Added: November 29, 2018

Malyshev D., Journal of Applied and Industrial Mathematics (перевод журналов "Сибирский журнал индустриальной математики" и "Дискретный анализ и исследование операций") 2020 Vol. 14 No. 4 P. 706-721

The edge coloring problem for a graph is to minimize the number of colors that are sufficient to color all edges of the graph so that all adjacent edges receive distinct colors. The computational complexity of the problem is known for all graph classes defined by forbidden subgraphs with at most 6 edges. We improve ...

Added: January 30, 2021

Vyalyi M., Дискретная математика 1991 Т. 3 № 3 С. 35-45

Added: October 17, 2014

Malyshev D., / Cornell University. Series math "arxiv.org". 2013. No. 1307.0278v1.

The coloring problem is studied in the paper for graph classes deﬁned by two small forbidden induced subgraphs. We prove some suﬃcient conditions for eﬀective solvability of the problem in such classes. As their corollary we determine the computational complexity for all sets of two connected forbidden induced subgraphs with at most ﬁve vertices except ...

Added: October 3, 2013

Gribanov D., Malyshev D., Discrete Applied Mathematics 2017 Vol. 227 P. 13-20

We consider boolean linear programming formulations of the independent set, the vertex and the edge dominating set problems and prove their polynomial-time solvability for classes of graphs with (augmented) constraint matrices having bounded minors in the absolute value ...

Added: April 23, 2017

Felikson А. A., Natanzon S. M., Differential Geometry and its Application 2012 Vol. 30 No. 5 P. 490-508

We consider (local) parameterizations of Teichmüller space Tg,n (of genus g hyperbolic surfaces with n boundary components) by lengths of 6 g- 6 + 3 n geodesics. We find a large family of suitable sets of 6 g- 6 + 3. n geodesics, each set forming a special structure called "admissible double pants decomposition". For ...

Added: February 5, 2013

Malyshev D., Gribanov D., Discrete Optimization 2018 Vol. 29 P. 103-110

We consider boolean linear programming formulations of the vertex and edge dominating set problems and prove their polynomial-time solvability for classes of graphs with constraint matrices having bounded minors in the absolute value. ...

Added: April 8, 2018

Marshirov V. V., Marshirova L. E., Сибирский журнал индустриальной математики 2013 Т. XVI № 4 С. 111-120

The paper considers the problem of determining the rate of cooling of metal during solidification at the intersection of the liquidus temperature under intense heat sink from the surface. The solution to this problem it is necessary to determine the process conditions, the boundary and initial conditions for which it is possible to get new ...

Added: November 17, 2013

Yasnitsky L., Пермь : Пермский государственный национальный исследовательский университет. – Электронные данные. , 2020

The collection contains materials from the international conference "Intelligent systems in science and technology" and the Sixth all-Russian scientific and practical conference "Artificial intelligence in solving urgent social and economic problems of the XXI century", which was held on October 12-18, 2020 in Perm as part of the Perm natural science forum "Mathematics and global ...

Added: December 4, 2020

Rubchinskiy A., / Высшая школа экономики. Series WP7 "Математические методы анализа решений в экономике, бизнесе и политике". 2015. No. WP7/2015/09.

An algorithm of solution of the Automatic Classification (AC for brevity) problem is set forth in the paper. In the AC problem, it is required to find one or several partitions, starting with the given pattern matrix or dissimilarity / similarity matrix. The three-level scheme of the algorithm is suggested. The output of the procedure ...

Added: October 19, 2017

Malyshev D., Discrete Mathematics 2015 Vol. 338 No. 11 P. 1860-1865

We completely determine the complexity status of the 3-colorability problem for hereditary graph classes defined by two forbidden induced subgraphs with at most five vertices. ...

Added: April 7, 2014

Kryuchkov M., Rusakov S. V., Вестник Ижевского государственного технического университета 2015 № 2(66) С. 110-112

This paper describes the results of testing the neuronal technical trend indicator according to the exchange rate of Brent oil in 2014. Testing of the model was carried out on three time series, which characterized by their features. ...

Added: August 31, 2015

Lanham : University Press of America, 2012

The history of logic and analytic philosophy in Central and Eastern Europe is still known to very few people. As an exception to the rule, only two scientific schools became internationally popular: the Vienna Circle and the Lvov-Warsaw School. Nevertheless, the countries included in this region have not only joint history, but also joint cultural ...

Added: February 13, 2013

Barcelona : IEEE, 2017

International Conference on Control, Decision and Information Technologies. ...

Added: January 17, 2018