Центральная научная библиотека ФИЦ КНЦ СО РАН

Труды сотрудников ИВМ СО РАН

w10=

Найдено документов в текущей БД: 3

Analysis of the Dependence of the Approximation Properties of a Nonparametric Estimate of a Probability Density on the Sampling Method for the Domain of Definition

Lapko, A. V.

/ A. V. Lapko, V. A. Lapko // Measurement Techniques. - 2015, DOI 10.1007/s11018-015-0741-z . - ISSN 0543-1972

Кл.слова (ненормированные):
approximation properties -- Brooks–Carruthers rule -- Freedman–Diaconis rule -- Heinhold–Gaede rule -- nonparametric estimate -- number of sampling intervals -- probability density -- Scott rule -- Sturges rule -- Probability -- Approximation properties -- Non-parametric estimates -- Probability densities -- Sampling interval -- Scott rule -- Sturges rule -- Probability density function

Аннотация: A method is proposed for comparing the efficiencies of procedures for sampling the range of values of a random quantity when estimating the probability density. The criterion of efficiency is taken to be an asymptotic expression for the mean square deviation of a regression fit for the probability density. © 2015 Springer Science+Business Media New York

Scopus,
WOS

Держатели документа:
Institute of Computational Modeling, Siberian Branch, Russian Academy of Sciences, Krasnoyarsk, Russian Federation
Siberian State Aerospace University, Krasnoyarsk, Russian Federation

Доп.точки доступа:
Lapko, V. A.; Лапко, Василий Александрович; Лапко, Александр Васильевич

Найти похожие

Construction of confidence boundaries for the decision function in a two-alternative problem of pattern recognition

Lapko, A. V.

/ A. V. Lapko, V. A. Lapko // Optoelectron. Instrum. Data Proces. - 2015. - Vol. 51, Is. 4. - P372-377, DOI 10.3103/S875669901504007X . - ISSN 8756-6990

Кл.слова (ненормированные):
confidence estimate -- decision function -- Heinhold–Gaede rule -- nonparametric estimate -- pattern recognition -- Bayesian -- Computational experiment -- confidence estimate -- Decision functions -- Learning samples -- Non-parametric estimates -- Probabilistic characteristics -- Pattern recognition

Аннотация: A nonparametric estimate of the decision function in a two-alternative problem of pattern recognition is considered. The principle of expansion of the learning sample and the analysis of the probabilistic characteristics of the obtained sets of random variables are used to synthesize this estimate. On this basis, a technique of construction of confidence boundaries for the Bayesian equation of the separating surface is derived. The efficiency of this technique is proved by results of computational experiments. © 2015, Allerton Press, Inc.

Scopus

Держатели документа:
Institute of Computational Modeling, Siberian Branch, Russian Academy of Sciences, Akademgorodok 50, building 44, Krasnoyarsk, Russian Federation
Reshetnev Siberian State Aerospace University, pr. im. Gazety “Krasnoyarskii rabochii” 31, Krasnoyarsk, Russian Federation

Доп.точки доступа:
Lapko, V. A.; Лапко, Василий Александрович; Лапко, Александр Васильевич

Найти похожие

Nonparametric Estimation of the Quadratic Functional of a Multimodal Probability Density

/ A. V. Lapko, V. A. Lapko // Meas. Tech. - 2019, DOI 10.1007/s11018-019-01693-z . - Article in press. - ISSN 0543-1972

Кл.слова (ненормированные):
choice of spread coefficient -- estimation of a functional of the probability density -- Heinhold–Gaede rule -- kernel estimate of probability density -- maximum likelihood criterion -- multimodal probability density -- Sturges rule

Аннотация: A nonparametric method for estimating the mean square functional of a multimodal probability density of a one-dimensional random variable is examined. The proposed method is based on using the Sturgis and Heinhold–Gaede formulas and an optimum sampling procedure for sampling a range of values of random quantities. This method is compared with the traditional approach based on choosing a spread coefficient using the condition for the maximum of the likelihood function. The conditions for competence of this method are determined. © 2019, Springer Science+Business Media, LLC, part of Springer Nature.

Scopus,
Смотреть статью,
WOS

Держатели документа:
Institute of Computational Modeling, Siberian Branch of the Russian Academy of Sciences, Krasnoyarsk, Russian Federation
Reshetnev Siberian State University of Science and Technology, Krasnoyarsk, Russian Federation

Доп.точки доступа:
Lapko, A. V.; Lapko, V. A.

Найти похожие