Piecewise Polynomial Aggregation as Preprocessing for Data Numerical Modeling

Тип публикации: доклад, тезисы доклада, статья из сборника материалов конференций

Конференция: International Conference on Information Technologies in Business and Industry; Tomsk Polytechn Univ, Tomsk, RUSSIA; Tomsk Polytechn Univ, Tomsk, RUSSIA

Год издания: 2018

Идентификатор DOI: 10.1088/1742-6596/1015/3/032028

Аннотация: Data aggregation issues for numerical modeling are reviewed in the present study. The authors discuss data aggregation procedures as preprocessing for subsequent numerical modeling. To calculate the data aggregation, the authors propose using numerical probabilistic analysis (NPA). An important feature of this study is how the authors represent the aggregated data. The study shows that the offered approach to data aggregation can be interpreted as the frequency distribution of a variable. To study its properties, the density function is used. For this purpose, the authors propose using the piecewise polynomial models. A suitable example of such approach is the spline. The authors show that their approach to data aggregation allows reducing the level of data uncertainty and significantly increasing the efficiency of numerical calculations. To demonstrate the degree of the correspondence of the proposed methods to reality, the authors developed a theoretical framework and considered numerical examples devoted to time series aggregation. © Published under licence by IOP Publishing Ltd.

Ссылки на полный текст

Издание

Журнал: Journal of Physics: Conference Series

Выпуск журнала: Vol. 1015, Is. 3

ISSN журнала: 17426588

Издатель: Institute of Physics Publishing

Авторы

  • Dobronets B.S. (Siberian Fed Univ, Kireskogo 26, Krasnoyarsk 660074, Russia)
  • Popova O.A. (Siberian Fed Univ, Kireskogo 26, Krasnoyarsk 660074, Russia)

Вхождение в базы данных

Информация о публикациях загружается с сайта службы поддержки публикационной активности СФУ. Сообщите, если заметили неточности.

Вы можете отметить интересные фрагменты текста, которые будут доступны по уникальной ссылке в адресной строке браузера.