Fuzzy-регресійні моделі в умовах наявності в статистичній вибірці нечислової інформації

Algorithms are presented for solving the problems of the fuzzy regression analysis under the conditions when the input and output variables are represented by Fuzzy-sets defined up to unknown parameters and the regression coefficients are real numbers. We proposed several new approximations of crite...

Повний опис

Збережено в:
Бібліографічні деталі
Дата:2017
Автор: Zack, Yuriy A.
Формат: Стаття
Мова:rus
Опубліковано: The National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute" 2017
Теми:
Онлайн доступ:http://journal.iasa.kpi.ua/article/view/101833
Теги: Додати тег
Немає тегів, Будьте першим, хто поставить тег для цього запису!
Назва журналу:System research and information technologies

Репозитарії

System research and information technologies
Опис
Резюме:Algorithms are presented for solving the problems of the fuzzy regression analysis under the conditions when the input and output variables are represented by Fuzzy-sets defined up to unknown parameters and the regression coefficients are real numbers. We proposed several new approximations of criteria based on the comparison of the convolution of the cross sections lengths and the center of gravity coordinates of membership functions of the Fuzzy-sets, which can be used for the fuzzy set variables of the problem of a general form. The algorithms convert a variable represented by linguistic terms of variable parameters or numerical scales into fuzzy sets and use these data in the problems of the Fuzzy-regression analysis. The results will allow to solve many practical problems in economics, logistics, sociology, and marketing.