An Interactive Method of Linear Mixed Integer Multicriteria Optimization

The paper describes a learning-oriented interactive method for solving linear mixed integer problems of multicriteria optimization. The method increases the possibilities of the decision maker (DM) to describe his/her local preferences and at the same time it overcomes some computational difficulties, especially in problems of large dimension. The method is realized in an experimental decision support system for finding the solution of linear mixed integer multicriteria optimization problems.

Classification-Based Method of Linear Multicriteria Optimization

The paper describes a classification-based learning-oriented interactive method for solving linear multicriteria optimization problems. The method allows the decision makers describe their preferences with greater flexibility, accuracy and reliability. The method is realized in an experimental software system supporting the solution of multicriteria optimization problems.

Classification of Smoking Cessation Status Using Various Data Mining Methods

AMS Subj. Classification: 62P10, 62H30, 68T01

Experience of Development and Application of Expert Systems for Economic Macroparameters Forecasting and Operation

In this article there are considered problems of forecasting economical macroparameters, and in the first place, index of inflation. Concept of development of synthetical forecasting methods which use directly specified expert information as well as calculation result on the basis of objective economical and mathematical models for forecasting separate “slowly changeable parameters” are offered. This article discusses problems of macroparameters operation on the basis of analysis of received prognostic magnitude.

Иерархические Модели Принятия Решений в Многокритериальных Задачах

При векторном подходе задача принятия решений посредством декомпозиции свойств альтернатив представляется иерархической системой критериев. Возникает проблема обратного перехода к оценке и сравнению альтернатив в целом. Эта проблема предполагает решение задачи композиции критериев по уровням иерархии. Задача решается методом вложенных скалярных сверток.

Снижение Размерности Признакового Пространства в Задачах Многокритериальной Классификации

Представлен метод последовательного снижения размерности признакового пространства, который позволяет упростить процедуру порядковой классификации многокритериальных альтернатив и уменьшить ее трудоемкость.