An Approach of Factor Screening in Multifactor Mixture Experiments using Rough Set Theory

Chetan, Nisha

Abstract: A large number of experiments are being conducted in industrial and other branches of science with an objective to compare and test quantity of inputs applied as mixture of two or more components. In particle, there are many situations where mixture experiments involve large number of factors, such types of mixture experiments are known as multifactor mixture experiments. Due to their practical applicability it is important to make such experiment user friendly. Reducing the number of factors without loss of information is an important step in this direction. Therefore, in present study rough set theory (RST), which is an extension of the set theory and has the implicit feature of compressing the data set, is used to reduce the factors in the multifactor mixture experiments.

Keywords: Mixture Experiments, Rough Set Theory, Factor Reduction, Indiscernibility Relation