A NEW APPROACH TO FUZZY LINEAR REGRESSION WITH FUZZY INPUT AND OTPUT DATA

This paper considers a fuzzy linear regression model with fuzzy input-output data and crisp coefficients. To find the coefficients of the model a new approach based on multi-objective linear programming is developed. Both symmetric and non-symmetric data can be considered in the developed model. The performance of the new model is compared with some existing methods based on simulation studies and numerical examples.

Keywords:

Fuzzy Regression , Fuzzy Input and Output Data , Multi-Objective Programming