Sensitivity

analysis is a technique of determination on how different values of an independent

variable could impact a dependent variable under a set of assumptions. These

techniques can be used in specific boundaries that depend on the input

variables. Sensitivity analysis has simple principle which is ‘change the model

and observe’. It refer to as what-if or simulation analysis, which it is a way

to predict the results of a decision given a certain range of variables.

Sensitivity analysis could be used to help in decision making, functions as the

aids searching for errors in the model and also is a method to predict the output

of a decision if a situation turns out to be different from the key

predictions. This conclude that, sensitivity analysis is one of the tools that

help decision makers with more than a solution to a problem and provides a

related intuition into the problems associated with the model.

Similarity

measure is a real-valued function that measures the similarity between two

objects. The concept of similarity is fundamentally important in almost every

scientific field. Similarity measure can be described as a function which

calculates the degree of similarity between objects. A lot of similarity

measures techniques have been proposed by many researchers to calculate the

degree of similarity between fuzzy numbers. All of these techniques are

implement due to numerous factors that affect the similarity degree of fuzzy

numbers such as overlapping midpoint, perimeters, and areas. Even though there are

various techniques had been establish to measure the degree of similarity

between fuzzy numbers, but the limitations for the existing fuzzy similarity

measures are still exist. It is because,

those techniques only can solve similarity problems based on certain selected

situation.

This study aimed

to investigate fuzzy similarity measure by using the sensitivity analysis

method. There are various methods to carry out the sensitivity analysis. In

this research will discuss about the similarity measures that compare more than

two sets of fuzzy models. This research will investigate a system that could be

use to compare more than two fuzzy numbers using selected fuzzy similarity

measures which is based on sensitivity analysis method.