An interval type-2 fuzzy K-nearest neighbor

This paper presents an interval type-2 fuzzy Knearest neighbor (NN) algorithm that is an extension of the type1 fuzzy K-NN algorithm proposed in [l]. In our proposed method, the membership values for each vector are 'extended as interval type-2 fuzzy memberships by assigning uncertainty to the type-1 memberships. By doing so, the classification result obtained by the interval type-2 fuzzy K-NN is found to he more reasonable than that of the crisp and type-1 effectiveness of our method. For this extension, we use initial K values in an appropriate r ~ , g e , ~ ~ ~ d l , ~ ~ of this uncertainty can decrease the contribution of an undesirable initial K on the classification process for the patterns. Hence, this can provide a more reasonable classification result by managing the uncertainty for the selected initial K , possesses the following advantages. fumy K-". Experimental results are given to show the In Our proposed type-2 approach