A goal-related distance function on fuzzy partitions and its use in nearest neighbour classification

Issue title: Hybrid Fuzzy Models

Guest editors: José M. Benítezx, Salvador Garcíay, Santi Caballéz and Ángel Alejandro Juanz

Article type: Research Article

Authors: Rodriguez, Yanet^a | De Baets, Bernard^b | Morell, Carlos^{a; *}

Affiliations: [a] Computer Science Department. Universidad Central de Las Villas, C. Camajuani km 5, Santa Clara, Cuba | [b] Department of Applied Mathematics, Biometric and Process Control. Ghent University, Coupure links 653, B-9000 Gent, Belgium | [x] Department of Computer Science and Artificial Intelligence, Universidad de Granada, Granada, Spain | [y] Department of Computer Science, University of Jaén, Jaén, Spain | [z] Open University of Catalonia, Barecelona, Spain

Correspondence: [*] Corresponding author. E-mail: [email protected]

Abstract: Fuzzy similarity measures have been widely studied but their relationship with classification tasks have hardly been emphasized. Besides, what they just consider is the superficial difference between the objects to be compared without a deeper understanding of the domain. Intuition suggests that the similarity of objects needs to be modified in accordance to the manner in which they are classified. From the cognitive point of view it is clear that human beings modify their general knowledge as they achieve new experiences. This paper proposes a new distance measure based in the concept of fuzzy association between a predictive (fuzzy) value and the class value in a given memory of instances. This type of goal related similarity measure is new in the fuzzy context.

Keywords: Similarity measure, distance function, fuzzy partition

DOI: 10.3233/HIS-2010-0105

Journal: International Journal of Hybrid Intelligent Systems, vol. 7, no. 1, pp. 65-73, 2010