Abstract
AbstractRepresenting and manipulating the vague concepts of partially true knowledge pose a major challenge to the development of machine intelligence. In particular, the issue of how to extract approximate facts from vague and partially true statements has received considerable attention in the field of fuzzy information processing. However, vagueness is often due to a lack of available information, making it impossible to satisfactorily evaluate membership. Atanassov (1996) demonstrated the feasibility of mapping intuitionistic fuzzy sets to historical fuzzy sets. Intuitionistic fuzzy sets are isomorphic to interval valued fuzzy sets, while interval valued fuzzy sets have been regarded as unique value among type-2 fuzzy sets. This study presents a theoretical method to represent and manipulate partially true knowledge. The proposed method is based on the measurement of similarity among type-2 fuzzy sets, which are used directly to handle rule uncertainty that type-1 fuzzy sets are unable to deal with. Moreover, the switching relationship between type-2 fuzzy sets and intuitionist fuzzy sets is defined axiomatically. Results of this study demonstrate the effectiveness of the proposed theoretical method in pattern recognition and reasoning with regard to medical diagnosis.KeywordsType-2 fuzzy setsIntuitionistic fuzzy setsFuzzy similarityPartial truth
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
