Fuzzy rule-based models for case retrieval

This paper provides a systematic treatment of fuzzy rule-based formalization of case retrieval in case-based reasoning, which classifies case retrieval into five categories from a logical viewpoint and proposes corresponding models and implementations at three levels: the level of similarity relations, level of fuzzy similarity relations, and level of similarity metrics. This paper also uses Zadeh's compositional rule of inference to extend the proposed rule-based case retrieval models into fuzzy rule-based models for case retrieval. The proposed approach shows that fuzzy rule-based case retrieval and the separation between similarity relations, fuzzy similarity relations, and similarity metrics are significant for the theoretical foundation and practical application of case retrieval.