This paper describes a class of fuzzyclustering procedures for fuzzy data. Most fuzzyclustering techniques are designed for handling crisp data with their class memberships using the idea of fuzzy set theory. Here w...
详细信息
This paper describes a class of fuzzyclustering procedures for fuzzy data. Most fuzzyclustering techniques are designed for handling crisp data with their class memberships using the idea of fuzzy set theory. Here we derive new types of fuzzyclustering procedures in dealing with fuzzy data. These procedures are called fuzzyc-numbers (FcN) clusterings. Specially, we construct these FcNs for LR-type, triangular, trapezoidal and normal fuzzynumbers.
This paper presents a fuzzyclustering algorithm, called the alternative fuzzyc-numbers (AFcN) clustering algorithm, for LR-type fuzzynumbers based on an exponential-type distance function. On the basis of the gross...
详细信息
This paper presents a fuzzyclustering algorithm, called the alternative fuzzyc-numbers (AFcN) clustering algorithm, for LR-type fuzzynumbers based on an exponential-type distance function. On the basis of the gross error sensitivity and influence function, this exponential-type distance is claimed to be robust with respect to noise and outliers. Hence, the AFcN clustering algorithm is more robust than the fuzzyc-numbers (FcN) clustering algorithm presented by Yang and Ko (fuzzy Sets and Systems 84 (1996) 49). Some numerical experiments were performed to assess the performance of FcN and AFcN. Numerical results clearly indicate AFcN to be superior in performance to FcN. Finally, we apply the FcN and AFcN algorithms to real data. The experimental results show the superiority of AFcN in Taiwanese tea evaluation. (c) 2004 Elsevier B.V. All rights reserved.
暂无评论