Fuzzy relational classifier trained by fuzzy clustering
نویسندگان
چکیده
منابع مشابه
Fuzzy relational classifier trained by fuzzy clustering
A novel approach to nonlinear classification is presented, in the training phase of the classifier, the training data is first clustered in an unsupervised way by fuzzy c-means or a similar algorithm. The class labels are not used in this step. Then, a fuzzy relation between the clusters and the class identifiers is computed. This approach allows the number of prototypes to be independent of th...
متن کاملA clustering-based fuzzy classifier
In this work we propose to use fuzzy prototypes for classification tasks. We create the prototypes by first clusterizing, separately, the available data for each class. Then we create a fuzzy set around each class center, according to clusterization indices that take into account both local and global data. We also investigate the use of an index to guide the process of obtaining a suitable num...
متن کاملA clustering-based fuzzy classifier
In this work we propose to use fuzzy prototypes for classification tasks. We create the prototypes by first clusterizing, separately, the available data for each class. Then we create a fuzzy set around each class center, according to clusterization indices that take into account both local and global data. We also investigate the use of an index to guide the process of obtaining a suitable num...
متن کاملA clustering-based fuzzy classifier
In this work we propose to use fuzzy prototypes for classification tasks. We create the prototypes by first clusterizing, separately, the available data for each class. Then we create a fuzzy set around each class center, according to clusterization indices that take into account both local and global data. We also investigate the use of an index to guide the process of obtaining a suitable num...
متن کاملClustering Fuzzy Relational Data base on fuzzy Cardinality
Our purpose is to provide a set-theoretical frame to clustering fuzzy relational data basically based on the cardinality of the fuzzy subsets and their complementaries that represent the objects under study, without applying any crisp property when the various elements that compose the process are fuzzified. From this perspective we define a family of fuzzy similarity indexes which includes a s...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Transactions on Systems, Man and Cybernetics, Part B (Cybernetics)
سال: 1999
ISSN: 1083-4419
DOI: 10.1109/3477.790444