Study on the Extension Models to Handle Missing Values

The starting point of the rough sets theory is an observation that objects having the same description are indiscernible with respect to the available information. But the indiscernibility relation may be too rigid in some situations. Therefore several generalizations of the rough sets theory have been proposed. Some of them extend the indiscernibility relation using more general similarity or tolerance relations. In this paper, several extension models of rough set under incomplete information are discussed. Furthermore, the performances of these extended relations are compared also.