Two kinds of average approximation accuracy

Rough set theory places great importance on approximation accuracy, which is used to gauge how well a rough model describes target concept. However, traditional accuracy has limitations since it varies with changes in the concept and cannot evaluate overall descriptive ability of model. To overcome this, two types average that objectively assess model’s approximate all information granules proposed. The first relative based sets universe several basic properties. second absolute undefinable yielded significant conclusions. We also explore relationship between these accuracy. Finally, practical applications addressing missing attribute values incomplete tables.