A relative tolerance relation of rough set for incomplete information systems

Rough set theory is an effective approach to imprecision, vagueness, and uncertainty. This theory overlaps with many other theories such that fuzzy sets, evidence theory, and statistics. From a practical point of view, it is a good tool for data analysis. However, classical rough set theory cannot cope with the incomplete information systems where some attribute values are missing. There have been efforts in studying incomplete information systems for data classification which are based on the extensions of rough set theory. Moreover, the existing approaches have their weaknesses in terms of inflexible and imprecise in data classifications. To overcome these issues, we propose a relative tolerance relation of rough set (RTRS) to handling incomplete information systems, which it has flexibility and precisely for data classification. We compared RTRS with the existing approaches, the results show that our proposed method relatively achieves higher flexibility and precisely in data classification in incomplete information systems