Rough set model based on possibility measure

• Published in: 2009 International Conference on Machine Learning and Cybernetics Vol. 5; pp. 2657 - 2662
• Main Authors: Fa-Chao Li, Li-Na An
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.07.2009
• Subjects: Approximate operators; Artificial intelligence; Educational institutions; Evidence theory; Fuzzy set theory; Information processing; Machine learning; Pattern recognition; Possibility distribution; Possibility measures; Rough set; Rough sets; Roughness; Set theory; Uncertainty
• DOI: 10.1109/ICMLC.2009.5212645
• ISBN: 9781424437023; 1424437024
• ISSN: 2160-133X

Rough sets theory (RS) is a new tool for processing fuzzy and uncertain knowledge, and has already been applied to many areas successfully. In this paper, by analyzing the basic characteristic of rough set, for the deficiency that the existing rough set model can't effectively solve data reduction and knowledge discovery with possibility feature, we propose rough sets model based on possibility measure (denoted by BP-RS for short), then we analyze the effectiveness of model through an example. The result indicates BP-RS not only have the advantages of classical rough set, but also it can solve effectively information processing problem with the possibility characteristics, and can be widely used in many field such as data mining, evidence theory, artificial intelligence and so on.