An approach for incremental updating approximations in Variable precision rough sets while attribute generalized

• Published in: 2010 IEEE International Conference on Intelligent Systems and Knowledge Engineering pp. 77 - 81
• Main Authors: Junbo Zhang, Tianrui Li, Dun Liu
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.11.2010
• Subjects: Approximation algorithms; Approximation methods; Approximations; Cognition; Data mining; Granular Computing; Incremental Updating; Information systems; Probabilistic logic; Probabilistic rough sets; Rough sets; Variable Precision Rough Sets
• ISBN: 1424467918; 9781424467914
• DOI: 10.1109/ISKE.2010.5680798

Rough set theory (RST) for knowledge updating have been successfully applied in data mining and it's correlative domains. As a special type of probabilistic rough set model, Variable precision rough sets (VPRS) model is an extension of RST. For an information system, the VPRS model allows a flexible approximation boundary region by using a precision variable and has a better tolerance ability for inconsistent data. However, the approximations of a concept may change when an information system varies. The approach for incremental updating of approximations while attribute generalizing in VPRS should be considered. In this paper, an incremental model and its algorithm for updating approximations of a concept based on VPRS are proposed when attribute generalized. Examples are employed to validate the feasibility of this approach.