Related family-based attribute reduction of covering information systems when varying attribute sets
This work addresses a specific problem in data mining for dynamic systems, but it appears incremental as it builds on existing related family approaches.
The paper tackles attribute reduction in dynamic covering information systems with varying attribute sets by proposing related family-based methods, and experimental results show these methods are effective for this task.
In practical situations, there are many dynamic covering information systems with variations of attributes, but there are few studies on related family-based attribute reduction of dynamic covering information systems. In this paper, we first investigate updated mechanisms of constructing attribute reducts for consistent and inconsistent covering information systems when varying attribute sets by using related families. Then we employ examples to illustrate how to compute attribute reducts of dynamic covering information systems with variations of attribute sets. Finally, the experimental results illustrates that the related family-based methods are effective to perform attribute reduction of dynamic covering information systems when attribute sets are varying with time.