Test cost sensitive multigranulation rough set: Model and minimal cost selection

摘要: Abstract Multigranulation rough set is an expansion of the classical by using multiple granular structures. Presently, three important multigranulation sets have been proposed, they are optimistic, pessimistic and β-multigranulation approaches. However, such do not take test cost into consideration, which issue in both data mining machine learning. To solve problem, we propose a sensitive model this paper. We show that generalization sets. Furthermore, it found traditional heuristic algorithm suitable for structure selection with lower cost, then backtracking minimal cost. The algorithms tested on ten UCI (University California–Irvine) Experimental results effectiveness comparing algorithm. This study suggests potential application areas new research trends concerning theory.