Interpretation of Variable Consistency Dominance-Based Rough Set Approach by Minimization of Asymmetric Loss Function
| [ P ] pracownik
2019
rozdział w monografii naukowej / referat
angielski
- rough sets
- variable consistency dominance-based rough set approach
- ordinal data analysis
- empirical risk minimization
EN In this paper, we give a statistical interpretation of the variable consistency dominance-based rough set approach (VC-DRSA), which is a version of DRSA useful for practical reasoning about ordinal data. This study is building a bridge between theories of rough sets and statistics, and it is developing, moreover, a new direction of study about VC-DRSA. We consider a classification problem for each pair of complementary upward and downward unions of decision classes, and define an empirical risk function with an asymmetric loss function consisting of hinge and 0–1 loss functions. Then, we prove that approximations of two decision classes by VC-DRSA correspond to the minimum of the empirical risk function.
07.03.2019
135 - 145
20