Rough Sets: Theoretical Aspects of Reasoning about Data
Rough Sets: Theoretical Aspects of Reasoning about Data
Machine Learning
Hi-index | 0.00 |
This paper proposes a modified rule generation (MRG) algorithm and rule induction prototype(RGRIP). It can help the decision-maker predict the outcomes of new cases effectively. Not only MRG algorithm provides a very fast and effective way to generate a minimal set of rule reducts from which “certain” rules can be induced, but also produces as a byproduct a revised decision tabel T from which “possible” rules could be conveniently induced. Then, combining the MRG algorithm with the rule induction schemes, we proposed a rule generation and rule induction prototype(RGRIP) that can automatically generate a minimal set of reducts and induce all certain rules as well as possible rule with all their plausibility indices. In term of ability to deal with uncertainty and inconsistency in the data set, RGRIP approach appears simplicity and conciseness in the process of its usage. The approach is efficient and effective in dealing with large data sets.