Comparative study of decision performance of decision tables induced by attribute reductions
Authors: Wei Wei, Jiye Liang, Yuhua Qian, Feng Wang, Chuangyin Dang
Abstract:
An attribute reduction approach given decides the decision performance of a reduced decision table, which can give a guidance for selecting one rule-extraction method in practical applications. The objective of this study is to compare the decision performance of positive-region reduction, Shannon's entropy reduction and Liang's entropy reduction. In this paper, the relationships in-between positive-region reduction, Shannon's entropy reduction and Liang's entropy reduction are first investigated. Then, by means of three evaluation indices (certainty measure, consistency measure, and support measure), we systemically analyze these change mechanism of decision performance of a decision table induced by each of these three types of reduction approaches. Finally, by numerical experiments, these change mechanism of a decision table's decision performance are verified for the above three attribute reductions.
Keywords：
Comparative study of decision performance of decision tables induced by attribute reductions.pdf
Fri Dec 24 15:35:00 CST 2010