Product design case databases contain a lot potential knowledge, which can tell us the relations among parameters and some interesting experience patterns. While designing product, it is supposed to support the designers to make decisions better. Therefore many researchers are trying to find an effective approach to discover the unknown knowledge. In this paper, we presented several algorithms which combining rough set theory and information entropy for knowledge discovery. With these algorithms, the potential knowledge was mined out from the original product design databases. It was generated in the form of several association rules. Also a case study was presented to demonstrate the process of these algorithms. And the efficiency was proved at last. It turns out that the process of these algorithms could acquire knowledge from design databases effectively.
[1]
Jiye Liang,et al.
A new method for measuring uncertainty and fuzziness in rough set theory
,
2002,
Int. J. Gen. Syst..
[2]
Guoyin Wang.
Algebra view and information view of rough sets theory
,
2001,
SPIE Defense + Commercial Sensing.
[3]
Z. Pawlak.
Rough Sets: Theoretical Aspects of Reasoning about Data
,
1991
.
[4]
Hong Wang,et al.
Rough Set Attribute Reduction in Decision Systems
,
2006,
RSKT.
[5]
Guoyin Wang,et al.
A Scalable Rough Set Knowledge Reduction Algorithm
,
2004,
Rough Sets and Current Trends in Computing.
[6]
Andrzej Skowron,et al.
The Discernibility Matrices and Functions in Information Systems
,
1992,
Intelligent Decision Support.
[7]
Zdzislaw Pawlak,et al.
Some Issues on Rough Sets
,
2004,
Trans. Rough Sets.