论文信息 - Transforming continuous attributes using GA for applications of Rough Set Theory to control centers

Transforming continuous attributes using GA for applications of Rough Set Theory to control centers

One of the possible application of Rough Sets Theory (RST) is the knowledge extraction in databases. Also, RST is useful to develop models for decision-making. During both processes one of the steps is the transformation of attributes with continuous values in digital values. This transformation sometimes can lose information. This paper presents a method for this transformation using genetic algorithms (GA). GA is used to determine the cut-off points for each attribute, getting a consistent transformation. An application in Control Centers with real data is presented.

[1] Peter Norvig,et al. Artificial Intelligence: A Modern Approach , 1995 .

[2] Andrzej Skowron,et al. Rudiments of rough sets , 2007, Inf. Sci..

[3] G. Lambert-Torres,et al. Application of rough sets in power system control center data mining , 2002, 2002 IEEE Power Engineering Society Winter Meeting. Conference Proceedings (Cat. No.02CH37309).

[4] Stephen D. Bay. Multivariate discretization of continuous variables for set mining , 2000, KDD '00.

[5] John H. Holland,et al. Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[6] Huan Liu,et al. Discretization: An Enabling Technique , 2002, Data Mining and Knowledge Discovery.

[7] Randy Kerber,et al. ChiMerge: Discretization of Numeric Attributes , 1992, AAAI.