Difference Similitude Method in Knowledge Reduction
An intergraded reduction method, which includes attributes reduction and rules induction, is proposed in this context. Firstly, U/C is calculated for reducing the complexity of the reduction. Then, difference and similitude sets, of the reduced information system, are calculated. The last, the attributes are selected according to their abilities for giving high accurate rules. The time complexity of the reduction, including attributes reduction and rules induction, is O(∣C∣2∣U/C∣2).
KeywordsTime Complexity Rule Induction Feature Subset Selection Conditional Attribute Discernibility Matrix
Unable to display preview. Download preview PDF.
- 4.Michalski, R.S., Chilausky, R.L.: Learning by being told and learning from examples: An experimental comparison of two methods of knowledge acquisition in context of developing on expert system for soybean disease diagnosm. Policy Analysis and Information Systems 4(2), 125–150 (1980)Google Scholar
- 5.Quinlan, J.: Induction of decision trees. Machine Learning 1, 81–106 (1986)Google Scholar
- 8.Hu, X.H., Nick, C.: Learning in relational databases: A rough set approach. International Journal of Computational Intelligence 11(2), 323–338 (1995)Google Scholar
- 10.Skowron, A., Rauszer, C.: The discernibility matrices and functions in information systems. In: Slowinski, R. (ed.) Intelligent Decision Support: Handbook of applications and advances of rough set theory, pp. 331–362. Kluwer Academic Publishers, Dordrecht (1992)Google Scholar