Extension of Covering Approximation Space and Its Application in Attribute Reduction
The concept of the complement of a covering is introduced firstly, and then the complement space and extended space of a covering approximation space is defined based on it. It is proved that a covering approximation space will generate the same covering lower and upper approximations as its complement space and extended space if the covering is degenerated to a partition. Moreover, the extended space of a covering approximation space often generate a bigger covering lower approximation or smaller covering upper approximation than itself. Through extending each covering in a covering decision system, the classification ability of each covering is improved. Thus, a heuristic reduction algorithm is developed to eliminate some coverings in a covering decision system without decreasing the classification ability of the system for decision. Theoretic analysis and example illustration indicate that this algorithm can get shorter reduction than other algorithms.
Keywordscovering rough set covering decision system attribute reduction
Unable to display preview. Download preview PDF.
- 3.Slowinski, R., Vsnderpooten, D.: A generalized definition of rough approximations based on similarity. IEEE Tansactions on Knowledge and Data Engineering 12, 331–326 (2000)Google Scholar
- 4.Wang, G.Y.: Extension of rough set under incomplete information systems. Journal of Computer Research and Development 39, 1238–1243 (2002)Google Scholar
- 8.Tsang, E.C.C., Chen, D.G., Lee, J.W.T., Yeung, D.S.: On the upper approximations of covering generalized rough sets. In: 3rd International Conference Machine Learning and Cybermetics, Shanghai, China, pp. 4200–4203 (2004)Google Scholar
- 9.Zhu, W., Wang, F.Y.: A new type of covering rough set. In: 3rd International IEEE Conference Intelligent Systems, London, pp. 444–449 (2006)Google Scholar
- 16.Wang, G.Y.: Rough set theory and knowledge acquisition. Xi’an Jiaotong University Press, Xi’an (2001)Google Scholar