Parallelized Computing of Attribute Core Based on Rough Set Theory and MapReduce
In this paper, computing attribute core for massive data based on rough set theory and MapReduce is studied, two novel algorithms for computing attribute core are proposed. A case study proves the correctness of the proposed algorithms, and the proposed algorithms are shown more efficient according to the experiment results on a real massive dataset.
Keywordsrough set MapReduce attribute core positive region cloud computing
Unable to display preview. Download preview PDF.
- 4.Guoyin, W.: Rough Set Theory and Knowledge Acquisition. Xi’an Jiaotong University Press, Xi’an (2001) (in Chinese)Google Scholar
- 5.Dongyi, Y., Zhaojiong, C.: A New Discernibility Matrix and The Computation of a Core. Acta Electronica Sinica 30, 1086–1088 (2002)Google Scholar
- 6.Zhangyan, X., Bingru, Y., et al.: Quick Computing Core Algorithm Based on Discernibility Matrix. Computer Engineering and Applications 42, 4–6 (2006)Google Scholar
- 8.Guoyin, W.: Calculation Methods for Core Attributes of Decision Table. Chinese Journal of Computers 26, 611–615 (2003)Google Scholar
- 10.Hadoop MapReduce, http://hadoop.apache.org/mapreduce/