A new cluster method using rough set theory

作者：Zhang, Su-Qi^*; Teng, Jian-Fu; Gu, Jun-Hua

来源：2011 International Conference on Machine Learning and Cybernetics, ICMLC 2011, Guilin, Guangxi, China, 2011-07-10 To 2011-07-13.

DOI：10.1109/ICMLC.2011.6016968

• Cluster
• Clustering solutions
• Clustering techniques
• Condition attributes
• Density-based
• K-means
• Local and global data
• Rough set theory (RST)

This paper proposes a new clustering technique based on elements of rough set theory (RST), for an information system which contains only input information (condition attributes) but without decision (class attribute). The proposed algorithm is unified in its approach to clustering and makes use of both local and global data properties to obtain clustering solutions. The results from some data sets are used to illustrate the technique and establish its efficiency.

• 单位
  天津大学; 河北工业大学