Abstract | ||
---|---|---|
Spectral clustering has aroused extensive attention in recent years. It performs well for the data with arbitrary shape and can converge to global optimum. But traditional spectral clustering algorithms set the importance of all attributes to 1 as default, when measuring the similarity of data points. In fact, each attribute contains different information and their contributions to the clustering are also different. In order to make full use of the information contained in each attribute and weaken the interference of noise data or redundant attributes, this paper proposes a feature weighted spectral clustering algorithm based on knowledge entropy (FWKE-SC). This algorithm uses the concept of knowledge entropy in rough set to evaluate the importance of each attribute, which can be used as the attribute weights, and then applies spectral clustering method to cluster the data points. Experiments show that FWKE-SC algorithm deals with high-dimensional data very well and has better robustness and generalization ability. © 2013 ACADEMY PUBLISHER. |
Year | DOI | Venue |
---|---|---|
2013 | 10.4304/jsw.8.5.1101-1108 | JSW |
Keywords | Field | DocType |
attribute importance,knowledge entropy,rough set,spectral clustering | Data mining,Fuzzy clustering,CURE data clustering algorithm,Computer science,Artificial intelligence,Cluster analysis,k-medians clustering,Canopy clustering algorithm,Data stream clustering,Correlation clustering,Pattern recognition,Constrained clustering,Machine learning | Journal |
Volume | Issue | Citations |
8 | 5 | 3 |
PageRank | References | Authors |
0.39 | 26 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hongjie Jia | 1 | 177 | 9.98 |
Shifei Ding | 2 | 1074 | 94.63 |
Hong Zhu | 3 | 81 | 7.20 |
Fulin Wu | 4 | 58 | 4.08 |
Lina Bao | 5 | 13 | 1.30 |