DocumentCode
2637682
Title
Attribute Division Algorithm Based on Entropy
Author
Dong, Liyan ; Sun, Minghui ; Ren, Xiangshi
Author_Institution
Coll. of Comput. Sci. & Technol., Jilin Univ., Changchun
fYear
2008
fDate
18-20 June 2008
Firstpage
365
Lastpage
365
Abstract
In order to preprocess data for data mining algorithms, an attribute division algorithm based on entropy is given through analyzing the physical meaning of information entropy. The algorithm measures the relativity among the different attributes based on entropy qualitatively and quantitatively. The original attribute set is divided into several subsets which are conditional independence by k-means clustering algorithm. Experimental results show that this algorithm can be used for data preprocessing.
Keywords
data mining; entropy; pattern clustering; attribute division algorithm; data mining algorithms; data preprocessing; information entropy; k-means clustering algorithm; Algorithm design and analysis; Clustering algorithms; Computer science; Data mining; Data preprocessing; Educational institutions; Information analysis; Information entropy; Mutual information; Random variables;
fLanguage
English
Publisher
ieee
Conference_Titel
Innovative Computing Information and Control, 2008. ICICIC '08. 3rd International Conference on
Conference_Location
Dalian, Liaoning
Print_ISBN
978-0-7695-3161-8
Electronic_ISBN
978-0-7695-3161-8
Type
conf
DOI
10.1109/ICICIC.2008.677
Filename
4603554
Link To Document