DocumentCode :
2119012
Title :
Attribute discretization algorithm for data stream based on hierarchical clustering and information entropy
Author :
Bo-Wei, Cao ; Qing, Xue ; Ai-Lan, Li
Author_Institution :
Acad. of Armored Forces Eng., Beijing, China
fYear :
2012
fDate :
21-23 April 2012
Firstpage :
193
Lastpage :
196
Abstract :
Attribute discretization is one of the basis pre-treatment methods for data stream mining. For the reason that the attribute discretization algorithm cannot be applied with the highspeed data stream directly, we firstly build a synopsis structure for data stream, then proposed an attribute discretization algorithm based on a synopsis structure, finally, the simulation experiment results show that the method has achieved the problem of data stream attribute discretization.
Keywords :
data mining; entropy; pattern clustering; attribute discretization algorithm; basis pretreatment methods; data stream attribute discretization problem; data stream mining; hierarchical clustering; information entropy; synopsis structure; Decision support systems; Frequency division multiplexing; Mercury (metals); Attribute Discretization; Data Stream; Hierarchical Clustering; Information Entropy; Synopsis Structure;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Consumer Electronics, Communications and Networks (CECNet), 2012 2nd International Conference on
Conference_Location :
Yichang
Print_ISBN :
978-1-4577-1414-6
Type :
conf
DOI :
10.1109/CECNet.2012.6201707
Filename :
6201707
Link To Document :
بازگشت