Title :
The Method for Data Reduction Based on Evaluation of Attribute Significance
Author :
He, Chaobo ; Chen, Qimai
Author_Institution :
Dept. of Comput. Sci. & Eng., Zhongkai Univ. of Agric. & Eng., Guangzhou, China
Abstract :
According to the problem of attribute subset selection, the paper put forward a method based on evaluation of attribute significance. Based on the rough set theories the method first defined the calculation formula of attribute significance and designed the corresponding solution algorithm, whose running time complexity decreased about |U|2 orders of magnitude comparing with the similar algorithm on the same test dataset with |U| records. The result of application example shows that this method can reserve the condition attributes, which are important for decision attributes, and also can perform the data reduction operation effectively.
Keywords :
data mining; data reduction; rough set theory; attribute significance; attribute subset selection; data reduction; rough set theory; running time complexity; Agricultural engineering; Agriculture; Application software; Chaos; Computer science; Data engineering; Data mining; Design engineering; Helium; Set theory;
Conference_Titel :
Intelligent Systems and Applications (ISA), 2010 2nd International Workshop on
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-5872-1
Electronic_ISBN :
978-1-4244-5874-5
DOI :
10.1109/IWISA.2010.5473715
