Title :
An Applied Method for Inferring Knowledge Rules
Author_Institution :
Dept. of Inf. Manage., Hangzhou Dianzi Univ., Zhejiang
Abstract :
A heuristic method for feature selection in inferring knowledge rules is proposed in the paper. It is a rough sets based method, which is used to determine discernibility between attributes and to define significance of attributes. According to the above the necessary condition attributes can be extracted from the data set and the optimal reduct can be constructed by calculating the intersection of a reduct and an entry in a discernibility matrix iteratively. It can be shown that the proposed heuristic algorithm is more efficient and effective in most cases
Keywords :
data mining; feature extraction; inference mechanisms; rough set theory; data mining; discernibility matrix; feature selection; heuristic algorithm; knowledge rule; optimal reduct; rough sets; Data mining; Feature extraction; Heuristic algorithms; Information management; Iterative algorithms; Machine learning; Machine learning algorithms; Pressing; Rough sets; Spatial databases; Data mining; feature selection; reducts; rough sets;
Conference_Titel :
Intelligent Control and Automation, 2006. WCICA 2006. The Sixth World Congress on
Conference_Location :
Dalian
Print_ISBN :
1-4244-0332-4
DOI :
10.1109/WCICA.2006.1714256
