H. Liu and S. Setiono. Some issues on scalable feature selection. In 4th World Congress of Expert Systems: Application of Advanced Info. Technologies.  Home/Search   Document Details and Download   Summary   Related Articles

....we adapt data mining techniques to act as a preprocessor to construct a set of features to use for classi cation. In past work, the rules produced by data mining algorithms have been used to construct classi ers primarily by ordering the rules into decision lists (e.g. Segal and Etzioni, 1994, Liu et al. 1998 ] or by merging them into more general rules that occur in the training data (e.g. Lee et al. 1998 ] In this paper, we convert the patterns discovered by the mining algorithm into a set of boolean features to feed into standard classi cation algorithms. The classi cation algorithms, in ....

....combined by majority weighting, and they took more care in choosing good parameters for this speci c task. Our goal, here, is to demonstrate that the features produced by FeatureMine improve classi cation performance. Data mining algorithms have often been applied to the task of classi cation. Liu et al. 1998 ] build decision lists out of patterns found by association mining. Ali et al. 1997 ] and [ Bayardo, 1997 ] both combine association rules to form classi ers. Our use of sequence mining is a generalization on association mining. Our pruning rules resemble ones used by [ Segal and Etzioni, 1994 ....

[Article contains additional citation context not shown here]

H. Liu and S. Setiono. Some issues on scalable feature selection. In 4th World Congress of Expert Systems: Application of Advanced Info. Technologies.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC