On the feature extraction in discrete space
Yıldız, Olcay Taner
MetadataShow full item record
In many pattern recognition applications, feature space expansion is a key step for improving the performance of the classifier. In this paper, we (i) expand the discrete feature space by generating all orderings of values of k discrete attributes exhaustively, (ii) modify the well-known decision tree and rule induction classifiers (ID3, Quilan, 1986  and Ripper, Cohen, 1995 ) using these orderings as the new attributes. Our simulation results on 15 datasets from UCI repository  show that the novel classifiers perform better than the proper ones in terms of error rate and complexity.