Feature selection using a hybrid associative classifier with masking techniques

Performance in most pattern classifiers is improved when redundant or irrelevant features are removed, however, this is mainly achieved by successive classifiers construction. In this paper hybrid classification and masking techniques are presented as a new feature selection approach. The algorithm uses a hybrid classifier to provide a mask that identifies the optimal subset of features without having to compute a new classifier at each step. This method allows us to identify irrelevant or redundant features for classification purposes. Our results suggest that this method is shown to be a feasible way to identify optimal subset of features.