In this paper, we investigate enhancements to an upper classifier -- a decision algorithm generated by an upper classification method, which is one of the classification methods in rough set theory. Specifically, we consider two enhancements. First, we present a stepwise backward feature selection algorithm to preprocess a given set of features. This is important because rough classification methods are incapable of removing superfluous features. We prove that the stepwise backward selection algorithm finds a small subset of relevant features that are ideally sufficient and necessary to define target concepts with respect to a given threshold. This threshold value indicates an acceptable degradation in the quality of an upper classifier. Second, to make an upper classifier adaptive, we associate it with some kind of frequency information, which we call incremental information. An extended decision table is used to represent an adaptive upper classifier. It is also used for interpreting...

In this paper, we study the feature selection problem and develop and analyze four algorithms for feature selection in the context of rough set methodology. The initial state and the feasibility criterion of all these algorithms are the same, that is, they start from a given feature set and progressively remove features, while controlling the amount of degradation in classification quality, but differ in the heuristic used for pruning the search space of features. Our experimental results confirm the analytical results on the complexity of algorithms as well as on controlled degradation of upper classification. The algorithms presented can be used with any methods of deriving a classifier where the quality of classification is monotonically decreasing function while feature set is reduced, though we have adopted the upper classifier in our study. The upper classifier has some important features that makes it suitable for database mining applications. In particular, we have shown that t...

In this paper, we experimentally compare classification of concepts based on rough sets using upper, lower, and elementary set methods in the context of feature selection algorithms. We study the performance of lower, upper, and elementary set classifiers on several machine learning data sets and a real-world data set on duodenal ulcer. The experimental set-up is such that the approximation space (i.e., the set of features retained) can be different depending on the classification method used. In data mining applications, we are more interested in describing the data at hand. Hence, we have used upperbound experiments, where same set of data is used for training and testing. Our initial result suggests that upper classifier performs better than lower classifier for the data set on duodenal ulcer that we have used. Keywords- Rough sets, feature selection, upper classifier, lower classifier, elementary set, database mining, knowledge discovery. 1 Introduction In a practical sense, data...