Rule extraction using a novel gradient-based method and data dimensionality reduction

Data dimensionality reduction is one of the preprocessing procedures carried out before inputting patterns to classifiers. In many cases, irrelevant or redundant attributes are included in data sets, which interfere with knowledge discovery from data sets. In this paper, we propose a novel gradient-based rule-extraction method with a separability-correlation measure (SCM) ranking the importance of attributes. According to the attribute ranking results, the attribute subsets which lead to the best classification results are selected and used as inputs to a classifier, such as an RBF neural network in our paper. The complexity of the classifier can thus be reduced and its classification performance improved. Our method uses the classification results with reduced attribute sets to extract rules. Computer simulations show that our method leads to smaller rule sets with higher accuracies compared with other methods.