A Fuzzy-GA Wrapper-Based Constructive Induction Model

Constructive Induction is a preprocessing step applied to representation space prior to machine learning algorithms and transforms the original representation with complex interaction into a representation that highlights regularities and is easy to be learned. In this paper a Fuzzy-GA wrapper-based constructive induction system is represented. In this model an understandable real-coded GA is employed to construct new features and a fuzzy system is designed to evaluate new constructed features and select more relevant features. This model is applied on a PNN classifier as a learning algorithm and results show that integrating PNN classifier with Fuzzy-GA wrapper-based constructive induction module will improve the effectiveness of the classifier.