Quantitative feature evaluation using hybrid neural network and fuzzy logic approach

This paper presents a hybrid feature evaluation method using a competitive learning neural network and fuzzy logic for the analysis of high dimensional data. Not only can we give the quantitative information of the relative importance of features but the contributions of features to each data category can be observed during the analysis. The motivation of this study is to provide a method to discover the nature of data represented by multiple features by evaluating the importance of features representing data and the data best describing the information embedded by features.