Improving a neuro-fuzzy classifier using exploratory factor analysis

As of this writing, there exists a large variety of recently developed patt ern classification methods coming from the domain of machine learning and a rtificial intelligence. In this paper, we study the performance of a recent ly developed and improved classifier that integrates fuzzy set theory in a neural network (NEFCLASS). The performance of NEFCLASS is compared to a wel l-known classification technique from machine learning (C4.5). Both C4.5 an d NEFCLASS will be evaluated on a collection of benchmarking data sets. Fur ther, to boost performance of NEFCLASS, we investigate the advantage of pre processing the algorithm by means of an exploratory factor analysis. We com pare the algorithms before and after applying an exploratory factor analysi s on leading performance indicators, as there are the accuracy of the creat ed classifier and the magnitude of the associated rule base. (C) 2000 John Wiley & Sons, Inc.