Fuzzy-rough Neural Network and Its Application to Vowel Recognition

To measure the fuzzy-rough uncertainty,a fuzzy-rough membership function is introduced.A FRNN(Fuzzy-rough Neural Network) is designed based on fuzzy-rough set theory.The FRNN integrates the ability to process fuzzy and rough information.The test result of speech recognition for five vowel characters indicates that the FRNN has the merit of quick learning and it has better classification performance than BP network,RBF network and Bayesian classifier.