Hybrid Neuro-Fuzzy Classifier Based On Nefclass Model

Abstract

The paper presents hybrid neuro-fuzzy classifier, based on NEFCLASS model, which wasmodified. The presented classifier was compared to popular classifiers – neural networks andk-nearest neighbours. Efficiency of modifications in classifier was compared with methodsused in original model NEFCLASS (learning methods). Accuracy of classifier was testedusing 3 datasets from UCI Machine Learning Repository: iris, wine and breast cancer wisconsin.Moreover, influence of ensemble classification methods on classification accuracy waspresented.

Keywords

• Neuro-fuzzy classifier; NEFCLASS; neural networks; fuzzy systems