Neuro-fuzzy network for flavour recognition and classification

Abstract

The paper presents the neuro-fuzzy TSK network for the recognition and classification of flavour. The important role in this process fulfills the self-organizing process used for the creation of the inference rules. The self-organizing neurons perform the role of clustering the data into fuzzy groups with different membership values (the preprocessing stage). Applying the automatic control of clusters we have got the optimal size of the TSK network. The developed measuring system has been applied for the recognition of the flavour of different brands of beer. The fuzzy neural network is used for processing the signals obtained from the semiconductor sensor array. The results of numerical experiments have confirmed the excellent performance of such solution.