Classification of milk by means of an electronic nose and SVM neural network

The paper presents the application of support vector machine (SVM) neural approach to the calibration of the electronic nose arrangement for milk recognition. The semiconductor gas sensor array mounted into the measurement test chamber has been used to measure the odour. The pre-processed sensor signals are applied to the SVM neural network performing the role of recognition and classification of the milk. The results of numerical experiments of the recognition of different types of milk have been presented and discussed. (C) 2003 Elsevier B.V. All rights reserved.