Title: ISE-Based Sensor Array System for Cassification of Foodstuffs
Citation: MEASUREMENT SCIENCE & TECHNOLOGY vol. 17 p. 6-11
Publication Year: 2006
JRC N°: JRC32161
URI: http://publications.jrc.ec.europa.eu/repository/handle/JRC32161
Type: Articles in periodicals and books
Abstract: A system composed of an array of polymeric membrane ion-selective electrodes and a pattern recognition block—a so-called 'electronic tongue'—was used for the classification of liquid samples: milk, fruit juice and tonic. The task of this system was to automatically recognize a brand of the product. To analyze the measurement set-up responses various non-parametric classifiers such as k-nearest neighbours, a feedforward neural network and a probabilistic neural network were used. In order to enhance the classification ability of the system, standard model solutions of salts were measured (in order to take into account any variation in time of the working parameters of the sensors). This system was capable of recognizing the brand of the products with accuracy ranging from 68% to 100% (in the case of the best classifier).
JRC Directorate:Institute for Health and Consumer Protection Historical Collection

Files in This Item:
There are no files associated with this item.

Items in repository are protected by copyright, with all rights reserved, unless otherwise indicated.