Apidologie 35 (2004) 397-402
DOI: 10.1051/apido:2004025

Electronic nose and neural network use for the classification of honey

Simona Benedetti^a, Saverio Mannino^a, Anna Gloria Sabatini^b and Gian Luigi Marcazzan<sup>b

a</sup>  Department of Food Science and Technologies, Chemistry Unit, via Celoria, 2, 20133 Milano, Italy
^b  Istituto Nazionale di Apicoltura, via di Saliceto, 80, 40128 Bologna, Italy

(Received 28 November 2002; revised 20 September 2003; accepted 21 November 2003)

Abstract - Seventy samples of honey of different geographical and botanical origin were analysed with an electronic nose. The instrument, equipped with 10 Metal Oxide Semiconductor Field Effect Transistors (MOSFET) and 12 Metal Oxide Semiconductor (MOS) sensors, was used to generate a pattern of the volatile compounds present in the honey samples. The sensor responses were evaluated by Principal Component Analysis (PCA) and Artificial Neural Network (ANN). Good results were obtained in the classification of honey samples by using a neural network model based on a multilayer perceptron that learned using a backpropagation algorithm. The methodology is simple, rapid and results suggest that the electronic nose could be a useful tool for the characterisation and control of honey.

Key words: honey / electronic nose / classification / neural network analysis

Corresponding author: Simona Benedetti simona.benedetti@unimi.it

© INRA, EDP Sciences, DIB, AGIB 2004