Discrimination of apricot cultivars by gas multisensor array using an artificial neural network

• Published in: Biosystems engineering Vol. 97; no. 3; pp. 371 - 378
• Main Authors: Paola Parpinello, Giuseppina, Fabbri, Angelo, Domenichelli, Sara, Mesisca, Veronica, Cavicchi, Lisa, Versari, Andrea
• Format: Journal Article
• Language: English
• Published: Kidlington Elsevier Ltd 01.07.2007; Elsevier
• Subjects: Agricultural machinery and engineering; Agronomy. Soil science and plant productions; apricots; Biological and medical sciences; cultivars; electronic nose; equations; food packaging; food quality; Fundamental and applied biological sciences. Psychology; gases; Generalities. Biometrics, experimentation. Remote sensing; genetic variation; Genetics and breeding of economic plants; headspace analysis; mathematical models; measurement; neural networks; Bioengineering; Multisensor; Stone fruit; Rosaceae; Apricot; Climacteric; Neural network; Temperate zone; Engineering; Discrimination; Fruit crop; Dicotyledones; Angiospermae; Prunus armeniaca; Spermatophyta; Agriculture; Fruit tree; Artificial intelligence; Cultivar
• ISSN: 1537-5110; 1537-5129
• DOI: 10.1016/j.biosystemseng.2007.02.017

In this study, an array of 10 metal-oxide sensors, a so-called electronic nose, in combination with artificial neural networks (ANN), was used to analyse the headspace of apricot fruits in order to classify 10 different cultivars. The ANN coupled to the electronic nose required a small computational effort to assure a satisfactory effectiveness. Different configurations were explored, ranging from one to three hidden layers. The single hidden layer ANN with 35 neurons gave a correlation index higher than 80% on test data set. The trained system allowed at least 90% correct classification of apricot cultivars, showing the potential of these new tools in the quality control of fruits.