The aim of this work is to propose a metrological system for the definition of the Extra Virgin Olive Oil Quality based on Panel Test. The information was obtained by a Kohonen neural network that simulates the biological perception mechanisms. This approach allowed to get a two-dimensional mapping of the flavors based on non-linear model. The predominant flavors are not evenly distribute on the map but they are located in specific zone. It is also possible to identify a separation between negative and positive attributes that defines a “quality direction” from low grade to high quality Extra Virgin Olive Oils. Moreover, the overlaps of different flavors on the same neuron of the map suggest possible correlations between them. This is an important starting point to identify the minimum number of independent attributes in order to optimize the Panel Test questionnaire.

Caciotta, M., Giarnetti, S., Leccese, F., Orioni, B., Oreggia, M., Pucci, C., et al. (2016). Flavors mapping by Kohonen network classification of Panel Tests of Extra Virgin Olive Oil. MEASUREMENT, 78(January 2016), 366-372 [10.1016/j.measurement.2015.09.051].

Flavors mapping by Kohonen network classification of Panel Tests of Extra Virgin Olive Oil

CACIOTTA, Maurizio;GIARNETTI, SABINO;LECCESE, Fabio;ORIONI, BARBARA;Pucci, Carlotta;
2016-01-01

Abstract

The aim of this work is to propose a metrological system for the definition of the Extra Virgin Olive Oil Quality based on Panel Test. The information was obtained by a Kohonen neural network that simulates the biological perception mechanisms. This approach allowed to get a two-dimensional mapping of the flavors based on non-linear model. The predominant flavors are not evenly distribute on the map but they are located in specific zone. It is also possible to identify a separation between negative and positive attributes that defines a “quality direction” from low grade to high quality Extra Virgin Olive Oils. Moreover, the overlaps of different flavors on the same neuron of the map suggest possible correlations between them. This is an important starting point to identify the minimum number of independent attributes in order to optimize the Panel Test questionnaire.
2016
Caciotta, M., Giarnetti, S., Leccese, F., Orioni, B., Oreggia, M., Pucci, C., et al. (2016). Flavors mapping by Kohonen network classification of Panel Tests of Extra Virgin Olive Oil. MEASUREMENT, 78(January 2016), 366-372 [10.1016/j.measurement.2015.09.051].
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11590/283982
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 18
  • ???jsp.display-item.citation.isi??? 16
social impact