Examinando por Autor "Sanmartin, Chiara"
Mostrando 1 - 3 de 3
- Resultados por página
- Opciones de ordenación
Ítem Classification of olive fruits and oils based on their fatty acid ethyl esters content using electronic nose technology(SPRINGER, 2021-08-20) Martínez Gila, Diego Manuel; Sanmartin, Chiara; Navarro Soto, Javiera; Mencarelli, Fabio; Gómez Ortega, Juan; Gámez García, JavierAmong several parameters defined for the commercial classes of virgins olive oils (VOOs), there is one, the fatty acid ethyl ester (FAEE), that is only define for the best quality (EVOO). Fruit condition mainly determine these compounds, although, extraction process or deplorable storage condition could rise them up. The FAEE oxidation compound are originated by adding an alcohol chain into the oil molecule. Therefore, the hypothesis of this study is that the inherent constitution of FAEE entails a modification of the volatile profile of oils and olives and this is significant enough to be detected using an electronic nose. With this aim, different samples of olives and oils were analyzed in an accredited laboratory. On the other hand, volatiles from the same samples were captured by an electronic nose. The classification problem was analyzed from two points of view or models. The first was to classify fruits and oils based on whether they are within or outside the legal limits. And the second problem was oriented to classify fruits and oils based on their high or low FAEE content but being within the legal limits. To solve this problem, three classification algorithms were evaluated: Naïve Bayes (NB), Multilayer Perceptron (MLP) and Sequential Minimal Optimization (SMO). For the first model, a well-classified sample rate of 80.3% was obtained for NB and 100% for SMO and MLP, for measurements on oils. The same model evaluated with measurements on olives yielded a success rate of 87.5% with NB, 87.7% with MLP and 82.1% with SMO. For the second model, the suc- cess rates remained within the same orders of magnitude. For measurements on oils, the results were 89.7% for NB, 92.5% for MLP and 100% for SMO. And for measurements on olives the results were 77.9% for NB, 88.6% for MLP and 90.9% for SMO. In all cases, the characteristics that worked best were those obtained from the first derivative of the electronic nose response. Based on these results, the e-nose demonstrate to be a non-invasive technology suitable for the classification of olive fruits and oils based on their FAEE content.Ítem Classification of olive fruits and oils based on their fatty acid ethyl esters content using electronic nose technology(SPRINGER, 2021-08-20) Martínez Gila, Diego Manuel; Sanmartin, Chiara; Navarro Soto, Javiera; Mencarelli, Fabio; Gómez Ortega, Juan; Gámez García, JavierAmong several parameters defined for the commercial classes of virgins olive oils (VOOs), there is one, the fatty acid ethyl ester (FAEE), that is only define for the best quality (EVOO). Fruit condition mainly determine these compounds, although, extraction process or deplorable storage condition could rise them up. The FAEE oxidation compound are originated by adding an alcohol chain into the oil molecule. Therefore, the hypothesis of this study is that the inherent constitution of FAEE entails a modification of the volatile profile of oils and olives and this is significant enough to be detected using an electronic nose. With this aim, different samples of olives and oils were analyzed in an accredited laboratory. On the other hand, volatiles from the same samples were captured by an electronic nose. The classification problem was analyzed from two points of view or models. The first was to classify fruits and oils based on whether they are within or outside the legal limits. And the second problem was oriented to classify fruits and oils based on their high or low FAEE content but being within the legal limits. To solve this problem, three classification algorithms were evaluated: Naïve Bayes (NB), Multilayer Perceptron (MLP) and Sequential Minimal Optimization (SMO). For the first model, a well-classified sample rate of 80.3% was obtained for NB and 100% for SMO and MLP, for measurements on oils. The same model evaluated with measurements on olives yielded a success rate of 87.5% with NB, 87.7% with MLP and 82.1% with SMO. For the second model, the suc- cess rates remained within the same orders of magnitude. For measurements on oils, the results were 89.7% for NB, 92.5% for MLP and 100% for SMO. And for measurements on olives the results were 77.9% for NB, 88.6% for MLP and 90.9% for SMO. In all cases, the characteristics that worked best were those obtained from the first derivative of the electronic nose response. Based on these results, the e-nose demonstrate to be a non-invasive technology suitable for the classification of olive fruits and oils based on their FAEE content.Ítem Prediction of Fruity Aroma Intensity and Defect Presence in Virgin Olive Oil Using an Electronic Nose(MDPI, 2021-03-25) Cano Marchal, Pablo; Sanmartin, Chiara; Satorres Martínez, Silvia; Gómez Ortega, Juan; Mencarelli, Fabio; Gámez García, JavierThe organoleptic profile of a Virgin Olive Oil is a key quality parameter that is currently obtained by human sensory panels. The development of an instrumental technique capable of providing information about this profile quickly and online is of great interest. This work employed a general purpose e-nose, in lab conditions, to predict the level of fruity aroma and the presence of defects in Virgin Olive Oils. The raw data provided by the e-nose were used to extract a set of features that fed a regressor to predict the level of fruity aroma and a classifier to detect the presence of defects. The results obtained were a mean validation error of 0.5 units for the prediction of fruity aroma using lasso regression; and 88% accuracy for the defect detection using logistic regression. Finally, the identification of two out of ten specific sensors of the e-nose that can provide successful results paves the way to the design of low-cost specific electronic noses for this application.