A Novel Chemometric Learning Of Virgin And Deep Frying Olive-Oil By Fourier Transform Infrared Spectroscopy (FT-IR)

English (OpenAlex)

The aim of this study is to examine the machine learning of chemometrically fried oils in virgin olive oil and eight times used olive oil compared using Fourier Transform Infrared spectroscopy (FT-IR). Deep-Frying Oils (DFO was carried out 8 times for 20 minutes. Because of chemical quality of oils, Cis, Trans, Ester, Methyl, Carbonyl, peroxide, unsatrated peroxide and ether groups were used in These results were evaluated by classification and regression using machine learning methods. For these evaluations, firstly classification and regression were made using all properties of these index. In classification models, Support Vector Machines (SVM), K Closest Neighborhood (KNN), Decision Tree (DT) were used. The evaluation was carried out in two stages. In the first stage, half of the dataset was used for training and the other half for testing. In the second stage, all data data was used for training and testing using cross validation (CV) method. The success results obtained using the all data set were 94% with Support Vector Machines and K Nearest Neighborhood methods. According to chemometric strategy, differences between virgin olive oils and DFO were found by high accurancy in this study. This phenomenon also could be possible for other oil type and degree of purity. Results illustrated that the method is very suitable and exact for detection deteriotion of olive oil.