Quality Analysis Of Edible Olive Oil By Chemometrics Methods And FT-IR,GC-MS

The quality of edible oil is closely related with the health of human being.Because of the urging of interest, the phenomenon that edible oil adulterated and shoddy emerge in endlessly. Fourier transform infrared spectroscopy and gas chromatography- mass spectrometry technology combining with chemometrics algorithms were both used to detect the adulteration in edible oils and determine the quality of edible oil. The major work may be summarized as the follows:1、The adulteration in edible oils is briefly analyzed and it should be clear that edible oil quality analysis is of great practical importance. Multifarious methods to analysis edible oil were briefly introduced, including chemical methods(spectroscopic method, chromatography) chemometrics algorithm(support vector machine, random forests).2、 Fourier transform infrared spectroscopy combined with partial least square-discriminant analysis was used to identify the authenticity of olive oils. Partial least square-discriminant analysis(PLS-DA) based on a reduced subset of variables was employed to build classification models. A modified Monte Carlo-uninformative variable elimination(MC-UVE) technique was proposed to select variables.Comparing with Monte Carlo-uninformative variable elimination, successive projections algorithm, competitive adaptive reweighted sampling etc, PLS-DA model using the selected variables by the modified MC-UVE provided better results. The classification accuracy obtained by cross validation was 97.6% and the correct classification rate of the prediction set was 100%. The results show that the model based on the modified MC-UVE is successful in the inspection of the authenticity of olive oils.3、Gas chromatography-mass spectrometry(GC-MS) was applied to analyze the fatty acid composition of sixty six samples from six different kinds of edible vegetable oils. The fatty acid profiles of these edible vegetable oils were used to classify the type of edible oils. For improving the classification accuracy of vegetableoils with respect to type, the support vector machine(SVM) technique, optimized using the genetic algorithm(GA), was employed to construct the classification model.The effectiveness of the GA-SVM combination in classification was compared with that of other well-known strategies for classification, such as minimum distance classification(MDC) and linear discriminant analysis(LDA). In addition, the Kennard-Stone algorithm was used to select the representative training samples and compared with the random sampling method. The misclassification rate obtained by cross validation was 8.48 % and the misclassification rate of the prediction set was3.03%. The results reveal that this strategy is of great promise in flexible and accurate classification of edible vegetable oils.4、Fourier transform infrared spectroscopy combined with random forests was used to identify the authenticity of olive oils. First of all, the data matrix is analyzed using principal component analysis to explore separation or clusters of all the samples.RF was subsequently employed to construct the classification model. Compared with partial least square-discriminant analysis and support vector machine were employed,random forests have better effect of classifying. The classification accuracy obtained by training set was 99.08% and the correct classification rate of the prediction set was97.76%. In addition, quantitative analysis was carried out through partial least squares,Support vector regression, random forest. The results reveal that this method was an accurate and rapid strategy for identifying olive oils.