investigating the effect of preprocessing on the authentication of extra virgin olive oil using raman and dd-simca one class modeling

Abstract: data preprocessing, a component of data preparation, describes any type of processing performed on raw data to prepare it for another data processing procedure. in addition to solving data problems, such as corrupt data or irrelevant or missing attributes in the data sets, one may be interested in learning more about the nature of the data, or changing the structure of data in order to prepare the data for a more efficient analysis. one form of preprocessing the calibration data which is performed in virtually all situations is mean centering [1]. in discriminant analysis, mean centering can reduce the effect of differences in signal intensities. in fact, mean centering closes together the scale of signals in different variables and it can effect on class modeling efficiency. pca is a linear modeling method which has been commonly used to explore the data sets. by performing pca, the experimental data matrix d is decomposed into two matrices: scores, containing the information related to objects, and loadings, containing the information related to variables (spectral information). pca, through feature reduction and visual display, allows us to observe the sources of variation in complex data sets. it is, however, possible to extract much more information from a pca. the principal components (pcs) are called latent variables. the purest variables can identify by convex hull of the principal component scores. it was shown by removing all other data points; the data set can be reduced to a very sparse set of essential data points [2]. esps can be used as feature selection techniques without losing important information of the data set. in this regard, the effect of preprocessing (mean centering, normalization) was investigated on efficiency the data driven soft independent modeling of class analogy (dd-simca) results for authentication extra virgin olive oil samples before and after data reduction with esps. in this study by using raman spectra of pure samples and samples adulterated with hazelnut, sunflower, soybean, and canola oils one class models were developed to evaluate the authenticity and adulteration of extra virgin olive oil before and after preprocessing. graphical abstract shows the preliminary results related to the acceptance plots for authenticity and adulterations models.