Neural networks applied to characterize blends containing refined and extra virgin olive oils

Rapid quantification of single component oil in perilla oil blends by ultraviolet-visible spectroscopy combined with chemometrics

As a unconventional oil, perilla oil is much more expensive than conventional oils since it has the highest content of α-linolenic acid among vegetable oils. Thus the adulteration of perilla oil is serious, which needs to be solved. In this study, the single component oil in perilla oil blends were first quantitatively analyzed by ultraviolet-visible (UV-vis) spectroscopy combined with chemometric methods. Soybean oil and palm oil were added into perilla oil to form binary and ternary perilla oil blends. Partial least squares (PLS), back propagation-artificial neural network (BP-ANN), support vector regression (SVR) and extreme learning machine (ELM) were compared and the best model was selected for calibration. In order to improve the prediction performance of the calibration model, ten preprocessing methods and five variable selection methods were investigated. Results show that PLS was the best calibration method for binary and ternary perilla oil blends. For binary perilla oil blends, the correlation coefficients of prediction (Rp) obtained by PLS were both above 0.99, which does not need preprocessing and variable selection. For ternary perilla oil blends, after the best continuous wavelet transform (CWT) preprocessing and discretized whale optimization algorithm (WOA) variable selection, the Rp values obtained by the best model CWT-WOA-PLS were all above 0.97. This research provides a common framework for calibration of perilla oil blends, which maybe a promising method for quality control of perilla oil in industry.

Classification of olive cultivars by machine learning based on olive oil chemical composition

Extra virgin olive oil traceability and authenticity are important quality indicators, and are currently the subject of exhaustive research, for developing methods to secure olive oil origin-related issues. The aim of this study was the development of a classification model capable of olive cultivar identification based on olive oil chemical composition. To achieve our aim, 385 samples of two Greek and three Italian olive cultivars were collected during two successive crop years from different locations in the coastline part of western Greece and southern Italy and analyzed for their chemical characteristics. Principal Component Analysis showed trends of differentiation among olive cultivars within or between the crop years. Artificial intelligence model of the XGBoost machine learning algorithm showed high performance in classifying the five olive cultivars from the pooled samples.

A Review of Advanced Methods for the Quantitative Analysis of Single Component Oil in Edible Oil Blends

Edible oil blends are composed of two or more edible oils in varying proportions, which can ensure nutritional balance compared to oils comprising a single component oil. In view of their economical and nutritional benefits, quantitative analysis of the component oils in edible oil blends is necessary to ensure the rights and interests of consumers and maintain fairness in the edible oil market. Chemometrics combined with modern analytical instruments has become a main analytical technology for the quantitative analysis of edible oil blends. This review summarizes the different oil blend design methods, instrumental techniques and chemometric methods for conducting single component oil quantification in edible oil blends. The aim is to classify and compare the existing analytical techniques to highlight suitable and promising determination methods in this field.

Near infrared spectroscopy combined with chemometrics for quantitative analysis of corn oil in edible blend oil

In this study, near infrared (NIR) spectroscopy combined with chemometrics was used for the quantitative analysis of corn oil in binary to hexanary edible blend oil. Sesame oil, soybean oil, rice oil, sunflower oil and peanut oil were mixed with corn oil subsequently to form binary, ternary, quaternary, quinary and hexanary blend oil datasets. NIR spectra for the five order blend oil datasets were measured in a transmittance mode in the range of 12000-4000 cm^-1. Partial least square (PLS) was used to build models for the five datasets. Six spectral preprocessing methods and their combinations were investigated to improve the prediction performance. Furthermore, the optimal preprocessing-PLS models were further optimized by uninformative variable elimination (UVE), Monte Carlo uninformative variable elimination (MCUVE) and randomization test (RT) variable selection methods. The optimal models acquire root mean square error of prediction (RMSEP) of 1.7299, 2.2089, 2.3742, 2.5608 and 2.6858 for binary, ternary, quaternary, quinary and hexanary blend oil datasets, respectively. The determination coefficients of prediction set (R²_P) and residual predictive deviations (RPDs) for the five datasets are all above 0.93 and 3. Results show that the prediction accuracy is gradually decreased with the increasing of mixture order of blend oil. However, with proper spectral preprocessing and variable selection, the optimal models present good prediction accuracy even for the higher order blend oil. It demonstrates that NIR technology is feasible for determining the pure oil contents in binary to hexanary blend oil.

Smartphone-based handheld Raman spectrometer and machine learning for essential oil quality evaluation

We present a method, utilising a smartphone-based miniaturized Raman spectrometer and machine learning for the fast identification and discrimination of adulterated essential oils (EOs). Firstly, the approach was evaluated for discrimination of pure EOs from those adulterated with solvent, namely benzyl alcohol. In the case of ylang-ylang EO, three different types of adulteration were examined, adulteration with solvent, cheaper vegetable oil and a lower price EO. Random Forest and partial least square discrimination analysis (PLS-DA) showed excellent performance in discriminating pure from adulterated EOs, whilst the same time identifying the type of adulteration. Also, utilising partial least squares regression analysis (PLS) all adulterants, namely benzyl alcohol, vegetable oil and lower price EO, were quantified based on spectra recorded using the smartphone Raman spectrometer, with relative error of prediction (REP) being between 2.41-7.59%.

Study of the Evolution of Pigments from Freshly Pressed to 'On-the-Shelf' Extra-Virgin Olive Oils by Means of Near-UV Visible Spectroscopy

Spectroscopic non-destructive methods have high potentialities as fast, cheap and easy-to-be-used approaches to address olive oil quality and authenticity. Based on previous research where near-UV Visible spectroscopy was used to investigate extra-virgin olive oils (EVOOs) and their main pigments’ content (i.e., β-carotene, lutein, pheophytin a and pheophytin b), we have implemented the spectral deconvolution method in order to follow the EVOO’s life, from ‘freshly pressed’ to ‘on-the-shelf’ EVOO samples at different storage time. In the first part of the manuscript, the new implemented deconvolution spectroscopic method aimed to quantify two additional pigments, namely chlorophyll a and chlorophyll b, is described and tested on ‘ad hoc’ samples with known concentrations of chlorophylls. The effect of light exposure and acidification was investigated to test the reliability and robustness of the spectral deconvolution. In the second part of the work, this approach was used to study the kinetic of pigments’ degradation in several monocultivar fresh EVOO samples under optimal storage’s conditions. The results here reported show that this spectroscopic deconvolution approach is a good method to study fresh EVOOs too; moreover, the proposed method revealed to be sensitive to detect eventual stresses of olive oil samples stored in not-good conditions.

Integrating metabolomic data with machine learning approach for discovery of Q-markers from Jinqi Jiangtang preparation against type 2 diabetes

Background

Jinqi Jiangtang (JQJT) has been widely used in clinical practice to prevent and treat type 2 diabetes. However, little research has been done to identify and classify its quality markers (Q-markers) associated with anti-diabetes bioactivity. In this study, a strategy combining mass spectrometry-based untargeted metabolomics with backpropagation artificial neural network (BP-ANN)-based machine learning approach was proposed to screen Q-markers from JQJT preparation.

Methods

This strategy mainly involved chemical profiling of herbal medicines, statistic processing of metabolomic datasets, detection of different anti-diabetes activities and establishment of BP-ANN model. The chemical features of seventy-eight batches of JQJT extracts were first profiled by using the untargeted UPLC-LTQ-Orbitrap metabolomic approach. The chemical features obtained which were associated with different anti-diabetes activities based on three modes of action were normalized, ranked, and then pre-selected by using ReliefF feature selection. BP-ANN model was then established and optimized to screen Q-markers based on mean impact value (MIV).

Results

Optimized BP-ANN architecture was established with high accuracy of R > 0.9983 and relative low error of MSE < 0.0014, which showed better performance than that of partial least square (PLS) model (R² < 0.5). Meanwhile, the BP-ANN model was subsequently applied to further screen potential bioactive components from the pre-selected chemical features by calculating their MIVs. With this machine learning model, 10 potential Q-markers with bioactivity were discovered from JQJT. The tested anti-diabetes bioactivities of 78 batches of JQJT could be accurately predicted.

Conclusions

This proposed artificial intelligence approach is desirable for quick and easy identification of Q-markers with bioactivity from JQJT preparation.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13020-021-00438-x.

Weighted multiscale support vector regression for fast quantification of vegetable oils in edible blend oil by ultraviolet-visible spectroscopy

Weighted multiscale support vector regression combined with ultraviolet-visible (UV-Vis) spectra for quantitative analysis of edible blend oil is proposed. In the approach, UV-Vis spectra of the training set are decomposed into a certain number of intrinsic mode functions (IMFs) and a residue by empirical mode decomposition (EMD) at first. Then support vector regression (SVR) sub-models are built on each IMF and residue. For prediction set, the spectra are decomposed as done on the training set and the final predictions are obtained by integrating SVR sub-model predictions by weighted average. The weight of the sub-model is the reciprocal of the fourth power of the root mean square error of cross-validation (RMSECV). For predicting peanut oil in binary blend oil and sesame oil in ternary blend oil, the proposed method has superiority in root mean square error of prediction (RMSEP) and correlation coefficient (R) compared with SVR and partial least squares (PLS).

Determination of Pigments in Virgin and Extra-Virgin Olive Oils: A Comparison between Two Near UV-Vis Spectroscopic Techniques

The colour of olive oil is due to the presence of natural pigments belonging to the class of carotenoids, chlorophylls, and their derivatives. These substances, other than being responsible for the colour, an important qualitative feature of the oil, have antioxidant and, more generally, nutraceutical properties and their quantification can be related to the product’s quality and authenticity. In this work, we have quantified the total amount of carotenoids and chlorophylls’ derivatives in several virgin and extra-virgin olive oils produced in Italy, by using two different methods that are based on near-ultraviolet-visible absorption spectroscopy. The first method defines two indexes, K670 and K470, related to absorbance values of oil at wavelengths of 670 and 470 nm, respectively. The second method is based on the mathematical deconvolution of the whole absorption spectrum of the oil to obtain the concentrations of four main pigments present in olive oils: β-carotene, lutein, pheophytin A, and pheophytin B. The concentrations of the total carotenoids and total chlorophylls’ derivatives, as obtained by the two spectroscopic methods, are compared and the results are discussed in view of the practical usefulness of spectroscopic techniques for a fast determination of pigments in olive oil.

A critical review on the use of artificial neural networks in olive oil production, characterization and authentication

Artificial neural networks (ANN) are computationally based mathematical tools inspired by the fundamental cell of the nervous system, the neuron. ANN constitute a simplified artificial replica of the human brain consisting of parallel processing neural elements similar to neurons in living beings. ANN is able to store large amounts of experimental information to be used for generalization with the aid of an appropriate prediction model. ANN has proved useful for a variety of biological, medical, economic and meteorological purposes, and in agro-food science and technology. The olive oil industry has a substantial weight in Mediterranean's economy. The different steps of the olive oil production process, which include olive tree and fruit care, fruit harvest, mechanical and chemical processing, and oil packaging have been examined in depth with a view to their optimization, and so have the authenticity, sensory properties and other quality-related properties of olive oil. This paper reviews existing literature on the use of bioinformatics predictive methods based on ANN in connection with the production, processing and characterization of olive oil. It examines the state of the art in bioinformatics tools for optimizing or predicting its quality with a view to identifying potential deficiencies or aspects for improvement.