Olive oil nutritional labeling by using Vis/NIR spectroscopy and compositional statistical methods

Optimized variable selection and machine learning models for olive oil quality assessment using portable near infrared spectroscopy

Olive oil is a key component of the Mediterranean diet, rich in antioxidants and beneficial monounsaturated fatty acids. As a result, high-quality olive oil is in great demand, with its price varying depending on its quality. Traditional chemical tests for assessing olive oil quality are expensive and time-consuming. To address these limitations, this study explores the use of near infrared spectroscopy (NIRS) in predicting key quality parameters of olive oil, including acidity, K232, and K270. To this end, a set of 200 olive oil samples was collected from various agricultural regions of Morocco, covering all three quality categories (extra virgin, virgin, and ordinary virgin). The findings of this study have implications for reducing analysis time and costs associated with olive oil quality assessment. To predict olive oil quality parameters, chemical analysis was conducted in accordance with international standards, while the spectra were obtained using a portable NIR spectrometer. Partial least squares regression (PLSR) was employed along with various variable selection algorithms to establish the relationship between wavelengths and chemical data in order to accurately predict the quality parameters. Through this approach, the study aimed to enhance the efficiency and accuracy of olive oil quality assessment. The obtained results show that NIRS combined with machine learning accurately predicted the acidity using iPLS methods for variable selection, it generates a PLSR with coefficients of determination R2 = 0.94, root mean square error RMSE = 0.32 and ratios of standard error of performance to standard deviation RPD = 4.2 for the validation set. Also, the use of variable selection methods improves the quality of the prediction. For K232 and K270 the NIRS shows moderate prediction performance, it gave an R2 between 0.60 and 0.75. Generally, the results showed that it was possible to predict acidity K232, and K270 parameters with excellent to moderate accuracy for the two last parameters. Moreover, it was also possible to distinguish between different quality groups of olive oil using the principal component analysis PCA, and the use of variable selection helps to use the useful wavelength for the prediction olive oil using a portable NIR spectrometer.

Machine Learning-Enabled NIR Spectroscopy. Part 3: Hyperparameter by Design (HyD) Based ANN-MLP Optimization, Model Generalizability, and Model Transferability

Data variations, library changes, and poorly tuned hyperparameters can cause failures in data-driven modelling. In such scenarios, model drift, a gradual shift in model performance, can lead to inaccurate predictions. Monitoring and mitigating drift are vital to maintain model effectiveness. USFDA and ICH regulate pharmaceutical variation with scientific risk-based approaches. In this study, the hyperparameter optimization for the Artificial Neural Network Multilayer Perceptron (ANN-MLP) was investigated using open-source data. The design of experiments (DoE) approach in combination with target drift prediction and statistical process control (SPC) was employed to achieve this objective. First, pre-screening and optimization DoEs were conducted on lab-scale data, serving as internal validation data, to identify the design space and control space. The regression performance metrics were carefully monitored to ensure the right set of hyperparameters was selected, optimizing the modelling time and storage requirements. Before extending the analysis to external validation data, a drift analysis on the target variable was performed. This aimed to determine if the external data fell within the studied range or required retraining of the model. Although a drift was observed, the external data remained well within the range of the internal validation data. Subsequently, trend analysis and process monitoring for the mean absolute error of the active content were conducted. The combined use of DoE, drift analysis, and SPC enabled trend analysis, ensuring that both current and external validation data met acceptance criteria. Out-of-specification and process control limits were determined, providing valuable insights into the model's performance and overall reliability. This comprehensive approach allowed for robust hyperparameter optimization and effective management of model lifecycle, crucial in achieving accurate and dependable predictions in various real-world applications.

Rapid determination of essential oils functional groups using compositional methods and VisNIR spectroscopy

Essential oils (EOs) are natural products formed by plant volatile compounds. EOs are frequently used in the cosmetic and food industries as well as for domestic purposes, because of their physiochemical, biological and sensory properties. The functional groups (FG), corresponding to various chemical structures present in EOs, are responsible for their biological activities. Therefore, simple, rapid, and economical techniques suitable to characterize the EOs features by measuring their contents, are of great interest. Near-infrared spectroscopy (NIRS) highlights because of its rapidity, and being no-contaminant, as a potential solution. Multivariate correlation methods are commonly used to build NIRS calibrations. These methods were designed for the real space, that is for values comprised between - ∞ and + ∞. However, EOs components are co-dependent data restricted to a simplex space. These are the so-called compositional data (CoDa), needing specific methods to be correlated with a set of spectral explicative variables. In this study, compositional visible and near-infrared (VISNIRS) models have been assessed to quantify the FG of the analyzed EOs. For this purpose, the FG were organized according to their greater frequency in 1) alcohol; 2) ether; 3) ester; 4) aldehydes; 5) ketones, and the hydrocarbon fraction representing the remainder EOs mass, to characterize them. The approach of this study, based on compositional models from VISNIRS spectra, has provided a satisfactory predictive performance for the quantitative estimation of the main FG of the EOs. The proposed approach can be an alternative to traditional chemical methods to characterize EOs.

Effect of Flavoring with Rosemary, Lemon and Orange on the Quality, Composition and Biological Properties of Olive Oil: Comparative Study of Extraction Processes

The goal of this work was to investigate the impact of the flavoring of some aromatic plants/spices, including rosemary (R), lemon (L) and orange (O) at the concentration of 5% and 35% (w/w) added by 2 methods (conventional maceration and direct flavoring), on quality attributes, chemical changes and oxidative stability of extra virgin olive oil (EVOO). Six flavored oils were obtained (EVOO + O, O + O, EVOO + R, O + R, EVOO + L and O + L). The physicochemical parameters (water content, refractive index, acidity and peroxide value, extinction coefficient, fatty acids, volatile aroma profiles, Rancimat test, phenols and pigments composition) of the flavored oils were investigated. Based on the results obtained, it was observed that flavoring with a conventional process provided increased oxidative stability to the flavored oils, especially with rosemary (19.38 ± 0.26 h), compared to that of unflavored oil. The volatile profiles of the different flavored oils revealed the presence of 34 compounds with the dominance of Limonene. The fatty acid composition showed an abundance of mono-unsaturated fatty acids followed by poly-unsaturated ones. Moreover, a high antioxidant activity, a significant peripheral analgesic effect (77.7% of writhing inhibition) and an interesting gastroprotective action (96.59% of ulcer inhibition) have been observed for the rosemary-flavored oil. Indeed, the flavored olive oils of this study could be used as new functional foods, leading to new customers and further markets.

Machine Learning-Enabled NIR Spectroscopy. Part 2: Workflow for Selecting a Subset of Samples from Publicly Accessible Data

An increasingly large dataset of pharmaceutics disciplines is frequently challenging to comprehend. Since machine learning needs high-quality data sets, the open-source dataset can be a place to start. This work presents a systematic method to choose representative subsamples from the existing research, along with an extensive set of quality measures and a visualization strategy. The preceding article (Muthudoss et al.. in AAPS PharmSciTech 23, 2022) describes a workflow for leveraging near infrared (NIR) spectroscopy to obtain reliable and robust data on pharmaceutical samples. This study describes the systematic and structured procedure for selecting subsamples from the historical data. We offer a wide range of in-depth quality measures, diagnostic tools, and visualization techniques. A real-world, well-researched NIR dataset was employed to demonstrate this approach. This open-source tablet dataset ( http://www.models.life.ku.dk/Tablets ) consists of different doses in milligrams, different shapes, and sizes of dosage forms, slots in tablets, three different manufacturing scales (lab, pilot, production), coating differences (coated vs uncoated), etc. This sample is appropriate; that is, the model was developed on one scale (in this research, the lab scale), and it can be great to investigate how well the top models are transferable when tested on new data like pilot-scale or production (full) scale. A literature review indicated that the PLS regression models outperform artificial neural network-multilayer perceptron (ANN-MLP). This work demonstrates the selection of appropriate hyperparameters and their impact on ANN-MLP model performance. The hyperparameter tuning approaches and performance with available references are discussed for the data under investigation. Model extension from lab-scale to pilot-scale/production scale is demonstrated. HIGHLIGHTS: • We present a comprehensive quality metrics and visualization strategy in selecting subsamples from the existing studies • A comprehensive assessment and workflow are demonstrated using historical real-world near-infrared (NIR) data sets • Selection of appropriate hyperparameters and their impact on artificial neural network-multilayer perceptron (ANN-MLP) model performance • The choice of hyperparameter tuning approaches and performance with available references are discussed for the data under investigation • Model extension from lab-scale to pilot-scale successfully demonstrated.

Machine Learning-Enabled NIR Spectroscopy in Assessing Powder Blend Uniformity: Clear-Up Disparities and Biases Induced by Physical Artefacts

NIR spectroscopy is a non-destructive characterization tool for the blend uniformity (BU) assessment. However, NIR spectra of powder blends often contain overlapping physical and chemical information of the samples. Deconvoluting the information related to chemical properties from that associated with the physical effects is one of the major objectives of this work. We achieve this aim in two ways. Firstly, we identified various sources of variability that might affect the BU results. Secondly, we leverage the machine learning-based sophisticated data analytics processes. To accomplish the aforementioned objectives, calibration samples of amlodipine as an active pharmaceutical ingredient (API) with the concentrations ranging between 67 and 133% w/w (dose ~ 3.6% w/w), in powder blends containing excipients, were prepared using a gravimetric approach and assessed using NIR spectroscopic analysis, followed by HPLC measurements. The bias in NIR results was investigated by employing data quality metrics (DQM) and bias-variance decomposition (BVD). To overcome the bias, the clustered regression (non-parametric and linear) was applied. We assessed the model's performance by employing the hold-out and k-fold internal cross-validation (CV). NIR-based blend homogeneity with low mean absolute error and an interval estimates of 0.674 (mean) ± 0.218 (standard deviation) w/w was established. Additionally, bootstrapping-based CV was leveraged as part of the NIR method lifecycle management that demonstrated the mean absolute error (MAE) of BU ± 3.5% w/w and BU ± 1.5% w/w for model generalizability and model transferability, respectively. A workflow integrating machine learning to NIR spectral analysis was established and implemented. Impact of various data learning approaches on NIR spectral data.

Bluetooth-Connected Pocket Spectrometer and Chemometrics for Olive Oil Applications

Unsaturated fatty acids are renowned for their beneficial effects on the cardiovascular system. The high content of unsaturated fatty acids is a benefit of vegetable fats and an important nutraceutical indicator. The ability to quickly check fat composition of an edible oil could be advantageous for both consumers and retailers. A Bluetooth-connected pocket spectrometer operating in NIR band was used for analyzing olive oils of different qualities. Reference data for fatty acid composition were obtained from a certified analytical laboratory. Chemometrics was used for processing data, and predictive models were created for determining saturated and unsaturated fatty acid content. The NIR spectrum also demonstrated good capability in classifying extra virgin and non-extra virgin olive oils. The pocket spectrometer used in this study has a relatively low cost, which makes it affordable for a wide class of users. Therefore, it may open the opportunity for quick and non-destructive testing of edible oil, which can be of interest for consumer, retailers, and for small/medium-size producers, which lack easy access to conventional analytics.

Potential of Near-Infrared Spectroscopy for the Determination of Olive Oil Quality

The analysis of the physico-chemical parameters of quality of olive oil is still carried out in laboratories using chemicals and generating waste, which is relatively costly and time-consuming. Among the various alternatives for the online or on-site measurement of these parameters, the available literature highlights the use of near-infrared spectroscopy (NIRS). This article intends to comprehensively review the state-of-the-art research and the actual potential of NIRS for the analysis of olive oil. A description of the features of the infrared spectrum of olive oil and a quick explanation of the fundamentals of NIRS and chemometrics are also included. From the results available in the literature, it can be concluded that the four most usual physico-chemical parameters that define the quality of olive oils, namely free acidity, peroxide value, K232, and K270, can be measured by NIRS with high precision. In addition, NIRS is suitable for the nutritional labeling of olive oil because of its great performance in predicting the contents in total fat, total saturated fatty acids, monounsaturated fatty acids, and polyunsaturated fatty acids in olive oils. Other parameters of interest have the potential to be analyzed by NIRS, but the improvement of the mathematical models for their determination is required, since the errors of prediction reported so far are a bit high for practical application.

Statistical Analysis of Chemical Element Compositions in Food Science: Problems and Possibilities

In recent years, many analyses have been carried out to investigate the chemical components of food data. However, studies rarely consider the compositional pitfalls of such analyses. This is problematic as it may lead to arbitrary results when non-compositional statistical analysis is applied to compositional datasets. In this study, compositional data analysis (CoDa), which is widely used in other research fields, is compared with classical statistical analysis to demonstrate how the results vary depending on the approach and to show the best possible statistical analysis. For example, honey and saffron are highly susceptible to adulteration and imitation, so the determination of their chemical elements requires the best possible statistical analysis. Our study demonstrated how principle component analysis (PCA) and classification results are influenced by the pre-processing steps conducted on the raw data, and the replacement strategies for missing values and non-detects. Furthermore, it demonstrated the differences in results when compositional and non-compositional methods were applied. Our results suggested that the outcome of the log-ratio analysis provided better separation between the pure and adulterated data and allowed for easier interpretability of the results and a higher accuracy of classification. Similarly, it showed that classification with artificial neural networks (ANNs) works poorly if the CoDa pre-processing steps are left out. From these results, we advise the application of CoDa methods for analyses of the chemical elements of food and for the characterization and authentication of food products.

Estimating Fat Components of Potato Chips Using Visible and Near-Infrared Spectroscopy and a Compositional Calibration Model

When aiming to assess the fat composition of commercial potato chip products, their diversity and the difficulties to verify the nutritional label of batches of chips by official methods are main challenges. Thus, the possibility of using alternative technologies is of great interest for both the industry and the public administration. Near-infrared spectroscopy (NIRS) is a rapid and non-destructive technique that has been proven useful in different applications in the food industry. However, suitable specific treatments of compositional references with NIRS methods have been until now very scarce in the literature. The nutritional label information is commonly given as percentage content values across several nutritional categories. This formally corresponds with the class of so-called compositional data, for which there are specific statistical methods. This study contributes to ongoing research on the feasibility of Vis/NIR spectroscopy for food nutritional labelling. In particular, a calibration model is formulated to estimate the relative content of fat in potato chips products based on NIR spectral signal that integrates a consistent statistical treatment of the nutritional reference data. The method provides accurate estimates of the fat composition, with this including saturated, monounsaturated, and polyunsaturated types of fat, as well as their total fat percentage (cross-validated overall R2 = 0.88 and R2 = 0.82 from ground and fragmented samples respectively) and shows its potential for both nutritional labelling and verification in a rapid and inexpensive manner.

QCM Sensor Arrays, Electroanalytical Techniques and NIR Spectroscopy Coupled to Multivariate Analysis for Quality Assessment of Food Products, Raw Materials, Ingredients and Foodborne Pathogen Detection: Challenges and Breakthroughs

Quality checks, assessments, and the assurance of food products, raw materials, and food ingredients is critically important to ensure the safeguard of foods of high quality for safety and public health. Nevertheless, quality checks, assessments, and the assurance of food products along distribution and supply chains is impacted by various challenges. For instance, the development of portable, sensitive, low-cost, and robust instrumentation that is capable of real-time, accurate, and sensitive analysis, quality checks, assessments, and the assurance of food products in the field and/or in the production line in a food manufacturing industry is a major technological and analytical challenge. Other significant challenges include analytical method development, method validation strategies, and the non-availability of reference materials and/or standards for emerging food contaminants. The simplicity, portability, non-invasive, non-destructive properties, and low-cost of NIR spectrometers, make them appealing and desirable instruments of choice for rapid quality checks, assessments and assurances of food products, raw materials, and ingredients. This review article surveys literature and examines current challenges and breakthroughs in quality checks and the assessment of a variety of food products, raw materials, and ingredients. Specifically, recent technological innovations and notable advances in quartz crystal microbalances (QCM), electroanalytical techniques, and near infrared (NIR) spectroscopic instrument development in the quality assessment of selected food products, and the analysis of food raw materials and ingredients for foodborne pathogen detection between January 2019 and July 2020 are highlighted. In addition, chemometric approaches and multivariate analyses of spectral data for NIR instrumental calibration and sample analyses for quality assessments and assurances of selected food products and electrochemical methods for foodborne pathogen detection are discussed. Moreover, this review provides insight into the future trajectory of innovative technological developments in QCM, electroanalytical techniques, NIR spectroscopy, and multivariate analyses relating to general applications for the quality assessment of food products.

Visible Near Infrared Spectroscopy as a Green Technology: An Environmental Impact Comparative Study on Olive Oil Analyses

The olive oil industry is a significant productive sector in the European Union and the related production process is characterised by practices and techniques associated with several adverse effects on the environment. In the literature, many works on the environmental impact assessment of the olive oil chain have been carried out but the effects of the analytical analyses procedures were considered to be negligible. Currently, the reduction of solvents and of energy consumption in the laboratory has become a crucial aspect to be investigated. In this scenario, non-destructive optical methods based on visible/near-infrared (vis/NIR) spectroscopy represent a simple, rapid, and easy-to-use method to predict olive and olive oil quality parameters. Therefore, the aim of the work was to evaluate the environmental impact of the use of optical vis/NIR technologies for analytical assessment in comparison to chemical analyses on olive oil. The life cycle assessment method (LCA) was used. The functional unit defined for this study was the analysis and a “from cradle to grave” approach was applied. The vis/NIR technology results were distinctly better, by 36 times on average, than the chemical methods. Attention must be paid to the calibration phase of the vis/NIR instrumentation: In this case, the two methods must coexist for this initial procedure to obtain the required reference data for a reliable chemometric model. In conclusion, the vis/NIR spectroscopy gives very reliable results and can be considered a green technology, representing a choice among applications of low environmental impact analytical technologies.