Classification of oils and margarines by FTIR spectroscopy in tandem with machine learning

Adulteration detection of multi-species vegetable oils in camellia oil using Raman spectroscopy: Comparison of chemometrics and deep learning methods

Oil adulteration is a global challenge in the production of high value-added natural oils. Raman spectroscopy combined with mathematical modeling can be used for adulteration detection of camellia oil (CAO). In this study, the advantages of traditional chemometrics and deep learning methods in identifying and quantifying adulterated CAO were compared from a statistical perspective, and no significant difference were founded in the identification of CAO at different levels of adulteration. The recognition rate of pure and adulterated CAO was 100 %, but there were misclassifications among different adulterated CAOs. The deep learning models outperformed chemometrics methods in quantitative prediction of adulteration level, with RP2, RMSEP, and RPD of the optimal ConvLSTM model achieved 0.999, 0.9 % and 31.5, respectively. The classifiers and models developed in this study based on deep learning have wide applicability and reliability, and provide a fast and accurate method for adulteration detection in CAO.

Machine learning approach for high-throughput phenolic antioxidant screening in black Rice germplasm collection based on surface FTIR

Pigmented rice contains beneficial phenolic antioxidants but analysing them across germplasm collections is laborious and time-consuming. Here we utilised rapid surface Fourier transform infrared (FTIR) spectroscopy and machine learning algorithms (ML) to predict and classify polyphenolic antioxidants. Total phenolics, flavonoids, anthocyanins, and proanthocyanidins were quantified biochemically from 270 diverse global coloured rice collection and attenuated total reflectance (ATR) FTIR spectra were obtained by scanning whole grain surfaces at 800-4000 cm-1. Five ML classification models were optimised using the biochemical and spectral data which performed predictions with 93.5%-100% accuracy. Random Forest and Support Vector Machine models identified key FTIR peaks linked to flavonols, flavones and anthocyanins as important model predictors. This research successfully established direct and non-destructive surface chemistry spectroscopy of the aleurone layer of pigmented rice integrated with ML models as a viable high-throughput platform to accelerate the analysis and profiling of nutritionally valuable coloured rice varieties.

QCL Infrared Spectroscopy Combined with Machine Learning as a Useful Tool for Classifying Acetaminophen Tablets by Brand

The development of new methods of identification of active pharmaceutical ingredients (API) is a subject of paramount importance for research centers, the pharmaceutical industry, and law enforcement agencies. Here, a system for identifying and classifying pharmaceutical tablets containing acetaminophen (AAP) by brand has been developed. In total, 15 tablets of 11 brands for a total of 165 samples were analyzed. Mid-infrared vibrational spectroscopy with multivariate analysis was employed. Quantum cascade lasers (QCLs) were used as mid-infrared sources. IR spectra in the spectral range 980-1600 cm-1 were recorded. Five different classification methods were used. First, a spectral search through correlation indices. Second, machine learning algorithms such as principal component analysis (PCA), support vector classification (SVC), decision tree classifier (DTC), and artificial neural network (ANN) were employed to classify tablets by brands. SNV and first derivative were used as preprocessing to improve the spectral information. Precision, recall, specificity, F1-score, and accuracy were used as criteria to evaluate the best SVC, DEE, and ANN classification models obtained. The IR spectra of the tablets show characteristic vibrational signals of AAP and other APIs present. Spectral classification by spectral search and PCA showed limitations in differentiating between brands, particularly for tablets containing AAP as the only API. Machine learning models, specifically SVC, achieved high accuracy in classifying AAP tablets according to their brand, even for brands containing only AAP.

Hyperspectral identification of oil adulteration using machine learning techniques

Food adulteration is a global concern, drawing attention from safety authorities due to its potential health risks. Detecting and categorizing oil adulteration is crucial for consumer safety and food industry integrity. This research explores hyperspectral imaging (HSI) analysis to identify substandard oil adulteration at different stages. Using the non-destructive HSI Specim Fx 10 system, a method for precise and easy imaging-based fraud detection and classification was proposed. The 670 oil samples, including pure (Almond, Mustard, Coconut, Olive) and adulterated (Sunflower, Castor, Liquid Paraffin), were analyzed. The Savitzky-Golay filter preprocessed the images to remove noise and smooth spectral signatures. The oils were identified using various machine learning approaches, including Support Vector Machines, Logistic Regression, Linear Discriminant Analysis, Random Forests, Decision Trees, K-Nearest Neighbors, and Naïve Bayes with Linear Discriminant Analysis excelling in identification. Performance parameters, including precision, recall, F1-score, and overall accuracy, were calculated. The proposed method achieved a validation accuracy of 100%, outperforming numerous state-of-the-art approaches. This study introduces a robust pipeline for effective oil adulteration detection, offering a significant advancement in food safety and quality control.

Machine Learning Approach to Comparing Fatty Acid Profiles of Common Food Products Sold on Romanian Market

Food composition issues represent an increasing concern nowadays, in the context of diverse food commodity varieties. The contents and types of fatty acids are a constant preoccupation among consumers because of their reflections of nutrition and health problems. This study aims to find the best tool for the rapid and reliable identification of similarities and differences among several food items from a fatty acid profile perspective. An acknowledged GC-FID method was considered, while, for a better interpretation of the analytical results, machine learning algorithms were used. It was possible to develop a recognition model able to simultaneously differentiate, with an accuracy of 79.3%, nine product types using the bagged tree ensemble model. The low number of samples or some similarities among the classes could be responsible for the wrong assignments that occurred, especially in the biscuit, wafer and instant soup classes. Better accuracies values of 95, 86.1, and 97.8% were obtained when the products were grouped into three categories: (1) sunflower oil, mayonnaise, margarine, and cream cheese; (2) biscuits, cookies, margarine, and wafers; and (3) sunflower oil, chips, and instant soup.