Soft Independent Modeling Of Class Analogy Model Research Articles

Classification of Kudoa thyrsites infected and uninfected fish using a handheld near-infrared spectrophotometer, SIMCA and PLS-DA.

Kudoa thyrsites infection of marine fish typically results in myoliquefaction, which is only apparent 24 to 56 h post-mortem. The traditional methods for the detection of K. thyrsites infected fish are time-consuming and destructive, reducing its marketability. This poses a challenge for the fish industry to remove infected fish before it reaches the market or further processing activities. This study investigated the use of near-infrared (NIR) spectroscopy, in combination with soft independent modelling of class analogy (SIMCA) and partial least square discriminant analysis (PLS-DA), for discriminating K. thyrsites infected fish from uninfected fish. Performance of the classification models was evaluated by calculating the sensitivity, specificity and precision. A total of 334 fish samples (200 sardine, 64 hake and 70 kingklip) were used for this study. Infection of K. thyrsites was determined with the use of qPCR assays. Ninety per cent (90%) of the sardine samples, 78% of the hake samples and 37% of the kingklip samples were infected. Class groups of infected and uninfected fish samples were created for the purpose of generating SIMCA and PLS-DA classification models for each species of fish, as well as for a species independent data set. Principal component analysis (PCA) of NIR spectra did not show any clustering for infected and uninfected samples. Calibration and test sample sets were generated for the purpose of building and testing the SIMCA and PLD-DA classification models. SIMCA and PLS-DA were unable to classify test samples correctly into the two classes. The number of misclassifications (NMC) was higher for the SIMCA models than for the PLS-DA models, with more than 60% incorrectly classified. SIMCA classified most of the test samples into both classes. The precision for PLS-DA were 89% for sardine, 81% for hake, 0% for kingklip and 87% for species independent models, however, most samples were classified at infected. The use of NIR spectroscopy and classification models such as SIMCA and PLS-DA showed limited use as a method to distinguish between K. thyrsites infected and uninfected fish samples. Textural and chemical changes during extended frozen storage of the fish samples may have masked the effects associated with K. thyrsites infection. Further studies are suggested where NIR spectroscopy is used in combination with texture analysis and image spectroscopy.

Non-destructive detection of water adulteration level in fresh milk based on combination of dielectric spectrum technology and machine learning method

To rapidly realize the identification of fresh milk for water adulteration and to predict the amount of water adulteration, this study adopts a coaxial probe and a vector network analyzer to analyze the variation laws of dielectric constant ε', dielectric loss factor ε'' and dielectric loss angle tangent tanδ in the range of 2–20 GHz under 100 frequency points. Soft independent modeling of class analogy (SIMCA), Naive Bayes (NB), K-nearest neighbors (KNN), and support vector machine (SVM) models were built based on full dielectric spectra for qualitative testing of adulteration levels in milk. Feature variables of FDS were extracted by using the successive projections algorithm (SPA) and uninformative variables elimination (UVE). Partial least squares regression (PLSR), support vector regression (SVR), and particle swarm optimization least square support vector regression (PSO-LSSVR) models were built for quantitative testing of adulteration levels in milk. The results demonstrate an increasing trend of ε'' and tanδ with increasing frequency and a decreasing trend of ε'. The ε'-SIMCA model achieves the best effect in distinguishing water adulteration in milk, showing accuracy (ACC) of 1, Sensitivity (SNS) of 1, Specificity (SPC) precision (PRE) of 1, and an F1-score (F1) of 1. The tanδ-SPA-PSO-LSSVR model optimally predicts the optimal prediction effect of moisture content of milk, showing an RP2 of 0.994 and an RMSEP of 0.016 %. This study is conducive to building a more comprehensive knowledge system of water adulteration in fresh milk. Its results can provide a theoretical reference in the development of non-destructive detection instruments for natural milk.

Detection and classification of spongy tissue disorder in mango fruit during ripening by using visible-near infrared spectroscopy and multivariate analysis

The esteemed Alphonso mango, cherished in India for its taste, saffron color, texture, and extended shelf life, holds global commercial appeal. Unfortunately, the prevalent spongy tissue disorder in Alphonso mangoes results in a soft and corky texture, with up to 30% of mangoes within a single batch affected. This issue leads to outright rejection during export due to delayed disorder identification. The current assessment method involves destructive sampling, causing substantial fruit loss, and lacks assurance for overall batch quality. In light of the mentioned challenges, this current study focuses on utilizing visible-near infrared (Vis-NIR) spectroscopy as a non-invasive method to assess the internal quality of mangoes. It also enables innovative classification models for automated binary categorization (healthy vs spongy tissue-affected). Through preprocessing and principal component analysis of spectral reflectance data, wavelength ranges of 670–750 nm, 900–970 nm, and 1100–1170 nm were identified for distinguishing healthy and damaged mangoes. Soft independent modelling of class analogy (SIMCA) modelling is a novel approach that can be used to classify mango into healthy and spongy tissue-affected categories for better postharvest management. The accuracy of SIMCA models for classifying mangoes into healthy and spongy tissue-affected classes was highest in the wavelength regions of 670–750 nm and 900–970 nm, being 94.4% and 96.7%, respectively. The spectral reflectance between wavelength region 650–970 nm gave significant and visible differentiation between all stages of spongy tissue, that is, mild, medium, and severe. Furthermore, the application of Vis-NIR spectroscopy alongside SIMCA modelling offers a viable avenue for examining internal abnormalities resulting from diseases or injuries in fruits, broadening its utility for diverse inspection needs.

The quality of EVOOs through the determination of VOCs coupled with SIMCA analysis

Determining the quality of the oil is essential to discriminate EVOOs from oils labeled as such but not having the chemical and physical characteristics to be EVOOs. The purpose of this study was to determine a metric based on multivariate Soft Independent Modeling of Class Analogy (SIMCA), to identify “Premium quality” versus “Standard quality”, 792 EVOO samples throughout VOCs and sensory analysis data. The result of SIMCA showed a correct classification of the “Premium quality” samples and only few samples were excluded from the SIMCA model (95.4 % sensitivity). The combination of VOCs collected by PTR-ToF-MS and SIMCA analysis allowed us to perfectly distinguish EVOO oils from non-EVOO oils. The proposed method could allow a secure, quick and reliable control of the EVOO quality within the global market.

Rapid determination of alprazolam in gin tonic cocktails based on the coupling of IR spectroscopy and chemometrics: A feasibility study

“Drug-facilitated sexual assault" (DFSA) is a sexual assault perpetrated against a person rendered unconscious by a substance that changes her/his physical and/or mental condition, such as ethanol or drugs. Several active pharmaceutical ingredients, whether used alone or with alcoholic beverages, can produce anterograde amnesia and loss of inhibition. The most common pharmaceuticals found in DFSAs are GHB (-hydroxybutyric acid), benzodiazepines (Valium, Xanax, or Roipnol), antidepressants (Venlafaxine), muscle relaxants (cyclobenzaprine), antihistamines, sleeping pills (diphenhydramines), hallucinogens, and opioids. Biological samples are typically examined in cases of suspected DFSA; however, occasionally, samples are sent to labs a long period after being collected, jeopardizing the accuracy of the analysis. As a result, in recent years, the focus has shifted to directly detecting the presence of drugs in alcoholic beverages. In light of this, the purpose of the current study is to build a FT-IR-based approach for the determination of alprazolam in a common long drink (gin and tonic). To achieve this goal, pure (Class Pure) and spiked gin tonics (Class Spiked) were analyzed by Fourier-transform infrared spectroscopy (FT-IR). Afterward, two classifiers were used: Sequential preprocessing through ORThogonalization Linear Discriminant Analysis (SPORT-LDA) and Soft Independent Modeling of Class Analogies (SIMCA). Both approaches provided good results: SPORT-LDA achieved a 95% and a 98% accuracy rate (on the external test set of samples) for spiked and pure cocktails, respectively. This corresponds to the misclassification of 5 spiked and 1 pure drinks. The SIMCA model of class pure achieved 98.2% and 91.7% of specificity and sensitivity, respectively, coinciding with 55 pure samples (over 60) correctly accepted and 2 (over 110) erroneously rejected by the model. In conclusion, the SIMCA model of class pure seems preferable, because it minimizes the type II error. Eventually, the study was circumscribed to the spiked cocktails and a novel SPORT model was used to quantify alprazolam in spiked cocktails. This provided noteworthy results, in fact, it led to a Root Mean Square Error in Prediction (RMSEP) of 0.95, and a R2pred of 0.98.

Machine learning-assisted near-infrared spectroscopy for rapid discrimination of apricot kernels in ground almond

Almonds are one of the most widely consumed seeds in the world, both for their taste and for their high nutritional value. A rapid and non-destructive method to detect adulteration of ground almond with apricot kernels is a necessity in the food industry because of almond's high commodity value and being one of the most consumed tree nuts. Almonds are a target for economically motivated adulteration, and apricot kernel is the most seen adulterant in ground almond. NIR spectroscopy is simple, non-destructive, and cheaper alternatives to traditional methods including chromatography for the detection of almond adulteration. A total of 120 almond samples were purchased in Türkiye. NIR spectra were collected using a portable and benchtop spectrometer and analyzed by Soft Independent Modeling of Class Analogy (SIMCA) and Conditional Entropy (CE) with machine learning algorithms to generate a classification model to authenticate ground almonds. Partial Least Square Regression (PLSR) and CE with machine learning algorithms were used to predict the levels of apricot kernel in ground almonds. Ground almonds were adulterated with apricot kernels at different level (0–50%) with 2% intervals. Both SIMCA and CE algorithms combined with spectral data obtained from the spectrometers provided very distinct clusters for pure and adulterated samples (100% accuracy). Both units also showed superior performance in predicting apricot kernels using PLSR with rval>0.96 with a standard error prediction (SEP) 3.98%. Besides, CE with machine learning algorithms reveal similar performance using benchtop NIR spectrometer (SEP>4.49). Based on the SIMCA, PLSR, and CE-based models, NIR spectroscopy can be used as an alternative methods and showed great potential for real-time surveillance to detect apricot kernel adulteration in ground almond.

Evaluation of Multivariate Filters on Vibrational Spectroscopic Fingerprints for the PLS-DA and SIMCA Classification of Argan Oils from Four Moroccan Regions.

This study aimed to develop an analytical method to determine the geographical origin of Moroccan Argan oil through near-infrared (NIR) or mid-infrared (MIR) spectroscopic fingerprints. However, the classification may be problematic due to the spectral similarity of the components in the samples. Therefore, unsupervised and supervised classification methods-including principal component analysis (PCA), Partial Least Squares-Discriminant Analysis (PLS-DA) and Soft Independent Modeling of Class Analogy (SIMCA)-were evaluated to distinguish between Argan oils from four regions. The spectra of 93 samples were acquired and preprocessed using both standard preprocessing methods and multivariate filters, such as External Parameter Orthogonalization, Generalized Least Squares Weighting and Orthogonal Signal Correction, to improve the models. Their accuracy, precision, sensitivity, and selectivity were used to evaluate the performance of the models. SIMCA and PLS-DA models generated after standard preprocessing failed to correctly classify all samples. However, successful models were produced after using multivariate filters. The NIR and MIR classification models show an equivalent accuracy. The PLS-DA models outperformed the SIMCA with 100% accuracy, specificity, sensitivity and precision. In conclusion, the studied multivariate filters are applicable on the spectroscopic fingerprints to geographically identify the Argan oils in routine monitoring, significantly reducing analysis costs and time.

UV-Vis spectroscopy and one-class modeling for the authentication of the geographical origin of green coffee beans from Cerrado Mineiro, Brazil

Green coffee beans produced in the Cerrado Mineiro region have a Protected Designation of Origin (PDO) certificate. This guarantees that its coffees are among Brazil's most appreciated and valued. This study aimed to develop an authentication method to characterize and differentiate coffee beans from this region. Ultraviolet-visible spectra of 130 green coffee bean samples were used for one-class modeling with SIMCA (soft independent modeling of class analogy), DD-SIMCA (data-driven SIMCA), and OCPLS (one-class partial least squares). Ordered predictors selection (OPS) variable selection was applied to simplify multivariate models and improve their performance. The interpretation of developed models was performed by evaluating the parameter modeling power for variables of SIMCA models. It was possible to assign the most predictive variables to trigonelline and chlorogenic acids as responsible for discriminating coffee beans from Cerrado Mineiro from coffee beans of their three main competitor regions: Caparaó, Mogiana, and Sul de Minas. Finally, methodologies as developed in this work, based on one-class modeling methods, can be proposed to authenticate other coffee-producing regions, food matrices, and agricultural products.

Protected Geographical Indication Discrimination of Zhejiang and Non-Zhejiang Ophiopogonis japonicus by Near-Infrared (NIR) Spectroscopy Combined with Chemometrics: The Influence of Different Stoichiometric and Spectrogram Pretreatment Methods.

This paper presents a method for the protected geographical indication discrimination of Ophiopogon japonicus from Zhejiang and elsewhere using near-infrared (NIR) spectroscopy combined with chemometrics. A total of 3657 Ophiopogon japonicus samples from five major production areas in China were analyzed by NIR spectroscopy, and divided into 2127 from Zhejiang and 1530 from other areas ('non-Zhejiang'). Principal component analysis (PCA) was selected to screen outliers and eliminate them. Monte Carlo cross validation (MCCV) was introduced to divide the training set and test set according to a ratio of 3:7. The raw spectra were preprocessed by nine single and partial combination methods such as the standard normal variable (SNV) and derivative, and then modeled by partial least squares regression (PLSR), a support vector machine (SVM), and soft independent modeling of class analogies (SIMCA). The effects of different pretreatment and chemometrics methods on the model are discussed. The results showed that the three pattern recognition methods were effective in geographical origin tracing, and selecting the appropriate preprocessing method could improve the traceability accuracy. The accuracy of PLSR after the standard normal variable was better, with R2 reaching 0.9979, while that of the second derivative was the lowest with an R2 of 0.9656. After the SNV pretreatment, the accuracy of the training set and test set of SVM reached the highest values, which were 99.73% and 98.40%, respectively. The accuracy of SIMCA pretreated with SNV and MSC was the highest for the origin traceability of Ophiopogon japonicus, which could reach 100%. The distance between the two classification models of SIMCA-SNV and SIMCA-MSC is greater than 3, indicating that the SIMCA model has good performance.

Determination of Possible Adulteration and Quality Assessment in Commercial Honey.

This study aims to predict several quality traits in commercial honey samples simultaneously and to reveal possible honey adulteration using a field-deployable portable infrared spectrometer without any sample preparation. A total of one hundred and forty-seven commercial honey samples were purchased from local and online markets in Turkey and the United States of America (USA), and their soluble solids (°Brix), pH, free acidity, moisture, water activity (aw), glucose, fructose, sucrose, and hydroxymethyl furfural (HMF) contents were determined using reference methods. The HMF (n = 11 samples) and sucrose (n = 21) concentrations were higher than the regulatory limits in some tested samples. The exceeding HMF content may imply temperature abuse during storage and prolonged storing. On the other hand, high sucrose content may indicate possible adulteration with commercial sweeteners. Therefore, soft independent modeling of class analogies (SIMCA) analysis was conducted to reveal this potential sweetener adulteration in the samples, and the SIMCA model was able to identify all the flagged samples. The suggested FT-IR technique may be helpful in regulatory bodies in determining honey authenticity issues as well as assessing the quality characteristics of honey samples in a shorter period and at a lower cost.

Rapid analysis the type of customs paper using Micro-NIR spectrometers and machine learning algorithms

Quick identification of paper types for customs is extremely crucial. Although there are a variety of researches focus on the discrimination of paper, these techniques either require complex preprocessing or large-scale instruments, which are not suitable for customs environments. In this study, we predicted the type of customs paper by using a Micro-NIR spectrometer, and compared the results with Attenuated Total Reflection-Fourier Transform Infrared Spectroscopy (ATR-FTIR). Four different classification algorithms, including linear and non-linear classifiers: K-nearest neighbor (KNN), soft independent modeling of class analogy (SIMCA), partial least squares discriminant analysis (PLS-DA), and least squares-support vector machine (LS-SVM) were employed to classify the type of paper. 20 groups of datasets were selected by Monte Carlo sampling. For Micro-NIR data, the performances of KNN and LS-SVM were outstanding than SIMCA and PLS-DA, with the average accuracies 96.06% and 98.91%, respectively. The outcome of SIMCA and PLS-DA were similar, with the average accuracies 93.00% and 93.97%. Based on the standard derivation, the best stability of models was LS-SVM (1.06%), followed by PLS-DA (1.12%), KNN (1.22%) and SIMCA (3.07%). Compared with ATR-FTIR, the effects of Micro-NIR were better, which were embodies in the better KNN and SIMCA models, and the comparable LS-SVM model. The result demonstrated that the Micro-NIR combined with machine learning algorithms was an effective method to classify the type of customs paper efficiently and quickly, even better than ATR-FTIR.

Classification of Rice Varieties Using SIMCA Applied to NIR Spectroscopic Data.

The selection of suitable rice varieties is the key to achieve high and stable yields, and the correct identification of rice varieties is the prerequisite for seed selection. In this paper, with Kenjing No.5, No.6, and No.9 as the subjects, the effectiveness of near-infrared spectroscopy (NIRS) combined with soft independent modeling of class analogy (SIMCA) in the rapid identification of rice varieties was explored. The modeling sets of Kenjing No.5, No.6, and No.9 samples were respectively used to establish a SIMCA classification model based on principal component analysis (PCA). The accuracies of the model in classifying the rice samples in the modeling set were 100, 100, and 97.5%, respectively. Then, the established SIMCA model was used to identify the rice samples in the test set. According to the experimental findings, the SIMCA analytical method achieved 100% prediction accuracy for the Kenjing No.5, Kenjing No.6, and Hongyu 001-1 samples. For the Kenjing No.9 sample, the accuracy rate was 90% with a 10% sample of Kenjing No.9 misidentified as Kenjing No.6. Therefore, the analytical method of NIRS combined with SIMCA could effectively identify the rice varieties, providing a new approach for the correct selection of planting varieties.

Confocal Raman spectroscopy assisted by chemometric tools: A green approach for classification and quantification of octyl p-methoxycinnamate in oil-in-water microemulsions

This work proposes a green analytical method based on confocal Raman spectrometry and chemometrics tools for the qualitative and quantitative analysis of oil in water microemulsions loaded with the UVB filter octyl p-methoxycinnamate (OMC). The method does not use reagents and only 10 µL of sample are needed. The analyzed microemulsion samples were synthetized in the laboratory using decaethylene glycol mono-dodecyl ether (21.9 %) as non-ionic surfactant, ethyl alcohol (7.3 %) as co-surfactant, oleic acid (1.5 %) as oil phase and water (69.3 %). A physicochemical characterization of the samples was carried out obtaining expected values for droplet size (<20 nm), polydispersity index (<0.290) and conductivity (0.04–0.07 mS cm−1), among others. Linear discriminant analysis (LDA) after selection of variables using the successive projections algorithm (SPA) and soft independent modelling of class analogy (SIMCA) were employed to classify microemulsions with different concentrations of OMC (1.0 to 10.0 %). In the case of LDA, seven Raman spectral variables were previously selected by SPA and after this SPA-LDA model resulted in one error in the prediction set achieving an accuracy of 97.8 %. The SIMCA model (α = 0.05) presented an explained variance higher 97 % using four principal components and it allowed the correct classification of 100 % of the samples (N = 15). In the quantitative analysis, partial least squares (PLS) was used to determine OMC in a range according to international legislation. The model presented optimal statistical parameters (R2 = 0.9699; RMSEP = 0.54 %) and the prediction of samples were in close agreement with HPLC method. Moreover, the greenery of the method was estimated using the AGREE metric and an optimal value of 0.85 was obtained demonstrating the proposed analytical method results environmentally friendly.

Evaluation of FT-IR spectroscopy combined with SIMCA and PLS‑DA for detection of adulterants in pistachio butter

This work scrutinized the adulteration of pistachio butter with three potential edible oils using Fourier transform infrared spectroscopy (FT-IR) and multivariate classification methods. Each of the classes, including non-adulterated samples and adulterated samples consisting of pistachio butter mixed with various concentrations of peanut oil, corn oil and sunflower oil, were classified. For this purpose, multivariate methods, including soft independent modeling of class analogy (SIMCA) and partial least squares discriminant analysis (PLS-DA), were applied to classify the FTIR data. After evaluating the model on unknown samples, the results indicated that PLS-DA was better than the SIMCA model. The classification efficiency of 98% was obtained using the PLS-DA algorithm compared to the SIMCA model with 91% efficiency for prediction. According to the results FTIR spectroscopy, accompanied by multivariate classification methods, can be used as a rapid and reliable method for classifying and predicting adulteration in pistachio butter with edible oils.

Optimizing the soft independent modeling of class analogy (SIMCA) using statistical prediction regions

The ultimate goal of a one-class classifier like the “rigorous” soft independent modeling of class analogy (SIMCA) is to predict with a certain confidence probability, the conformity of future objects with a given reference class. However, the SIMCA model, as currently implemented often suffers from an undercoverage problem, meaning that its observed sensitivity often falls far below the desired theoretical confidence probability, hence undermining its intended use as a predictive tool. To overcome the issue, the most reported strategy in the literature, involves incrementing the nominal confidence probability until the desired sensitivity is obtained in cross-validation. This article proposes a statistical prediction interval-based strategy as an alternative strategy to properly overcome this undercoverage issue. The strategy uses the concept of predictive distributions sensu stricto to construct statistical prediction regions for the metrics. Firstly, a procedure based on goodness-of-fit criteria is used to select the best-fitting family of probability models for each metric or its monotonic transformation, among several plausible candidate families of right-skewed probability distributions for positive random variables, including the gamma and the lognormal families. Secondly, assuming the best-fitting distribution, a generalized linear model is fitted to each metric data using the Bayesian method. This method enables to conveniently estimate uncertainties about the parameters of the selected distribution. Propagating these uncertainties to the best-fitting probability model of the metric enables to derive its so-called posterior predictive distribution, which is then used to set its critical limit. Overall, the evaluation of the proposed approach on a diversity of real datasets shows that it yields unbiased and more accurate sensitivities than existing methods which are not based on predictive densities. It can even yield better specificities than the strategy that attempts to improve sensitivities of existing methods by “optimizing” the type 1 error, especially in low sample sizes’ contexts.

Rapid identification of raw and sulfur-fumigated Paeoniae Radix Alba based on Heracles NEO ultra-fast gas phase electronic nose

Since the current identification method for Paeoniae Radix Alba is complex in operation and long time-consuming with high requirements for technicians, the present study employed Heracles NEO ultra-fast gas phase electronic nose(E-nose) technology to identify raw and sulfur-fumigated Paeoniae Radix Alba decoction pieces in order to establish a rapid identification method for sulfur-fumigated Paeoniae Radix Alba. The odors of raw Paeoniae Radix Alba and its sulfur-fumigated products were analyzed by Heracles NEO ultra-fast gas phase E-nose to obtain the odor chromatographic information. The chemometric model was established, and the data were processed by principal component analysis(PCA), discriminant function analysis(DFA), soft independent modeling of class analogy(SIMCA), and partial least squares discriminant analysis(PLS-DA). The differential compounds of raw and sulfur-fumigated samples were qualitatively analyzed based on the Kovats retention index and Arochembase. As revealed by the comparison of gas chromatograms of raw and sulfur-fumigated Paeoniae Radix Alba, the heights of several peaks in the chromatograms before and after sulfur fumigation changed significantly. The peak(No.8) produced by ethylbenzene disappeared completely due to sulfonation reaction in the process of sulfur fumigation, indicating that ethylbenzene may be the key component in the identification of Paeoniae Radix Alba and its sulfur-fumigated products. In PCA, DFA, SIMCA, and PLS-DA models, the two types of samples were separated into two different regions, indicating that the established models can clearly distinguish between raw and sulfur-fumigated Paeoniae Radix Alba. The results showed that Heracles NEO ultra-fast gas phase E-nose technology could realize the rapid identification of raw and sulfur-fumigated Paeoniae Radix Alba, which provides a new method and idea for the rapid identification of sulfur-fumigated Chinese medicine.

A single screen-printed electrode in tandem with chemometric tools for the forensic differentiation of Brazilian beers

In the present study a single screen-printed carbon electrode (SPCE) and chemometric techniques were utilized for forensic differentiation of Brazilian American lager beers. To differentiate Brazilian beers at the manufacturer and brand level, the classification techniques: soft independent modeling of class analogy (SIMCA), partial least squares regression discriminant analysis (PLS-DA), and support vector machines discriminant analysis (SVM-DA) were tested. PLS-DA model presented an inconclusive assignment ratio of 20%. On the other hand, SIMCA models had a 0 inconclusive rate but an sensitivity close to 85%. While the non-linear technique (SVM-DA) showed an accuracy of 98%, with 95% sensitivity and 98% specificity. The SPCE-SVM-DA technique was then used to distinguish at brand level two highly frauded beers. The SPCE coupled with SVM-DA performed with an accuracy of 97% for the classification of both brands. Therefore, the proposed electrochemicalsensor configuration has been deemed an appropriate tool for discrimination of American lager beers according to their producer and brands.

Information theory and machine learning based authentication of flaxseed oil using portable and handheld vibrational spectroscopy sensors

Flaxseed oil is one of the popular edible oils, and its adulteration has become a concern because of its high commodity value. Therefore, there is a need to detect adulterated flaxseeds with a rapid, non-invasive, and simple method to keep the quality of flaxseed oil. This study aimed to develop a machine learning algorithm and information theory to detect adulterated flaxseed oils by vibrational spectroscopy units combined with chemometrics. Oil spectra were collected with portable/handheld vibrational spectroscopic units and analyzed using conditional entropy, support vector machines (SVM), and soft independent modeling of class analogy (SIMCA) to generate classification models to identify the pureness of oils and partial least square regression (PLSR) to predict the adulterant levels and fatty acid distributions. Conditional entropy showed that two or three wavenumbers/shifts could discriminate the oils using machine learning algorithms with an accuracy of over 95%. SIMCA models determined the oils with an interclass distance (ICD) over 1.1. Specifically, the Fourier transform mid-infrared (FT-MIR) unit provided the best classification of the oils with ICD over 4.9. All instruments showed good performance in predicting fatty acids and adulteration levels with r val ≥0.89 and standard error prediction (SEP) ≤1.7%. Overall, these portable/handheld units showed great potential for rapid, simple, and non-invasive monitoring to identify adulterated flaxseed oils.

Adulteration detection of Sudan Red and metanil yellow in turmeric powder by NIR spectroscopy and chemometrics: The role of preprocessing methods in analysis

Turmeric powder is valued both for its medicinal properties and for its popular culinary use, such as being a component of curry powder. Due to its high demand in international trade, turmeric powder has been subject to economically driven and hazardous chemical adulteration. The objective of this study was to classify and quantify two major adulterants (Sudan Red and Metanil yellow) in turmeric powder using near-infrared (NIR) spectroscopy associated with chemometric models. The absorbance spectra of samples were obtained in frequency regions of 10,000–4200 cm−1. A Soft Independent Modeling of Class Analogy (SIMCA) model was established to determine the authenticity of the turmeric powder. A partial least squares (PLS) regression was used to predict the adulteration level. The different combinations of preprocessing methods such as standard normal variate transformation (SNV), median filter, Savitzky-Golay, wavelet, multiplicative scatter correction (MSC), first derivative (D1) and second derivative (D2) were applied to preprocess the spectral data, in which SNV combined with median filter and D1 performed best. The sample correct classification rate in SIMCA model were found 96.7 and 93.4 in both calibration and validation set respectively. The PLS regression models were evaluated by the coefficient of determination (r2) and root mean square error (RMSE). All PLS regression models established with the combination of different spectral pretreatment except of MSC, Savitzky-Golay, D1 and MSC, Wavelet, D1 showed low values of RMSE and ideal coefficient of determination for both calibration and prediction sets while using relatively few factors. Also, the PLS regression results showed that first derivative led to better calibration models when compared with the second derivative. The obtained statistical parameters for Sudan Red were r2 = 0.90, RMSE = 0.059 in test set and r2 = 0.91 and RMSE = 0.058 for metanil yellow in test set.

Rapid and non-destructive spatially offset Raman spectroscopic analysis of packaged margarines and fat-spread products

Spatially offset Raman spectroscopy (SORS) is a novel technique capable of measuring samples through the original packaging and recovering the spectra without the contribution of surface layers. Here, a portable SORS equipment was used to measure 62 samples of margarines and fat spreads through the original plastic container. Chemometric tools were used to analyse the data obtained. A total of 25 classification models were developed based on: (i) geographical origin, (ii) vegetable oils and (iii) some significant minor constituents present in the samples. Partial least squares-discriminant analysis (PLS-DA), support vector machine (SVM) and soft independent modelling of class analogy (SIMCA) were used for model classification. Quantitative analysis using the partial least squares regression (PLSR) method was also performed to determine the total fat content. In parallel, a benchtop conventional Raman spectrometer was used to analyse the same samples, develop the models with the same training and validation sets in order to compare the results. The calculated classification performance metrics showed better classification models from SORS data than conventional Raman spectroscopy (CRS), highlighting the one-class SIMCA models for margarines containing phytosterols, olive oil or linseed oil. These models exhibited very high predictability (performance parameters with values equal to or higuer than 0.8, 0.9 and 1, respectively). The quantitation model developed from SORS exhibited a higher R2 than from CRS data, and prediction errors below 5% from SORS versus errors between 5 and 13% from CRS data.These results reveal the ability of SORS to avoid the influence of fluorescence, a major drawback when analysing Raman spectra, but also the potential of the technique as a fast, non-destructive and non-invasive analytical technique in the field of food analysis. In conclusion, the tandem 'SORS-chemometrics' has been shown to be a potential tool in the food quality and food authentication fields. Thus, it is necessary to perform further investigations in this field in order to advance the knowledge of this technique and to be able to develop new methods of rapid analysis.