Soft Independent Modeling Of Class Analogy Methods Research Articles

Rapid and non-destructive quality verification of epoxy resin product using ATR-FTIR spectroscopy coupled with chemometric methods

Epoxy resin is the most commonly used thermosetting resin in various domains. Nevertheless, in industrial production, manual operations are still the mainstream in the weighing and mixing procedures of resin raw materials, where operating errors are inevitable, resulting in the performance of the final product uncontrollable. This paper presented a novel method by attenuated total reflection-Fourier transform infrared (ATR-FTIR) spectroscopy for rapid and non-destructive quality verification of epoxy resin prepolymers, in which the principal component analysis (PCA) and the soft independent modeling of class analogy (SIMCA) are applied to improve the detection capability of abnormal products. Eleven abnormal samples of 83 epoxy resin prepolymers are screened out by the SIMCA method, which is 84.6% in agreement with the traditional differential scanning calorimetry (DSC) testing results. It indicates that ATR-FTIR in tandem with the SIMCA method can be used as an alternative approach for rapid quality verification of resin systems in the industry.

Comparison of partial least squares‐discriminant analysis and soft independent modeling of class analogy methods for classification of Saccharomyces cerevisiae cells based on mid‐infrared spectroscopy

AbstractSaccharomyces cerevisiae is a widely studied and highly utilized eukaryotic organism, ideally suited to high throughput metabolic analysis, being a powerful model for understanding basic cell biology. This study compares the models developed by two supervised methods, such as the partial least squares‐discriminant analysis (PLS‐DA) and soft independent modeling of class analogy (SIMCA), using mid‐infrared (MIR) spectra registered during the growth of S. cerevisiae in bioreactor. The spectra were analyzed using the principal component analysis (PCA), with resolution in five different classes, which were well defined in terms of their biochemical parameters. The SIMCA model showed a significant fitting, 99%, validation, 98%, and prediction parameters, 97%, comparatively with PLS‐DA model. Regarding accuracy, sensitivity, and specificity parameters, a value between 83% and 100% was achieved for both methods, but the SIMCA method showed significant specificity and sensitivity values, 98%–100%, representing a suitable classification tool of yeast cells. According to these results, the MIR spectra associated with chemometric tools can be considered a valued strategy for a classification and detailed analysis for an accurate control, allowing to predict the evolution of the corrected process in advance, avoiding losses of time and costs associated with new fermentations, identifying a significant number of samples in any biotechnological process.

Geographical discrimination of saffron (Crocus sativus L.) using ICP-MS elemental data and class modeling of PDO Zafferano dell’Aquila produced in Abruzzo (Italy)

PDO (protected designation of origin) Zafferano dell’Aquila (AQ), Iranian (IR), and commercial (CS) saffron samples were analyzed by inductively coupled plasma mass spectrometry (ICP-MS). The ICP-MS data of 30 elements were handled by unsupervised (principal component analysis (PCA)) and supervised (linear discriminant analysis (LDA)) multivariate statistical methods to identify a subset of discriminant variables useful for geographical classification. Moreover, class modeling of AQ saffron was performed by both UNEQ (unequal disperses classes) and SIMCA (soft independent modeling of class analogy) methods. A good differentiation of the AQ, IR, and CS samples was obtained by the LDA based on four selected elements: Sr, Ca, Mo, and Fe. A UNEQ class model for the PDO AQ saffron based on the above four elements provided 100% sensitivity (all authentic AQ saffron were accepted) and 100% specificity (all IR and CS were rejected), while slightly worse results were obtained using the SIMCA (89% sensitivity and 96% specificity).

Variable selection for multivariate classification aiming to detect individual adulterants and their blends in grape nectars

During the quality inspection control of fruit beverages, some types of adulterations can be detected, such as the addition or substitution with less expensive fruits. To determine whether grape nectars were adulterated by substitution with apple or cashew juice or by a mixture of both, a methodology based on attenuated total reflectance Fourier transform mid infrared spectroscopy (ATR-FTIR) and multivariate classification methods was proposed. Partial least squares discriminant analysis (PLS-DA) and soft independent modeling of class analogy (SIMCA) models were developed as multi-class methods (classes unadulterated, adulterated with cashew and adulterated with apple) with the full-spectra. PLS-DA presented better performance parameters than SIMCA in the classification of samples with just one adulterant, while poor results were achieved for samples with blends of two adulterants when using both classification methods. Three variable selection methods were tested in order to improve the effectiveness of the classification models: interval partial least squares (iPLS), variable importance in projection scores (VIP scores) and a genetic algorithm (GA). Variable selection methods improved the performance parameters for the SIMCA and PLS-DA methods when they were used to predict samples with only one adulterant. Only PLS-DA coupled with iPLS was able to classify samples with blends of two adulterants, providing sensitivity values between 100% and 83% at 100% specificity for the three studied classes.

The Classification of Ground Roasted Decaffeinated Coffee Using UV-VIS Spectroscopy and SIMCA Method

In this work, an investigation on the classification between decaffeinated and non- decaffeinated coffee samples using UV-VIS spectroscopy and SIMCA method was investigated. Total 200 samples of ground roasted coffee were used (100 samples for decaffeinated coffee and 100 samples for non-decaffeinated coffee). After extraction and dilution, the spectra of coffee samples solution were acquired using a UV-VIS spectrometer (Genesys™ 10S UV-VIS, Thermo Scientific, USA) in the range of 190-1100 nm. The multivariate analyses of the spectra were performed using principal component analysis (PCA) and soft independent modeling of class analogy (SIMCA). The SIMCA model showed that the classification between decaffeinated and non-decaffeinated coffee samples was detected with 100% sensitivity and specificity.

Classification and Identification of Plant Fibrous Material with Different Species Using near Infrared Technique-A New Way to Approach Determining Biomass Properties Accurately within Different Species.

Plant fibrous material is a good resource in textile and other industries. Normally, several kinds of plant fibrous materials used in one process are needed to be identified and characterized in advance. It is easy to identify them when they are in raw condition. However, most of the materials are semi products which are ground, rotted or pre-hydrolyzed. To classify these samples which include different species with high accuracy is a big challenge. In this research, both qualitative and quantitative analysis methods were chosen to classify six different species of samples, including softwood, hardwood, bast, and aquatic plant. Soft Independent Modeling of Class Analogy (SIMCA) and partial least squares (PLS) were used. The algorithm to classify different species of samples using PLS was created independently in this research. Results found that the six species can be successfully classified using SIMCA and PLS methods, and these two methods show similar results. The identification rates of kenaf, ramie and pine are 100%, and the identification rates of lotus, eucalyptus and tallow are higher than 94%. It is also found that spectra loadings can help pick up best wavenumber ranges for constructing the NIR model. Inter material distance can show how close between two species. Scores graph is helpful to choose the principal components numbers during the model construction.

Screening of adulteration in packaging biocomposites by infrared spectroscopy and chemometrics

Fourier transform infrared spectroscopy coupled with chemometrics was employed to detect packaging polylactic acid-based biocomposite samples adulterated with polypropylene (PP) 30–45% and linear low-density polyethylene 2–10%. Principal component analysis, soft independent modeling of class analogy (SIMCA) and partial least square discriminate analysis (PLS-DA) chemometric techniques were utilized to classify samples in different classes. Totally, 362 samples were modeled in three different classes (two adulterated and one non-adulterated). The obtained results revealed that PLS-DA is the most suitable chemometric approach for prediction of probable adulteration in biocomposite samples with reliable specificity and selectivity. It could provide 99% correct class prediction rate between non-adulterated biocomposite samples and adulterated ones, while SIMCA methods provided 73.33% prediction accuracy in classification.

Fourier Transform Infrared Spectroscopy (FTIR) and Multivariate Analysis for Identification of Different Vegetable Oils Used in Biodiesel Production

The main objective of this study was to use infrared spectroscopy to identify vegetable oils used as raw material for biodiesel production and apply multivariate analysis to the data. Six different vegetable oil sources—canola, cotton, corn, palm, sunflower and soybeans—were used to produce biodiesel batches. The spectra were acquired by Fourier transform infrared spectroscopy using a universal attenuated total reflectance sensor (FTIR-UATR). For the multivariate analysis principal component analysis (PCA), hierarchical cluster analysis (HCA), interval principal component analysis (iPCA) and soft independent modeling of class analogy (SIMCA) were used. The results indicate that is possible to develop a methodology to identify vegetable oils used as raw material in the production of biodiesel by FTIR-UATR applying multivariate analysis. It was also observed that the iPCA found the best spectral range for separation of biodiesel batches using FTIR-UATR data, and with this result, the SIMCA method classified 100% of the soybean biodiesel samples.

Affected States soft independent modeling by class analogy from the relation between independent variables, number of independent variables and sample size.

The aim of study is to introduce method of Soft Independent Modeling of Class Analogy (SIMCA), and to express whether the method is affected from the number of independent variables, the relationship between variables and sample size. Simulation study. SIMCA model is performed in two stages. In order to determine whether the method is influenced by the number of independent variables, the relationship between variables and sample size, simulations were done. Conditions in which sample sizes in both groups are equal, and where there are 30, 100 and 1000 samples; where the number of variables is 2, 3, 5, 10, 50 and 100; moreover where the relationship between variables are quite high, in medium level and quite low were mentioned. Average classification accuracy of simulation results which were carried out 1000 times for each possible condition of trial plan were given as tables. It is seen that diagnostic accuracy results increase as the number of independent variables increase. SIMCA method is a method in which the relationship between variables are quite high, the number of independent variables are many in number and where there are outlier values in the data that can be used in conditions having outlier values.

Near Infrared Spectroscopy Combined with Support Vector Machines as a Process Analytical Chemistry Tool at Petroleum Refineries

Introduction Process control and product quality control in petroleum refineries are often performed by means of on-line analysers which provide real-time information to a central system. This allows the adjustment of process variables if process disturbances or set point tendencies arise that differ from desired values. Analytical methods based on near infrared (NIR) spectroscopy combined with chemometric methods have been used as a tool for process analytical chemistry (PAC). This approach can provide useful information about sample composition at petroleum refineries because the various petroleum fractions and their physico-chemical characteristics are associated with different proportions of n-alkanes, iso-alkanes, cycloalkanes and aromatic compounds present in the fractions. Near infrared spectroscopy is able to distinguish between different contents of C–H bonds of methyl and methylene groups present in these compounds together with N–H, S–H and O–H bonds present in minor quantities. The partial least squares (PLS) algorithm is the one most commonly used in multivariate calibration model development. PLS is a linear method that can model some degree of non-linearity using an appropriate number of latent variables. However, certain applications of the support vector machines (SVM) algorithm have been shown to produce results better than those obtained by PLS. Feedstocks for petroleum refineries are often from different geographic regions and possess quite different characteristics. Likewise, petroleum fractions used in the production of derivatives may vary their characteristic properties over a wide range. It is difficult to include in a calibration model all the variability which may occur in practice in the refining process by means of experimental design and, moreover, complex mixtures such as petroleum fractions may not have a linear relationship with the parameter under study. For these reasons, it becomes necessary to use analytical methods that can provide non-linear calibration models with low prediction errors even for samples which have not been included in the calibration analytical range. One such method uses the SVM algorithm; it is based on statistical learning theory and can provide non-linear calibration models with high generalisation performance. These features make SVM an attractive option for the development of calibration models more effective for on-line analysis of petroleum, petroleum fractions and petroleum derivatives at petroleum refineries. The SVM algorithm was originally developed to solve pattern recognition problems and was subsequently extended to handle regression problems. Support vector machines for classification or support vector classification (SVC) simultaneously minimises the empirical error of classification and maximises the separation margin between classes using an optimal separation hyperplane, leading to a unique solution. One of the major features of SVC models is that they can operate in a kernelinduced feature space allowing non-linear modeling while good generalisation performance can be obtained even with relatively small datasets. These characteristics mean that SVC can provide a better classification performance than linear classification algorithms such as soft independent modeling of class analogy (SIMCA). To deal with regression problems, a modification of the classification algorithm was performed; in support vector regression (SVR), the use of the e-insensitive loss function that limits regression errors and penalises deviations beyond the adjusted limit during model development, helps ensure good performance. Key steps in SVC and SVR model development are the parametric optimisation and appropriate choice of the kernel function. This work reports the performance of SVM applied to NIR spectroscopy data for (1) development of regression and classification models for on-line analysis of petroleum fraction streams and diesel oil at a refinery and (2) compares the SVM predicted results with corresponding data produced by SIMCA and PLS methods.

Application to Classification of Mulberry Leaves using Multivariate Analysis of Proton NMR Metabolomic Data

Recently, NMR-based metabolomic analysis has been used to acquire information based on differentiation among biological samples. In the present study, we examined whether multivariate analysis was able to be applied to natural products and/or material field. Each extraction of 24 leaf samples, divided into six locations from the tip of the stem in each of four strains, was analyzed by pattern recognition methods, known as Principal Component Analysis (PCA) and Soft Independent Modeling of Class Analogy (SIMCA). Twenty-four extracts from mulberry leaf showed independent spectra by 1H NMR. The separation of leaf extraction data due to the difference at six locations was achieved in the PCA score plot as correlation PC1 (86.1%) and PC3 (4.6%) and showed two loading plots, suggesting classification by leaf position as an independent variable in the loading plot. Moreover, the difference among six locations clarified the seven highest discrimination powers by the SIMCA method. Meanwhile, the PCA score plot obtained classification by the variety of mulberry strains with three loading plots, but the SIMCA method did not give a peak by classification.

Pattern Recognition Analysis for Classification of Hypertensive Model Rats and Diurnal Variation Using 1H-NMR Spectroscopy of Urine

Urine samples were collected during the daytime and nighttime from spontaneously hypertensive model rats and normal rats without dosing. The 1H NMR spectra were measured for their urine samples, and analyzed by a pattern recognition method, known as Principal Component Analysis (PCA) and Soft Independent Modeling of Class Analogy (SIMCA). The separation of urinary data due to the diurnal variation (daytime and nighttime) and also to the difference between the two strains of rat was achieved in the PCA score plot. Differences of the urinary profiles in the respective separation were effectively extracted as marker variables by the SIMCA method. NMR measurements coupled with pattern recognition methods provide a straightforward approach to inspect the disease metabolic status and the preliminary screening tool of marker candidates for further development.

A structure–activity relationship study of quinone compounds with trypanocidal activity

A set of 25 quinone compounds with anti-trypanocidal activity was studied by using the density functional theory (DFT) method in order to calculate atomic and molecular properties to be correlated with the biological activity. The chemometric methods principal component analysis (PCA), hierarchical cluster analysis (HCA), stepwise discriminant analysis (SDA), Kth nearest neighbor (KNN) and soft independent modeling of class analogy (SIMCA) were used to obtain possible relationships between the calculated descriptors and the biological activity studied and to predict the anti-trypanocidal activity of new quinone compounds from a prediction set. Four descriptors were responsible for the separation between the active and inactive compounds: T 5 (torsion angle), QTS1 (sum of absolute values of the atomic charges), VOLS2 (volume of the substituent at region B) and HOMO-1 (energy of the molecular orbital below HOMO). These descriptors give information on the kind of interaction that occurs between the compounds and the biological receptor. The prediction study was done with a set of three new compounds by using the PCA, HCA, SDA, KNN and SIMCA methods and two of them were predicted as active against the Trypanosoma cruzi.

SIMCA (Soft Independent Modeling of Class Analogy) Demonstrated with Characterization and Classification of Italian Olive Oil

Abstract The multivariate technique SIMCA (soft independent modeling of class analogy) has been applied to the classification of foodstuffs on the basis of gas chromatographic profiles of some of their constituents. The data set used in this investigation consists of the percentage distribution of 7 fatty acids (7 variables) in 100 samples of virgin olive oil from 2 different regions (2 classes) of Italy, East and West Liguria. The SIMCA method can be used to compute whether an olive oil sample from Liguria originated in the western or eastern part of this region, while 98.8% of samples that do not originate in Liguria are correctly classified as outliers. The developed classification rules are adequate for identifying oils according to their origin. Standard decision diagrams (SDD) are very attractive tools for classification of new samples; the similarity between a new sample and each of the classes is easily computed. Consequently, the SDD visualizes any similarity toward each of the classes, and enables a decision on whether the new sample originates in one of the regions under study.