On the use of counterpropagation artificial neural networks to characterize Italian rice varieties

A counterpropagation artificial neural network (CP-ANN) approach was used to classify 1779 Italian rice samples according to their variety, using physical measurements which are routinely determined for the commercial classification of the product. If compared to the classical Principal Component Analysis, the mapping based on the Kohonen network showed a significantly better representational ability, being able to separate classes which appeared quite undistinguished in the PC space. From the classification and prediction viewpoint, the optimal CP-ANN was able to correctly predict more than 90% of the test set samples.     

Supervised pattern recognition applied to the discrimination of the floral origin of six types of Italian honey samples

In this work a supervised chemometric approach to the discrimination of Italian honey samples from different floral origin is presented. The analytical data of 73 Italian honey samples from six varieties (chestnut, eucalyptus, heather, sulla, honeydew, and wildflower) have been processed by Linear Discriminant Analysis (LDA), using two different variable selection procedures (Fisher F-based and stepwise LDA). Three and two variables, respectively have been necessary to obtain a 100% predictive ability as evaluated by cross-validation. Successively, a class modeling approach has been followed, using UNEQ. The resulting models showed 100% sensitivity and specificity.     

Using liquid chromatography-mass spectrometry based metabolomics to discriminate between cold pressed rice bran oils produced from two different cultivars of Oryza sativa L. ssp. indica in Thailand

A newly developed liquid chromatography-mass spectrometry (LC-MS) method for the analysis of cold pressed rice bran oil (RBO) was established and used to discriminate between RBOs produced from two different cultivars of major Thai fragrant rice species. The cold pressed RBO was prepared using the screw compression method. The LC-MS data were preprocessed with MZmine 2.10 program before evaluating with principal component analysis using SIMCA 13 software. The LC-MS method was able to detect and quantify several kinds of valuable constituents such as fatty acids, vitamin E, and γ-oryzanol. The chromatographic condition was feasible; short time for analysis and simple method were achieved. From score plot and loading plot of principle component analysis (PCA), two rice cultivar samples were clearly separated, and it was revealed that Khao-Hom-Pathum was more suitable than Khao-Hom-Mali for cold pressed RBO production since it contained high total γ-oryzanol and less saturated free fatty acids. As with the fixed price of all the rice brans, this information can be used in order to, if possible, preserve the price of rice brans from different cultivars.     

Discrimination of Ganoderma lucidum according to geographical origin with near infrared diffuse reflectance spectroscopy and pattern recognition techniques

A rapid and nondestructive near infrared (NIR) method combined with chemometrics was used to discriminate Ganoderma lucidum according to cultivation area. Raw, first, and second derivative NIR spectra were compared to develop a robust classification rule. The chemical properties of G. lucidum samples were also investigated to find out the difference between samples from six varied origins. It could be found that the amount of polysaccharides and triterpenoid saponins in G. lucidum samples was considerably different based on cultivation area. These differences make NIR spectroscopic method viable. Principal component analysis (PCA), discriminant partial least-squares (DPLS) and discriminant analysis (DA) were applied to classify the geographical origins of those samples. The results showed that excellent classification could be obtained after optimizing spectral pre-treatment. For the discriminating of samples from three different provinces, DPLS provided 100% correct classifications. Moreover, for samples from six different locations, the correct classifications of the calibration as well as the validation data set were 96.6% using the DA method after the SNV first derivative spectral pre-treatment. Overall, NIR diffuse reflectance spectroscopy using pattern recognition was shown to have significant potential as a rapid and accurate method for the identification of herbal medicines.     

Tracing the origin of extra virgin olive oils by infrared spectroscopy and chemometrics: A case study

In this paper, the potential of coupling mid- and near-infrared spectroscopic fingerprinting techniques and chemometric classification methods for the traceability of extra virgin olive oil samples from the PDO Sabina was investigated. To this purpose, two different pattern recognition algorithm representative of the discriminant (PLS-DA) and modeling (SIMCA) approach to classification were employed. Results obtained after processing the spectroscopic data by PLS-DA evidenced a rather high classification accuracy, NIR providing better predictions than MIR (as evaluated both in cross-validation and on an external test set). SIMCA confirmed these results and showed how the category models for the class Sabina can be rather sensitive and highly specific. Lastly, as samples from two harvesting years (2009 and 2010) were investigated, it was possible to evidence that the different production year can have a relevant effect on the spectroscopic fingerprint. Notwithstanding this, it was still possible to build models that are transferable from one year to another with good accuracy.     

Comparison of supervised pattern recognition methods with McNemar’s statistical test: Application to qualitative analysis of sugar beet by near-infrared spectroscopy

The application of supervised pattern recognition methodology is becoming important within chemistry. The aim of the study is to compare classification method accuracies by the use of a McNemar’s statistical test. Three qualitative parameters of sugar beet are studied: disease resistance (DR), geographical origins and crop periods. Samples are analyzed by near-infrared spectroscopy (NIRS) and by wet chemical analysis (WCA). Firstly, the performances of eight well-known classification methods on NIRS data are compared: Linear Discriminant Analysis (LDA), K-Nearest Neighbors (KNN) method, Soft Independent Modeling of Class Analogy (SIMCA), Discriminant Partial Least Squares (DPLS), Procrustes Discriminant Analysis (PDA), Classification And Regression Tree (CART), Probabilistic Neural Network (PNN) and Learning Vector Quantization (LVQ) neural network are computed. Among the three data sets, SIMCA, DPLS and PDA have the highest classification accuracies. LDA and KNN are not significantly different. The non-linear neural methods give the less accurate results. The three most accurate methods are linear, non-parametric and based on modeling methods. Secondly, we want to emphasize the power of near-infrared reflectance data for sample discrimination. McNemar’s tests compare classification developed with WCA or with NIRS data. For two of the three data sets, the classification results are significantly improved by the use of NIRS data.     

Authentication of vegetable oils on the basis of their physico-chemical properties with the aid of chemometrics

In food production, reliable analytical methods for confirmation of purity or degree of spoilage are required by growers, food quality assessors, processors, and consumers. Seven parameters of physico-chemical properties, such as acid number, colority, density, refractive index, moisture and volatility, saponification value and peroxide value, were measured for quality and adulterated soybean, as well as quality and rancid rapeseed oils. Chemometrics methods were then applied for qualitative and quantitative discrimination and prediction of the oils by methods such exploratory principal component analysis (PCA), partial least squares (PLS), radial basis function-artificial neural networks (RBF-ANN), and multi-criteria decision making methods (MCDM), PROMETHEE and GAIA.In general, the soybean and rapeseed oils were discriminated by PCA, and the two spoilt oils behaved differently with the rancid rapeseed samples exhibiting more object scatter on the PC-scores plot, than the adulterated soybean oil. For the PLS and RBF-ANN prediction methods, suitable training models were devised, which were able to predict satisfactorily the category of the four different oil samples in the verification set. Rank ordering with the use of MCDM models indicated that the oil types can be discriminated on the PROMETHEE II scale. For the first time, it was demonstrated how ranking of oil objects with the use of PROMETHEE and GAIA could be utilized as a versatile indicator of quality performance of products on the basis of a standard selected by the stakeholder. In principle, this approach provides a very flexible method for assessment of product quality directly from the measured data.     

Differentiation of organic and non-organic ewe's cheeses using main mineral composition or near infrared spectroscopy coupled to chemometric tools: a comparative study

Two independent methodologies were investigated to achieve the differentiation of ewes’ cheeses from different systems of production (organic and non-organic). Eighty cheeses (40 organic and 40 non-organic) from two systems of production, two different breeds of ewe, different sizes, seasons (summer and winter) and ripening times up to 9 months were elaborated. Their mineral composition or the information provided by their spectra in the near infrared zone (NIR) coupled to chemometric tools were used in order to differentiate between organic and non-organic cheeses. Main mineral composition (Ca, K, Mg, Na and P) of cheeses and stepwise lineal discriminant analysis were used to develop a discriminant model. The results from canonical standardised coefficients indicated that the most important mineral was Mg (1.725) followed by P (0.764) and K (0.742). The percentage of correctly classified samples was 88% in internal validation and 90% in external validation, selecting Mg, K and P as variables.Spectral information in the NIR zone was used coupled to a discriminant analysis based on a regression by partial least squares in order to obtain a model which allowed a rate of samples correctly classified of 97% in internal validation and 85% in external validation.     

Electronic nose based on metal oxide semiconductor sensors as a fast alternative for the detection of adulteration of virgin olive oils

An “electronic nose” has been used for the detection of adulterations of virgin olive oil. The system, comprising 12 metal oxide semiconductor sensors, was used to generate a pattern of the volatile compounds present in the samples. Prior to different supervised pattern recognition treatments, feature selection techniques were employed to choose a set of optimally discriminant variables. Linear discriminant analysis (LDA), quadratic discriminant analysis (QDA) and artificial neural networks (ANN) were applied. Excellent results were obtained in the differentiation of adulterated and non-adulterated olive oils and it was even possible to identify the type of oil used in the adulteration. Promising results were also obtained as regards quantification of the percentages of adulteration.     

Artificial neural networks study of the catalytic reduction of resazurin: stopped-flow injection kinetic-spectrophotometric determination of Cu(II) and Ni(II)

An artificial neural network (ANN) procedure was used in the development of a catalytic spectrophotometric method for the determination of Cu(II) and Ni(II) employing a stopped-flow injection system. The method is based on the catalytic action of these ions on the reduction of resazurin by sulfide. ANNs trained by back-propagation of errors allowed us to model the systems in a concentration range of 0.5-6 and 1-15 mg l⁻¹ for Cu(II) and Ni(II), respectively, with a low relative error of prediction (REP) for each cation: REP_Cu(II) = 0.85% and REP_Ni(II) = 0.79%. The standard deviations of the repeatability (s_r) and of the within-laboratory reproducibility (s_w) were measured using standard solutions of Cu(II) and Ni(II) equal to 2.75 and 3.5 mg l⁻¹, respectively: s_r[Cu(II)] = 0.039 mg l⁻¹, s_r[Ni(II)] = 0.044 mg l⁻¹, s_w[Ni(II)] = 0.045 mg l⁻¹ and s_w[Ni(II)] = 0.050 mg l⁻¹. The ANNs-kinetic method has been applied to the determination of Cu(II) and Ni(II) in electroplating solutions and provided satisfactory results as compared with flame atomic absorption spectrophotometry method. The effect of resazurin, NaOH and Na₂S concentrations and the reaction temperature on the analytical sensitivity is discussed.     

Application of artificial neural networks as a technique for interference removal: kinetic-spectrophotometric determination of trace amounts of Se(IV) in the presence of Te(IV)

Artificial neural networks (ANNs) are among the most popular techniques for nonlinear multivariate calibration in complicated mixtures using spectrophotometric data. In this study we propose a computer-based method for removing Te(IV) interference in the determination of Se(IV) using artificial neural networks. In this way, an artificial neural network consisting of three layers of nodes was trained by applying a back-propagation learning rule. The resulting RMSE of prediction for selenium was obtained as 0.108.     

Application of the Doehlert experimental design to molecularly imprinted polymers: surface response optimization of specific template recognition as a function of the type and degree of cross-linking

We propose the use of Doehlert’s experimental design, a second-order uniform shell design, for the optimization of molecularly imprinted polymers (MIPs). We have chosen a simple model system where the influence of kind and degree of cross-linking on template recognition was studied using S-propranolol as the template. We found that Doehlert’s design allows—with very few experiments—one to screen the evolution of the binding capacity of a MIP as a function the different parameters, and thus appears to be a powerful means to screen for the best composition and synthesis method for MIPs. We believe that this chemometric tool can significantly accelerate the development of new MIPs as synthetic recognition elements, particularly in the context of a given application, and will be a versatile complement or alternative to first-order designs to fit complex processes. Electronic supplementary material The online version of this article (doi:) contains supplementary material, which is available to authorized users.     

Self and nonself recognition of chiral catalysts: the origin of nonlinear effects in the amino-alcohol catalyzed asymmetric addition of diorganozincs to aldehydes

Asymmetric addition of dialkylzincs to aldehydes in the presence of (2S)-3-exo-(dimethylamino)isoborneol [(S)-DAIB] exhibits various nonclassical phenomena. The enantiomeric excess (ee) of the alkylation product, obtained with partially resolved DAIB, is much higher than that of the chiral amino alcohol, while the rate decreases considerably as the ee of DAIB is lowered. The asymmetric amplification effects reflect the relative turnover numbers of two enantiomorphic catalytic cycles, where an essential feature is the reversible homochiral and heterochiral dimerization of the coexisting enantiomeric DAIB-based Zn catalysts. The interplay between the thermodynamics of the monomer/dimer equilibration and the kinetics of alkylation reaction strongly affect the overall profile of asymmetric catalysis. The self and nonself recognition of the chiral Zn catalysts is a general phenomenon when (S)-DAIB is mixed with its enantiomer, diastereomer, or even an achiral beta-amino alcohol. The degree of nonlinearity is highly affected not only by the structures and purity of catalysts but also by various reaction parameters. The salient features have been clarified on the basis of molecular weight measurements, NMR and X-ray crystallographic studies of organozinc complexes, and kinetic experiments, as well as computer-aided quantitative analysis.     

Rapid identification of the quality decoction pieces by partial least squares ‐based pattern recognition: grade classification of the decoction pieces of Saposhnikovia divaricata

Herbal medicines are commonly used in many countries after they undergo processing. Quality decoction pieces are a guarantee of the efficacy and safety of the herbal medical products. Here, a strategy based on chemical analysis combined with chemometric techniques was proposed for the classification and prediction of the different grades of the decoction pieces. Considering the necessity for a shared and simple method for the grade classification for the public, in this paper, the characterization of the chemical constituents was determined by utilizing high‐performance liquid chromatography (HPLC)/diode array detection. HPLC was first established for the characterization of the chemical constituents of the different grade decoction pieces. Furthermore, a simultaneous quantification of several of the marker compounds in these decoction pieces was obtained. Finally, a partial least squares‐based pattern recognition method was utilized to obtain a predictive model for the grade classification of the decoction pieces. Saposhnikovia divaricata (Turcz.) Schischk was used as a case study. The partial least squares ‐based pattern recognition for the grade classification of the decoction pieces of S. divaricata demonstrated good sensitivity, specificity and prediction performance, which may efficiently validate the identification results of appearance assessment. The proposed strategy is expected to provide a new insight for the grade classification and quality control of the decoction pieces. Copyright © 2016 John Wiley & Sons, Ltd.     

Evaluation of strontium isotope abundance ratios in combination with multi-elemental analysis as a possible tool to study the geographical origin of ciders

In order to evaluate alternative analytical methodologies to study the geographical origin of ciders, both multi-elemental analysis and Sr isotope abundance ratios in combination with multivariate statistical analysis were estimated in 67 samples from England, Switzerland, France and two Spanish regions (Asturias and the Basque Country). A methodology for the precise and accurate determination of the ⁸⁷Sr/⁸⁶Sr isotope abundance ratio in ciders by multicollector inductively coupled plasma mass spectrometry (MC-ICP-MS) was developed. Major elements (Na, K, Ca and Mg) were measured by ICP-AES and minor and trace elements (Li, Be, B, Al, Sc, Ti, V, Cr, Mn, Fe, Co, Ni, Cu, Zn, Ga, As, Se, Rb, Sr, Y, Mo, Cd, Sn, Sb, Cs, Ba, La, Ce, W, Tl, Pb, Bi, Th and U) were measured by ICP-MS using a collision cell instrument operated in multitune mode. An analysis of variance (ANOVA test) indicated that group means for B, Cr, Fe, Ni, Cu, Se, Cd, Cs, Ce, W, Pb, Bi and U did not show any significant differences at the 95% confidence level, so these elements were rejected for further statistical analysis. Another group of elements (Li, Be, Sc, Co, Ga, Y, Sn, Sb, La, Tl, Th) was removed from the data set because concentrations were close to the limits of detection for many samples. Therefore, the remaining elements (Na, Mg, Al, K, Ca, Ti, V, Mn, Zn, As, Rb, Sr, Mo, Ba) together with ⁸⁷Sr/⁸⁶Sr isotope abundance ratio were considered for principal component analysis (PCA) and linear discriminant analysis (LDA). Finally, LDA was able to classify correctly 100% of cider samples coming from different Spanish regions, France, England and Switzerland when considering Na, Mg, Al, K, Ca, Ti, V, Mn, Zn, As, Rb, Sr, Mo, Ba and ⁸⁷Sr/⁸⁶Sr isotope abundance ratio as original variables.     

Trends of the bonding effect on the performance of DFT methods in electric properties calculations: A pattern recognition and metric space approach on some XY2 (X = O,S and Y = H,O, F,S, Cl) molecules

A test set of 10 molecules (open and ring forms of ozone and sulfur dioxide as well as water and hydrogen sulfide and their respective fluoro‐ and chloro‐substituted analogs) of specific atmospheric interest has been formed as to assess the performance of various density functional theory methods in (hyper)polarizability calculations against well‐established ab initio methods. The choice of these molecules was further based on (i) the profound change in the physics between isomeric systems, e.g., open (C_2v) and ring (D_3h) forms of ozone, (ii) the relation between isomeric forms, e.g., open and ring form of sulfur dioxide (both of C_2v symmetry), and (iii) the effect of the substitution, e.g., in fluoro‐ and chloro‐substituted water analogs. The analysis is aided by arguments chosen from the information theory, graph theory, and pattern recognition fields of Mathematics: In brief, a multidimensional space is formed by the methods which are playing the role of vectors with the independent components of the electric properties to act as the coordinates of these vectors, hence the relation between different vectors (e.g., methods) can be quantified by a proximity measure. Results are in agreement with previous studies revealing the acceptable and consistent behavior of the mPW1PW91, B3P86, and PBE0 methods. It is worth noting the remarkable good performance of the double hybrid functionals (namely: B2PLYP and mPW2PLYP) which are for the first time used in calculations of electric response properties. © 2009 Wiley Periodicals, Inc. J Comput Chem 2010     

Use of sequential injection analysis to construct an electronic-tongue: application to multidetermination employing the transient response of a potentiometric sensor array

An electronic tongue based on the transient response of an array of non-specific-response potentiometric sensors was developed. A sequential injection analysis (SIA) system was used in order to automate its training and operation. The use of the transient recording entails the dynamic nature of the sensor's response, which can be of high information content, of primary ions and also of interfering ions; these may better discriminated if the kinetic resolution is added. This work presents the extraction of significant information contained in the transient response of a sensor array formed by five all-solid-state potentiometric sensors. The tool employed was the Fourier transform, from which a number of coefficients were fed into an artificial neural network (ANN) model, used to perform a quantitative multidetermination. The studied case was the analysis of mixtures of calcium, sodium and potassium. Obtained performance is compared with the more traditional automated electronic tongue using final steady-state potentials.