Using pH variations to improve the discrimination of wines by 3D front face fluorescence spectroscopy associated to Independent Components Analysis

Front-face excitation-emission matrix fluorescence spectroscopy combined with interpretable deep learning for the rapid identification of the storage year of Ningxia wolfberry

Ningxia wolfberry stored for many years may be disguised as fresh wolfberry by unscrupulous traders and sold for huge profits. In this work, the front-face excitation-emission matrix (FF-EEM) fluorescence spectroscopy coupled with interpretable deep learning was proposed to identify the storage year of Ningxia wolfberry in a lossless, fast and accurate way. Alternating trilinear decomposition (ATLD) algorithm was used to decompose the three-way data array obtained by Ningxia wolfberry samples, extracting the chemically meaningful information. Meanwhile, a convolutional neural network (CNN) model for the identification of the storage year of Ningxia wolfberry, called EEMnet, was proposed. The model successfully classified wolfberry samples from different storage years by extracting the subtle feature differences of the spectra, and the correct classification rate of the training set, test set and prediction set was more than 98%. In addition, a series of interpretability analyses were implemented to break the "black box" of the deep learning model. These results indicated that the method based on FF-EEM fluorescence spectroscopy combined with EEMnet could quickly and accurately identify the year of Ningxia wolfberry in a green way, providing a new idea for the identification of the storage years of Chinese medicinal materials.

Multispectral fluorescence sensitivity to acidic and polyphenolic changes in Chardonnay wines - The case study of malolactic fermentation

In this study, stationary and time-resolvedfluorescence signatures, were statistically and chemometrically analyzed among three typologies of Chardonnay wines (A, B and C) with the objectives to evaluate their sensitivity to acidic and polyphenolic changes. For that purpose, a dataset was built using Excitation Emission Matrices of fluorescence (N = 103) decomposed by a Parallel Factor Analysis (PARAFAC), andfluorescence decays (N = 22), mathematically fitted, using the conventional exponential modeling and the phasor plot representation. Wine PARAFAC component C4 coupledwith its phasor plot g and s values enable the description of malolactic fermentation (MLF) occurrence in Chardonnay wines. Such proxies reflect wine concentration modifications in total acidity, malic/lactic and phenol acids.Lower g values among fresh MLF + wines compared to MLF- wines are explained by a quenching effect on wine fluorophores by both organic and phenolic acids.The combination of multispectral fluorescence parametersopens a novel routinely implementable methodology to diagnose fermentative processes.

Flavor classification and year prediction of Chinese Baijiu by time-resolved fluorescence

Baijiu is a traditional and popular Chinese liquor with enormous sale potential, which is affected by factors such as flavor and storage time. Chinese Baijiu is a complex and transparent mixture that makes analyzing difficult. The utility of time-resolved fluorescence helped to develop a new method to analyze Baijiu. Forty-two Baijiu samples among six brands with three flavors were prepared, and their fluorescence spectra were analyzed with an excitation light of 374.2 nm. Hexanoic acid and ethyl butyrate were found to have an impact on Baijiu fluorescence. The properties of lifetimes in Baijiu were investigated, and its mechanism was studied by calculations through density function theory. Using parameters of fluorescence lifetimes, Baijiu samples were classified according to their flavors. Additionally, the correlations between fluorescence lifetimes and storage time of Baijiu in Luzhou flavor were obtained, leading to a reliable and efficient method to establish the year forecast model of Chinese Baijiu with a mean error of 2.79 months. It also provides an important reference of the utility of time-resolved fluorescence for quantitative research of multi-component systems.

Spectrofluorometric analysis combined with machine learning for geographical and varietal authentication, and prediction of phenolic compound concentrations in red wine

Fluorescence spectroscopy is rapid, straightforward, selective, and sensitive, and can provide the molecular fingerprint of a sample based on the presence of various fluorophores. In conjunction with chemometrics, fluorescence techniques have been applied to the analysis and classification of an array of products of agricultural origin. Recognising that fluorescence spectroscopy offered a promising method for wine authentication, this study investigated the unique use of an absorbance-transmission and fluorescence excitation emission matrix (A-TEEM) technique for classification of red wines with respect to variety and geographical origin. Multi-block data analysis of A-TEEM data with extreme gradient boosting discriminant analysis yielded an unrivalled 100% and 99.7% correct class assignment for variety and region of origin, respectively. Prediction of phenolic compound concentrations with A-TEEM based on multivariate calibration models using HPLC reference data was also highly effective, and overall, the A-TEEM technique was shown to be a powerful tool for wine classification and analysis.

Geographical origin authentication of southern Brazilian red wines by means of EEM-pH four-way data modelling coupled with one class classification approach

EEM data recorded at different pH values was exploited by MCR-ALS in order to determine qualitative information about Brazilian red wines. In addition, the geographical traceability of wines produced in the Serra Gaúcha (Rio Grande do Sul) was carried out by DD-SIMCA considering 53 samples from the target class and 20 from other producing regions. The fluorescence signal corresponds to 9 EEMs recorded at different pH (3-11), generating four-way data. By MCR-ALS decomposition, eight factors were retrieved and related to typical chemical compounds found in red wine. In addition, the EEM pH data was used to build a one-class classification model, considering that MCR scores and all samples of the target class were properly recognised as belonging to the target class, with maximal sensitivity equal to 1. Samples of the non-target class were also adequately rejected by the model, and the specificity was found to be 0.97.

Improve the performance of independent component analysis by mapping the spectrum to an orthogonal space

Independent Component Analysis (ICA) has attracted chemists recently, for its charm can separate the independent signals from a mixed system and does not need prior knowledge. However, its dissatisfactory performance for the chemical measured signal is still blocking the practicability. Thus, this paper summarized the ICA processing path from the establishment of rectangular coordinates in linear space to the determination of the corresponding relation between the coordinate system and real components. The primary cause of the deviation between the ICA results and the chemical measurements is that the measuring signal was subject to uncertainty. Besides, uncertainty made the deviation of source signal from the statistical independence assumption, or in other words, it appeared to be nonorthogonal. For this key, it proposed to map the measured value to the high-order derivative space, use the derivative to narrow the peak width, reduce the influence of uncertainty, and improve the separation performance of ICA to chemical measurement signal, such as the spectrum. Actual cases of this paper showed that when up to 6th order, the separating results had been perfect for IR spectra, and even for homologs isomers.

Varietal classification of white wines by fluorescence spectroscopy

The Slovak Tokaj region is one of the producers of high-quality white wine having protected designations of origin. The main grape varieties of this region are Furmint, Lipovina and Muscat blanc, which have specific sensory characteristics. This research work presents a strategy for the classification of three mentioned varieties of white wines using fluorescence spectroscopy with chemometrics. Emission and synchronous fluorescence spectra were obtained for bulk as well as diluted samples, principal component analysis (PCA) was applied for exploratory analysis and the scores of the selected PCs were used in linear discriminant analysis (LDA). For undiluted samples, the best PCA-LDA models based on either emission spectra excited at 370 nm or synchronous fluorescence spectra obtained at wavelength difference of 40 and 100 nm provided total correct classifications of 100, 100 and 93% for the calibration, validation and prediction steps, respectively. For diluted samples, the best PCA-LDA models (excitation at 280 nm; wavelength difference of 40 nm) again provided total correct classifications as mentioned above.

Independent components analysis (ICA) at the "cocktail-party" in analytical chemistry

Independent components analysis (ICA) is a probabilistic method, whose goal is to extract underlying component signals, that are maximally independent and non-Gaussian, from mixed observed signals. Since the data acquired in many applications in analytical chemistry are mixtures of component signals, such a method is of great interest. In this article recent ICA applications for quantitative and qualitative analysis in analytical chemistry are reviewed. The following experimental techniques are covered: fluorescence, UV-VIS, NMR, vibrational spectroscopies as well as chromatographic profiles. Furthermore, we reviewed ICA as a preprocessing tool as well as existing hybrid ICA-based multivariate approaches. Finally, further research directions are proposed. Our review shows that ICA is starting to play an important role in analytical chemistry, and this will definitely increase in the future.

Characterization and classification of wines according to geographical origin, vintage and specific variety based on elemental content: a new chemometric approach

A highly informative chemometric approach using elemental data to distinguish and classify wine samples according to different criteria was successfully developed. The robust chemometric methods, such fuzzy principal component analysis (FPCA), FPCA combined with linear discriminant analysis (LDA), namely FPCA-LDA and mainly fuzzy divisive hierarchical associative-clustering (FDHAC), including also classical methods (HCA, PCA and PCA-LDA) were efficaciously applied for characterization and classification of white wines according to the geographical origin, vintage or specific variety. The correct rate of classification applying LDA was 100% in all cases, but more compact groups have been obtained for FPCA scores. A similar separation of samples resulted also when the FDHAC was employed. In addition, FDHAC offers an excellent possibility to associate each fuzzy partition of wine samples to a fuzzy set of specific characteristics, finding in this way very specific elemental contents and fuzzy markers according to the degrees of membership (DOMs).

Rapid detection of three quality parameters and classification of wine based on Vis-NIR spectroscopy with wavelength selection by ACO and CARS algorithms

The feasibility of rapid detection of three quality parameters and classification of wines based on visible and near infrared spectroscopy (Vis-NIRs) was investigated. A modified ant colony optimization (ACO) algorithm for wavelength selection in Vis-NIR spectral analysis was proposed to improve the prediction performance of partial least squares regression (PLSR) model. The result proved that feature wavelengths/variables can be selected by the proposed method for building a high performance PLSR model. The root mean square error of total acid, total sugar and alcohol obtained by ACO-PLS were 0.00122 mol/l, 0.0893 g/l and 0.206 (v/v), respectively. Their correlation coefficients obtained by ACO-PLS reach to 0.973, 0.994 and 0.928, respectively. Compared with full-spectral PLS and PLS based on competitive adaptive reweighted sampling (CARS-PLS) method, the application of ACO wavelength selection provided a notably improved regression model. The prediction results were significantly better than the full-spectral PLS model and slightly better than the CARS-PLS method. Meanwhile, a classification study was also constructed based on the ACO-Principal component analysis (ACO-PCA) model showed that Vis-NIR spectra could be used to classify wines according to the geographical origins. Therefore, it can be concluded that the Vis-NIR spectroscopy technique based on ACO wavelength selection has high potential to differentiate the wine origins and predict the quality parameters in a nondestructive way.

Processing Excitation-Emission Matrix Fluorescence and Total Synchronous Fluorescence Spectroscopy Data Sets with Constraint Randomised Non-negative Factor Analysis: a Novel Fluorescence Based Analytical Procedure to Analyse the Multifluorophoric Mixtures

The present work successfully shows the application of novel chemometric approach constraint randomised non-negative factor analysis (CRNNFA) for the analyses of the composite multidimensional fluorescence data sets. The CRNNFA involves the initialisation of the spectral variables in a constraint fashion thus ensures that algorithm does not wander with chemically and spectro-chemically irrelevant variables. The CRNNFA approach does not require that there must be pure variables for each fluorophores of the multifluorophoric mixture. One of the biggest advantages of CRNNFA is that it does not involve any convergence criteria thus circumventing the premature convergence of the algorithm. The CRNNFA achieves the termination only when the iteration limit is reached. The CRNNFA analysis s carried out under the non-negativity constraints therefore the mathematically retrieved profiles can easily be compared with those obtained experimentally. In the present work, both trilinear as well as non-trilinear multidimensional data sets are subjected to CRNNFA to validate its applicability. Excitation emission matrix fluorescence (EEMF) spectral profiles of Catechol, Hydroquinone, Indole and Tryptophan mixtures is used as the source of trilinear data sets. Total synchronous fluorescence spectroscopy (TSFS) spectral profiles of Benzo[a] Pyrene, Chrysene and Pyrene mixtures are used as the source of non-trilinear data sets. The CRNNFA approach is found to work equally well with trilinear as well with non-trilinear data sets. Thus, CRNFFA clearly does not have any prerequisite in the data structure. The obtained results clearly shows that CRNNFA algorithm in combination with EEMF and TSFS data sets are potential analytical tool for the analysis of complex-multifluorophoric mixtures.