Fusing 1H NMR and Raman experimental data for the improvement of wine recognition models

被引：9

作者：

Hategan, Ariana Raluca ^{[1
,2
]}

David, Maria ^{[1
,2
]}

Pirnau, Adrian ^{[1
]}

Cozar, Bogdan ^{[1
]}

Cinta-Pinzaru, Simona ^{[2
]}

Guyon, Francois ^{[3
]}

Magdas, Dana Alina ^{[1
,2
]}

机构：

[1] Natl Inst Res & Dev Isotop & Mol Technol, 67-103 Donat St, Cluj Napoca 400293, Romania

[2] Babes Bolyai Univ, Fac Phys, Kogalniceanu 1, Cluj-napoca 400084, Cluj, Romania

[3] Serv Commun Labs, 146 Traverse Charles Susini, F-13388 Marseille, France

来源：

FOOD CHEMISTRY | 2024年 / 458卷

关键词：

Wine authentication; Data fusion; 1H NMR; Raman spectroscopy; Feature selection; CLASSIFICATION; SPECTRA; AUTHENTICATION; NANOPARTICLES; ORIGIN; ACIDS; FOOD;

D O I：

10.1016/j.foodchem.2024.140245

中图分类号：

O69 [应用化学];

学科分类号：

081704 ;

摘要：

The present study proposes the development of new wine recognition models based on Artificial Intelligence (AI) applied to the mid-level data fusion of 1H NMR and Raman data. In this regard, a supervised machine learning method, namely Support Vector Machines (SVMs), was applied for classifying wine samples with respect to the cultivar, vintage, and geographical origin. Because the association between the two data sources generated an input space with a high dimensionality, a feature selection algorithm was employed to identify the most relevant discriminant markers for each wine classification criterion, before SVM modeling. The proposed data processing strategy allowed the classification of the wine sample set with accuracies up to 100% in both cross-validation and on an independent test set and highlighted the efficiency of 1H NMR and Raman data fusion as opposed to the use of a single-source data for differentiating wine concerning the cultivar and vintage.

引用

页数：9

共 47 条

[11] SUPPORT-VECTOR NETWORKS [J].

CORTES, C ;

VAPNIK, V .

MACHINE LEARNING, 1995, 20 (03) :273-297

[12] Can spectroscopy geographically classify Sauvignon Blanc wines from Australia and New Zealand? [J].

Cozzolino, D. ;

Cynkar, W. U. ;

Shah, N. ;

Smith, P. A. .

FOOD CHEMISTRY, 2011, 126 (02) :673-678

[13] Food authentication: Techniques, trends & emerging approaches [J].

Danezis, Georgios P. ;

Tsagkaris, Aristidis S. ;

Camin, Federica ;

Brusic, Vladimir ;

Georgiou, Constantinos A. .

TRAC-TRENDS IN ANALYTICAL CHEMISTRY, 2016, 85 :123-132

[14] Reference database of Raman spectra of biological molecules [J].

De Gelder, Joke ;

De Gussem, Kris ;

Vandenabeele, Peter ;

Moens, Luc .

JOURNAL OF RAMAN SPECTROSCOPY, 2007, 38 (09) :1133-1147

[15]

Eigenvector Research Inc., 2017, Eigenvector Research wiki. Advanced Preprocessing: Variable Scaling

[16]

Eigenvector Research Inc, 2018, EIGENVECTOR RES WIKI

[17] Differentiation of Romanian Wines on Geographical Origin and Wine Variety by Elemental Composition and Phenolic Components [J].

Geana, Elisabeta Irina ;

Marinescu, Adrian ;

Iordache, Andreea Maria ;

Sandru, Claudia ;

Ionete, Roxana Elena ;

Bala, Camelia .

FOOD ANALYTICAL METHODS, 2014, 7 (10) :2064-2074

[18] Wine Analysis and Authenticity Using 1H-NMR Metabolomics Data: Application to Chinese Wines [J].

Gougeon, Louis ;

Da Costa, Gregory ;

Le Mao, Ines ;

Ma, Wen ;

Teissedre, Pierre-Louis ;

Guyon, Francois ;

Richard, Tristan .

FOOD ANALYTICAL METHODS, 2018, 11 (12) :3425-3434

[19] Geographical and varietal origin differentiation of alcoholic beverages through the association between FT-Raman spectroscopy and advanced data processing strategies [J].

Hategan, Ariana Raluca ;

David, Maria ;

Berghian-Grosan, Camelia ;

Magdas, Dana Alina .

FOOD CHEMISTRY-X, 2023, 20

[20] The improvement of honey recognition models built on 1H NMR fingerprint through a new proposed approach for feature selection [J].

Hategan, Ariana Raluca ;

Guyon, Francois ;

Magdas, Dana Alina .

JOURNAL OF FOOD COMPOSITION AND ANALYSIS, 2022, 114

← 1 2 3 4 5 →