Support vector machines in tandem with infrared spectroscopy for geographical classification of green arabica coffee

Bona, Evandro; Marquetti, Izabele; Link, Jade Varaschim; Makimori, Gustavo Yasuo Figueiredo; Arca, V.; Lemes, André Luis Guimarães; Ferreira, Juliana Mendes Garcia; Scholz, Maria Brígida dos Santos; Valderrama, Patrícia; Poppi, Ronei J.

doi:10.1016/j.lwt.2016.04.048

Cited by 101 publications

(50 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[22] As an alternative analytical approach, the dielectric spectroscopy approach losses the resonant nature of other approaches that have proven to be effective for this type of coffee studies. [30][31][32][33][34] One of the most notable advantages of this approach is that the samples do not require of any sort of previous handling and that the wide frequency range offers the possibility of exploring several behaviors. Consequently, this technology offers an intermediate alternative between data availability and easiness of analysis and use.…”

Section: Resultsmentioning

confidence: 99%

Determination of the complex permittivity of cherry, pulped, green, and roasted coffee using a planar dielectric platform and a coaxial probe between 0.3 and 6 GHz

Velasquez

Peña

Bohórquez

et al. 2018

International Journal of Food Properties

View full text Add to dashboard Cite

Section: Resultsmentioning

confidence: 99%

Determination of the complex permittivity of cherry, pulped, green, and roasted coffee using a planar dielectric platform and a coaxial probe between 0.3 and 6 GHz

Velasquez

Peña

Bohórquez

et al. 2018

International Journal of Food Properties

View full text Add to dashboard Cite

“…On addition, the class distance was determined by considering that each class was bounded by a region of space, which represents a confidence level of 95% (Herrera Alvarez et al, 2017). For the PLS-DA, the number of latent variables was defined using 10-fold cross-validation of calibration samples based on the mean of the areas under the receiver operating characteristic curve (RDC) for each class (Bona et al, 2017). The PLS-DA output was converted into a posteriori probabilities using Bayes' Theorem.…”

Section: Discussionmentioning

confidence: 99%

“…On southern Brazil there are a large number of brands of yerba mate that are commercialized from different regions, and the antioxidant potential of each of these is influenced by the factors mentioned above. Nowadays, the differences in foods that are mainly related to their geographical origin are investigated using the combination of analytical results and multivariate statistical tools (Herrera Alvarez et al, 2017;Bona et al, 2017). This association makes it possible to extract a maximum quantity of information from the dataset and it increases understanding about the data structure (Zielinski et al, 2014b).…”

Section: Introductionmentioning

confidence: 99%

A multivariate approach to differentiate yerba mate (Ilex paraguariensis) commercialized in the southern Brazil on the basis of phenolics, methylxanthines and in vitro antioxidant activity

et al. 2020

Self Cite

View full text Add to dashboard Cite

The consumption of yerba mate beverages is related to several health benefits. These desirable properties are mainly due to the bioactive compounds. However, the levels of those compounds are directly affected by factors such as geographical origin. This study aimed to use chemometrics to evaluate the antioxidant compounds of yerba mate (consumed as chimarrão) marketed in southern Brazil. Neochlorogenic acid and caffeine were the main bioactive compounds found in this type of yerba mate beverage (chimarrão). The dataset was analyzed by chemometrics, and principal component analysis using the first three principal components explained 61.30% of the total variance. Hierarchical cluster analysis suggested three clusters, with cluster 1 containing the majority of the samples from the states of Rio Grande do Sul and Paraná, with higher levels of phenolics, methylxanthines, and antioxidant activity. The supervised methods, soft independent modeling of class analogy (SOMCA) and partial least squares-discriminant analysis (PLS-DA), had similar predictability (≥75% of accuracy) in terms of classifying yerba mate according to different Brazilian regions. Therefore, the chemometric tools used in the current study was suitable to monitor and assess a large variation of the antioxidant composition of yerba mate from different southern Brazilian states.

show abstract

“…These methods are especially useful when there are few samples in each class, presenting high generalization capability and avoiding over-fitting (Bishop, 2006). For SVM, the receiver operating characteristic (ROC) curve for the ith SVM was calculated and the accuracy was calculated according to Bona et al (2017). The training of the SVM models was performed using the radial basis functions kernel (RBF; gamma = 0.045).…”

Section: Discussionmentioning

confidence: 99%

“…For SVM, the receiver operating characteristic (ROC) curve for the i th SVM was calculated and the accuracy was calculated according to Bona et al. (). The training of the SVM models was performed using the radial basis functions kernel (RBF; gamma = 0.045).…”

Section: Methodsmentioning

confidence: 99%

Chemometric Authentication of Brazilian Coffees Based on Chemical Profiling

Monteiro

Santos

Rodionova

et al. 2019

Journal of Food Science

View full text Add to dashboard Cite

In this work, different chemometric tools were compared to classify n = 26 conventional (CONV) and n = 19 organic (ORG) coffees from the main Brazilian producing regions based on the chemical composition, physicochemical properties, and antioxidant activity. Principal component analysis separated ORG and CONV coffees but the distinction among the producing regions of Brazilian coffee was not possible. Partial least squares discriminant analysis classified all ORG and CONV coffees in the external validation. Similarly, linear discriminant analysis was able to discriminate 100% and 81% of ORG and CONV coffees in the external validation, respectively, in which total phenolic content (TPC), ferric reducing antioxidant activity, and caffeic acid were the main discriminant variables. Overall 100% of samples from Paraná, Minas Gerais, and blended samples were correctly classified, where TPC, flavonoids, inhibition of lipid peroxidation, caffeic acid, pH, and soluble solids were the main discriminant variables. Support vector machines classified 95% ORG and 88% CONV, 100% Coffea arabica, and 88% and 78% coffees produced in São Paulo and Minas Gerais. k‐Nearest neighbors was effective in distinguishing 100% CONV, 89% ORG, 100% coffees from São Paulo, and 100% C. arabica coffees. Overall, HPLC data and simple physicochemical parameters allied to chemometrics were effective in authenticating the cultivation system and the botanical origin of Brazilian coffees. Practical Application Coffee adulteration is a serious problem in the food chain as some fraudsters replace coffee powder by other cheaper products. In the case of organic coffee, this scenario is even worse as still there is not a universal method to differentiate conventionally grown coffee from its organic counterpart. In addition, Brazilian coffee is produced in different regions and the commercial value varies. Therefore, we analyzed some physicochemical, chemical, and antioxidant properties of Brazilian coffees from distinct origins and classified the samples using chemometrics. Our approach seems to be interesting for quality control purposes.

show abstract

Support vector machines in tandem with infrared spectroscopy for geographical classification of green arabica coffee

Cited by 101 publications

References 29 publications

Determination of the complex permittivity of cherry, pulped, green, and roasted coffee using a planar dielectric platform and a coaxial probe between 0.3 and 6 GHz

Determination of the complex permittivity of cherry, pulped, green, and roasted coffee using a planar dielectric platform and a coaxial probe between 0.3 and 6 GHz

A multivariate approach to differentiate yerba mate (Ilex paraguariensis) commercialized in the southern Brazil on the basis of phenolics, methylxanthines and in vitro antioxidant activity

Chemometric Authentication of Brazilian Coffees Based on Chemical Profiling

Contact Info

Product

Resources

About