Multivariate classification for the direct determination of cup profile in coffee blends via handheld near-infrared spectroscopy.

Published on Jan 15, 2021in Talanta6.057
· DOI :10.1016/J.TALANTA.2020.121526
Michel Rocha Baqueta5
Estimated H-index: 5
,
Aline Coqueiro10
Estimated H-index: 10
+ 1 AuthorsPatrícia Valderrama19
Estimated H-index: 19
Sources
Abstract
Abstract Professional cupping is a reliable methodology for the coffee industry and its professionals. However, it faces barriers for its implementation on an industrial scale. To date, no study has determined a coffee cup profile using a handheld near-infrared (NIR) spectrometer. Therefore, the aim of this study was to evaluate directly cup profiles in roasted and ground coffee blends via handheld NIR spectroscopy combined with partial least squares with discriminant analysis (PLS-DA), in an industrial case study. The sensitivity and specificity of the model obtained ranged from 91–100%, 84–100%, and 73–95% in the training, prediction, and internal cross-validation sets, respectively. These results are therefore promising for the industrial reality and the methodology could assist coffee professionals in their decisions during cup evaluation in further tests. The proposed method is viable for the direct determination of cup profile at industrial scale since it is portable, fast, simple, robust, and less expensive compared to the benchtops equipment.
📖 Papers frequently viewed together
References34
Newest
The present study evaluated the potential of near-infrared (NIR) spectroscopy coupled with partial least squares with discriminant analysis (PLS-DA) for the authentication of organic sugars. A portable NIR equipment was employed in the range from 900 to 1650 nm. Three PLS-DA models were built: the first one for discrimination organic from conventional crystal sugar, a second model for discrimination organic from conventional demerara sugar, and the third one for discrimination of organic from co...
Source
#2Aline CoqueiroH-Index: 10
Last. Patrícia ValderramaH-Index: 19
view all 4 authors...
This research presents the use of near-infrared (NIR) spectroscopy as a fast alternative of conventional methods, suitable for in-line use for quality control in the industrial coffee processing. Chemometric models were constructed from spectra of 217 coffees sampled during the period of 5 months of coffee processing, which demonstrates the viability of the NIR spectroscopy in terms of prediction, since it provides realistic variability in chemometric models. In this work, granulometry, moisture...
Source
#2Aline CoqueiroH-Index: 10
Last. Patrícia ValderramaH-Index: 19
view all 3 authors...
The diversity of compounds and variations in the aroma and flavor of ground and roasted coffee make the sensory evaluation by the "cupping test" a complex task to be performed. A total of 217 commercial coffee samples classified as different beverage type and with different roast degrees were evaluated by official cuppers in the "cupping test" and the responses for sensory attributes were used to verify the correlation to the near-infrared (NIR) spectra. Chemometric models based on partial least...
Source
#1A. Tugnolo (University of Milan)H-Index: 5
#2Roberto Beghi (University of Milan)H-Index: 17
Last. Riccardo Guidetti (University of Milan)H-Index: 19
view all 4 authors...
The aim of this work was to compare two near infrared spectrometers (960–1650 nm) to assess coffee matrices for real-time characterization during processing. A benchtop spectrophotometer built for process measurement, equipped with a rotating acquisition system suitable for in-line analyses (device 1), and a portable spectrophotometer for at-line analyses (device 2) were tested. The experimentation was conducted on green, roasted bean, and ground coffee, relating to three coffee blends, employin...
Source
#1Davide Giacalone (University of Southern Denmark)H-Index: 16
#2Tina Kreuzfeldt Degn (UCPH: University of Copenhagen)H-Index: 2
Last. Morten Münchow (UCPH: University of Copenhagen)H-Index: 5
view all 6 authors...
Abstract The demand for high quality and specialty coffee is increasing worldwide. In order to meet these demands, a more uniform and standardized quality assessment of coffee is essential. The aim of this study was to make a sensory scientific and chemical characterization of common roasting defects in coffee, and to investigate their potential relevance for consumers’ acceptance of coffee. To this end, six time-temperature roasting profiles based on a single origin Arabica bean were developed:...
Source
#1Rafael Carlos Eloy Dias (Zurich University of Applied Sciences/ZHAW)H-Index: 3
#2Patrícia Valderrama (UTFPR: Federal University of Technology - Paraná)H-Index: 19
Last. Chahan Yeretzian (Zurich University of Applied Sciences/ZHAW)H-Index: 33
view all 6 authors...
Abstract Chemical analyses and sensory evaluation are the most applied methods for quality control of roasted and ground coffee (RG). However, faster alternatives would be highly valuable. Here, we applied infrared-photoacoustic spectroscopy (FTIR-PAS) on RG powder. Mixtures of specific defective beans were blended with healthy (defect-free) Coffea arabica and Coffea canephora bases in specific ratios, forming different classes of blends. Principal Component Analysis allowed predicting the amoun...
Source
#1Ana Paula Craig (UFMG: Universidade Federal de Minas Gerais)H-Index: 10
#2Bruno G. Botelho (UFMG: Universidade Federal de Minas Gerais)H-Index: 12
Last. Adriana S. Franca (UFMG: Universidade Federal de Minas Gerais)H-Index: 36
view all 4 authors...
Abstract Sensory (cup) analysis is a reliable methodology for green coffee quality evaluation, but faces barriers when applied to commercial roasted coffees due to lack of information on roasting conditions. The aim of this study was to examine the potential of mid-infrared spectroscopy for predicting cup quality of arabica coffees of different roasting degrees. PCA analysis showed separation of arabica and robusta. A two-level PLS-DA Hierarchical strategy was employed, with coffee being classif...
Source
#1Radigya M. Correia (UFES: Universidade Federal do Espírito Santo)H-Index: 9
#2Flavia Tosato (UFES: Universidade Federal do Espírito Santo)H-Index: 7
Last. Wanderson Romão (UFES: Universidade Federal do Espírito Santo)H-Index: 30
view all 8 authors...
Abstract The use of portable micro-spectrometers such as a micro near infrared region (microNIR) spectrometer is a promising technique for solving analytical problems in several areas of science. This work evaluated the potential of microNIR in quality control of Arabica coffee. Arabica coffee has a high commercial value product, motivating the development of analytical methods with high sensitivity and accuracy for detection of its adulteration. Herein, microNIR was successfully used to determi...
Source
#1Verônica Belchior (UFMG: Universidade Federal de Minas Gerais)H-Index: 3
#2Bruno G. Botelho (UFMG: Universidade Federal de Minas Gerais)H-Index: 12
Last. Adriana S. Franca (UFMG: Universidade Federal de Minas Gerais)H-Index: 36
view all 4 authors...
Abstract Coffee cup quality, determined by the sensory attributes evaluated by professional tasters, is a decisive factor for evaluating coffee, with the “Specialty Coffee Association of America” (SCAA) classification being nowadays considered the most suitable. P anels of trained coffee tasters are used by the industry to describe and evaluate beverage quality, but those evaluations can be subjective and time demanding. Recent studies have demonstrated the potential of spectroscopy-based method...
Source
Last. Fernanda Vitória LeimannH-Index: 17
view all 9 authors...
A quantidade de residuos gerados durante o beneficiamento do cafe no Brasil (principalmente casca) representa aproximadamente 50% da producao. Visando diminuir este problema, o objetivo deste trabalho foi obter diferentes extratos das cascas de cafe, avaliar sua composicao e atividade antimicrobiana. Utilizando extracoes por Soxhlet, com solventes de diferentes polaridades e seletividades e analisando estes extratos por Cromatografia Gasosa acoplada a Espectrometria de Massas e Espectroscopia de...
Source
Cited By5
Newest
#1Leonardo Valderrama (UFSC: Universidade Federal de Santa Catarina)H-Index: 4
Last. Eduardo Carasek (UFSC: Universidade Federal de Santa Catarina)H-Index: 39
view all 3 authors...
Abstract null null Carbendazim (CBZ) is a fungicide employed in grape crop disease controls, and its maximum residue limit in food is regulated by specialized agencies. This study aimed to determine the CBZ content in the grape juices in a semi-quantitative classification model based on portable Ultraviolet–Visible spectroscopy and partial least squares with discriminant analysis. The sensitivity and specificity of the obtained model ranged from 83 to 100%, with the external validation set. Thes...
Source
Currently, many newborns are consuming human milk (HM) donated by nursing mothers, especially those in the neonatal intensive care unit. However, a frequent problem in HM banks is the lack of information about the lactation phase of donated milk (colostrum, transition, or maturity), which makes it more difficult to supply children according to their particular needs. This research aims to develop models based on handheld near-infrared spectroscopy (NIR) coupled with partial least squares with di...
Source
#1Jinming LiuH-Index: 2
#2Shuo JinH-Index: 1
Last. Wenzhe Li (NEAU: Northeast Agricultural University)H-Index: 2
view all 5 authors...
Abstract In this study, a rapid detection method based on near-infrared reflectance spectroscopy was proposed for measuring the contents of cellulose, hemicellulose and lignin in corn stover. In the basis of strategies of variable selection, feature extraction and nonlinear modeling, BiPLS-PCA-SVM was constructed using backward interval partial least squares combined with principal component analysis and support vector machine, which was used to improve the performance of spectral regression cal...
Source
#1Yu-Tang Chang (NTU: National Taiwan University)H-Index: 1
#2Meng‐Chien Hsueh (NTU: National Taiwan University)H-Index: 1
Last. Shih-Fang Chen (NTU: National Taiwan University)H-Index: 1
view all 6 authors...
BACKGROUND Specialty coffee fascinates people with its bountiful flavors. Currently, flavor descriptions of specialty coffee beans are only offered by certified coffee cuppers. However, such professionals are rare, and the market demand is tremendous. The hypothesis of this study was to investigate the feasibility to train machine learning (ML) and deep learning (DL) models for predicting the flavors of specialty coffee using near-infrared spectra of ground coffee as the input. Successful model ...
Source
This website uses cookies.
We use cookies to improve your online experience. By continuing to use our website we assume you agree to the placement of these cookies.
To learn more, you can find in our Privacy Policy.